Search

Marine heatwaves (MHWs) have measurable impacts on marine ecosystems and reliant fisheries and associated communities. However, how MHWs translate to changes in fishing opportunities and the displacement of fishing fleets remains poorly understood. Using fishing vessel tracking data from the automatic identification system (AIS), we developed vessel distribution models for two pelagic fisheries targeting highly migratory species, the U.S. Atlantic longline and Pacific troll fleets, to understand how MHW properties (intensity, size, and duration) influence core fishing grounds and fleet displacement. For both fleets, MHW size had the largest influence on fishing ground area with northern fishing grounds gaining and southern fishing grounds decreasing in area. However, fleet displacement in response to MHWs varied between coasts, as the Atlantic longline fleet displaced farther in southern regions whereas the most northern and southern regions of the Pacific troll fleet shifted farther. Characterizing fishing fleet responses to these anomalous conditions can help identify regional vulnerabilities under future extreme events and aid in supporting climate‐readiness and resilience in pelagic fisheries. [ABSTRACT FROM AUTHOR]

Successful management of imperilled anadromous salmon stocks requires understanding how salmon will respond to a changing climate across their extensive ranges. Though largely unused for anadromous salmon to date, environmental niche models (ENMs) can provide a strong foundation for estimating where and how much habitat will likely remain favourable. We applied a comprehensive suite of ENM statistical approaches to five Pacific salmon species, focusing on freshwater spawning and natal rearing habitat as not only critical for population survival, but also highly susceptible to a changing climate. We developed ENMs for spawning ranges across British Columbia (BC), Canada, and western US, and projected future scenarios for BC. Projections indicated net expansion of favourable spawning habitat across species in BC, with the most change occurring by 2060. However, shifts in favourable habitat varied greatly geographically and by species, with notable reductions in coastal and southern interior streams. Our results provide a basis for identifying important changes in spawning and natal rearing habitat conditions to help inform priorities for restoration and protection actions. [ABSTRACT FROM AUTHOR]

Identifying threatened ecosystem types is fundamental to conservation and management decision‐making. When identification relies on expert judgment, decisions are vulnerable to inconsistent outcomes and can lack transparency. We elicited judgements of the occurrence of a widespread, critically endangered Australian ecosystem from a diverse pool of 83 experts. We asked 4 questions. First, how many experts are required to reliably conclude that the ecosystem is present? Second, how many experts are required to build a reliable model for predicting ecosystem presence? Third, given expert selection can narrow the range opinions, if enough experts are selected, do selection strategies affect model predictions? Finally, does a diverse selection of experts provide better model predictions? We used power and sample size calculations with a finite population of 200 experts to calculate the number of experts required to reliably assess ecosystem presence in a theoretical scenario. We then used boosted regression trees to model expert elicitation of 122 plots based on real‐world data. For a reliable consensus (90% probability of correctly identifying presence and absence) in a relatively certain scenario (85% probability of occurrence), at least 17 experts were required. More experts were required when occurrence was less certain, and fewer were needed if permissible error rates were relaxed. In comparison, only ∼20 experts were required for a reliable model that could predict for a range of scenarios. Expert selection strategies changed modeled outcomes, often overpredicting presence and underestimating uncertainty. However, smaller but diverse pools of experts produced outcomes similar to a model built from all contributing experts. Combining elicited judgements from a diverse pool of experts in a model‐based decision support tool provided an efficient aggregation of a broad range of expertise. Such models can improve the transparency and consistency of conservation and management decision‐making, especially when ecosystems are defined based on complex criteria. [ABSTRACT FROM AUTHOR]

Psycholinguistic studies have shown that there are many variables implicated in language comprehension and production. At the lexical level, subjective age of acquisition (AoA), the estimate of the age at which a word is acquired, is key for stimuli selection in psycholinguistic studies. AoA databases in English are often used when testing a variety of phenomena in second language (L2) speakers of English. However, these have limitations, as the norms are not provided by the target population (L2 speakers of English) but by native English speakers. In this study, we asked native Spanish L2 speakers of English to provide subjective AoA ratings for 1604 English words, and investigated whether factors related to 14 lexico-semantic and affective variables, both in Spanish and English, and to the speakers' profile (i.e., sociolinguistic variables and L2 proficiency), were related to the L2 AoA ratings. We used boosted regression trees, an advanced form of regression analysis based on machine learning and boosting algorithms, to analyse the data. Our results showed that the model accounted for a relevant proportion of deviance (58.56%), with the English AoA provided by native English speakers being the strongest predictor for L2 AoA. Additionally, L2 AoA correlated with L2 reaction times. Our database is a useful tool for the research community running psycholinguistic studies in L2 speakers of English. It adds knowledge about which factors—linked to the characteristics of both the linguistic stimuli and the speakers—affect L2 subjective AoA. The database and the data can be downloaded from: https://osf.io/gr8xd/?view_only=73b01dccbedb4d7897c8d104d3d68c46. [ABSTRACT FROM AUTHOR]

Aim: Spatially explicit protections of coastal habitats determined on the current distribution of species and ecosystems risk becoming obsolete in 100 years if the movement of species ranges outpaces management action. Hence, a critical step of conservation is predicting the efficacy of management actions in future. We aimed to determine how foundational, habitat‐building species will respond to climate change in Fiji. Location: The Republic of Fiji. Methods: We develop species distribution models (SDMs) using MaxEnt, General Additive Models and Boosted Regression Trees and publicly available data from the Global Biodiversity Information Facility to predict changes in distribution of suitable habitat for mangrove forests, coral habitat, seagrass meadows and critical fisheries invertebrates under several IPCC climate change scenarios in 2070 or 2100. We then overlay predicted distribution models onto existing Fijian protected area network to assess whether today's conservation measures will afford protection to tomorrow's distributions. Results: We found that mangrove suitability is projected to decrease along the Coral Coast and increase northward towards the Yasawa Islands due to precipitation changes. The response of seagrass meadows was predicted to be inconsistent and dependent on the climate scenario. Meanwhile, suitability for coral reefs was not predicted to decline significantly overall. The mangrove crab Scylla serrata, an important resource for fisherwomen in Fiji, is projected to increase in habitat suitability while economically important sea cucumber species will have highly variable responses to climate change. Main conclusions: Species distribution models are a critical tool for conservation managers, as linking spatial distribution data with future climate change scenarios can aid in the creation and resiliency of protected area programmes. New protected area designations should consider the future distribution of species to maximize benefits to those taxa. [ABSTRACT FROM AUTHOR]

There is increasing interest in utilizing the high carbon sequestration capacity of wetlands as a rationale for their restoration, but this requires careful assessment of their greenhouse gas (GHG) fluxes. We used a spatially extensive sampling approach across salinity gradients and management regimes (disturbed, restored, and reference) in 22 wetland sites across two Oregon, USA estuaries, Tillamook and Coos Bays, to measure fluxes of methane (CH4), ecosystem respiration as carbon dioxide (CO2), and nitrous oxide (N2O) over 1 year and related them to environmental forcing variables. Boosted regression tree (BRT) models explained drivers of GHG fluxes reasonably well despite highly nonlinear and interactive relationships and many flux measurements below detection. We used the BRT models to predict annual GHG fluxes in a subset of restored and reference sites where continuous environmental data were recorded and compared them to previously published soil carbon sequestration rates. Most sites had net removal of CO2-equivalents from the atmosphere over both 20 and 100 year timeframes. Our results show that a spatially extensive GHG flux sampling scheme and machine-learning statistical techniques can be used to estimate GHG fluxes in other current and former wetlands within the region if environmental data are collected at a spatial resolution that reflects site variability and at sufficient duration to reflect seasonality (i.e., at least one full year). Such an approach can save time and money in determining the feasibility of wetland restoration as a climate mitigation strategy. We use our results to suggest wetland restoration strategies that optimize climate benefits. [ABSTRACT FROM AUTHOR]

Conservation of threatened species and anthropogenic threat mitigation commonly rely on spatially managed areas selected according to habitat preference. Since the impact of threats can be behaviour‐specific, such information could be incorporated into spatial management to improve conservation outcomes. However, collecting spatially explicit behavioural data is challenging.Using multi‐sensor biologging tags containing high‐resolution movement sensors (e.g. accelerometer, magnetometer, GPS) and animal‐borne video cameras, combined with supervised machine learning, we developed a method to automatically detect and geolocate typically ambiguous behaviours for the poorly understood flatback turtle Natator depressus. Subsequently, we evaluated behaviour‐specific spatiotemporal patterns of habitat use.Boosted regression trees successfully identified the presence of foraging and resting in 7074 dives (AUC > 0.9), using dive features representing characteristics of locomotory activity, body posture, and three‐dimensional dive paths validated by ancillary video data. Foraging was characterised by dives with longer duration, variable depth, tortuous bottom phases; resting was characterised by dives with decreased locomotory activity and longer duration bottom phases.Foraging and resting showed minimal spatial segregation based on 50% and 95% utilisation distributions. Expected diel patterns of behaviour‐specific habitat use were superseded by the extreme tides at the near‐shore study site. Turtles rested in areas close to the subtidal and intertidal boundary within larger overlapping foraging areas, allowing efficient access to intertidal food resources upon inundation at high tides when foraging was ~25% more likely.Synthesis and applications. Using supervised machine learning and biologging tools, we show the potential for dynamic spatial management of flatback turtles to mitigate behaviour‐specific threats by prioritising protection of important locations at pertinent times. Although results are a species‐specific response to a super‐tidal environment, our approach can be generalised to a broad range of taxa and study systems, facilitating a conceptual advance in spatial management. [ABSTRACT FROM AUTHOR]

Aim: Large marine predators, such as cetaceans and sharks, play a crucial role in maintaining biodiversity patterns and ecosystem function, yet few estimates of their spatial distribution exist. We aimed to determine the species richness of large marine predators and investigate their fine‐scale spatiotemporal distribution patterns to inform conservation management. Location: The Hauraki Gulf/Tīkapa Moana/Te Moananui‐ā‐Toi, Aotearoa/New Zealand. Methods: We conducted a replicate systematic aerial survey over 12 months. Flexible machine learning models were used to explore relationships between large marine predator occurrence (Bryde's whales, common and bottlenose dolphins, bronze whaler, pelagic and immature hammerhead sharks) and environmental and biotic variables, and predict their monthly distribution and associated spatially explicit uncertainty. Results: We revealed that temporally dynamic variables, such as prey distribution and sea surface temperature, were important for predicting the occurrence of the study species and species groups. While there was variation in temporal and spatial distribution, predicted richness peaked in summer and was the highest in coastal habitats during that time, providing insight into changes in distributions over time and between species. Main Conclusions: Temporal changes in distribution are not routinely accounted for in species distribution studies. Our approach highlights the value of multispecies surveys and the importance of considering temporally variable abiotic and biotic drivers for understanding biodiversity patterns when informing ecosystem‐scale conservation planning and dynamic ocean management. [ABSTRACT FROM AUTHOR]

Louisiana is facing a land loss crisis with 5,000 km2 lost since the 1930s, and another 10,000 km2 may disappear over the next 50 years. In response, the state developed a Comprehensive Master Plan for a Sustainable Coast, which includes predictions for how wildlife species respond to futures with or without restoration action. However, the 2017 Master Plan did not include a bird species representative of brackish or freshwater wetland habitats. Our objective therefore was to evaluate the potential for the Bald Eagle (Haliaeetus leucocephalus) to serve as an indicator of freshwater wetland health, and to develop a model to predict Bald Eagle responses to land cover change 20 and 50 years into the future, with or without restoration action. Using nest location data collected by the Louisiana Department of Wildlife and Fisheries from the Barataria Basin, we modeled the relationship between Bald Eagle nest occurrence and land cover using boosted regression trees. Model performance was strong, explaining 54.4 ± 0.1% of the deviance in nest occurrence, and showed that Bald Eagle nests were more common in areas with greater fresh forested wetland, freshwater marsh, and flotant marsh land cover. Future suitability for nesting Bald Eagles was higher in 20 and 50 years with restoration action compared to without, although suitability in both years was lower than contemporary suitability, regardless of restoration action. Our model suggests that comprehensive restoration action is needed, including the implementation of Mississippi River diversions, to sustain high densities of nesting Bald Eagles in coastal Louisiana. [ABSTRACT FROM AUTHOR]

Pathogens can spill over and infect new host species by overcoming a series of ecological and biological barriers. Hendra virus (HeV) circulates in Australian flying foxes and provides a data‐rich study system for identifying environmental drivers underlying spillover events. The frequency of spillover events to horses has varied interannually since the virus was first discovered in 1994. These observations suggest that HeV spillover events are driven, in part, by environmental factors, including loss of flying fox habitat and climate variability.We explicitly examine the impact of environmental variation on the risk of HeV spillover at three spatial scales relevant to this system. We use a dataset of 60 spillover events and boosted regression tree methods to identify environmental features (including concurrent and lagged temperature, rainfall, vegetation indices, land cover, and climate indices) at three spatial scales (1‐km, 20‐km, 100‐km radii) associated with horse contacts and reservoir species ecology.We find that temperature, local (1‐km radius) human population density, and landscape (100‐km radius) forest cover and pasture are the most influential environmental features associated with HeV spillover risk. By including multiple spatial scales and temporal lags in environmental features, we can more accurately quantify risk across space and time than with models that use a single scale. For example, high quality vegetation at the local scale and within a foraging radius (20‐km) in the concurrent month and previous years, combined with poorer quality vegetation at the landscape scale in the concurrent month increase risk of HeV spillover. These and other environmental associations likely influence the dynamic foraging behaviour of reservoir flying foxes and drive contacts that facilitate spillover into horse populations.Synthesis and application: Current management of HeV spillover focuses on local‐scale interventions – primarily through vaccination and detection of infected horses. Our study finds that HeV spillover risk is also driven by environmental changes over much larger scales and demonstrates management practices would benefit from incorporating landscape interventions alongside local interventions. [ABSTRACT FROM AUTHOR]

Microclimate research gained renewed interest over the last decade and its importance for many ecological processes is increasingly being recognized. Consequently, the call for high‐resolution microclimatic temperature grids across broad spatial extents is becoming more pressing to improve ecological models. Here, we provide a new set of open‐access bioclimatic variables for microclimate temperatures of European forests at 25 × 25 m2 resolution. [ABSTRACT FROM AUTHOR]

Optimizing the configuration of green–blue spaces is crucial in mitigating the urban heat island effect. However, many existing studies neglect to consider the synergistic cooling effect of green–blue space and its spatial comparison, focusing instead on individual ecological elements of green space or water bodies. Additionally, the relative importance of different configuration indicators and their marginal effects on the cooling effect of green–blue space remain unclear, with an identified need for the quantification of indicator thresholds for maximizing the cooling effect. To address these gaps, this study investigated green–blue spaces in 30 urban waterfront communities located in Kunshan City, Jiangsu Province, China, and measured the scale, distribution, morphology, green–blue relationship, and built environment of these spaces. To determine the cooling effect, maximum air temperature and mean cold island intensity were measured using ENVI-met simulations. Correlation analyses and boosted regression trees (BRT) were utilized to identify the configuration indicators that affect the cooling effect and their action threshold. The results show that green space distribution and water body shape are the most important features affecting the maximum air temperature, with green space patch density (PD) and water landscape shape index (LSI) contributing 21.3% and 20.9% to the reduction in temperature, while the thresholds are 550 and 4.2, respectively. The contribution of green–blue space percentage is critical in raising urban cold island intensity, with threshold effects at 43%. These findings provide practical guidance for the efficient exploitation of the synergistic cooling effects of green–blue space and enhancement of climate resilience in coastal cities. [ABSTRACT FROM AUTHOR]

The coexistence of distinct alternative mating strategies (AMS) is often explained by mechanisms involving trade‐offs between reproductive traits and lifetime fitness; yet their relative importance remains poorly understood. Here, we used an established individual‐based, spatially explicit model to simulate bull trout (Salvelinus confluentus) in the Skagit River (Washington, USA) and investigated the influence of female mating preference, sneaker‐specific mortality, and variation in age‐at‐maturity on AMS persistence using global sensitivity analyses and boosted regression trees. We assumed that two genetically fixed AMS coexisted within the population: sneaker males (characterized by younger age‐at‐maturity, greater AMS‐specific mortality, and lower reproductive fitness) and territorial males. After 300 years, variation in relative sneaker success in the system was explained by sneaker males' reproductive fitness (72%) and, to a lesser extent, the length of their reproductive lifespan (21%) and their proportion in the initial population (8%). However, under a wide range of parameter values, our simulated scenarios predicted the extinction of territorial males or their persistence in small, declining populations. Although these results do not resolve the coexistence of AMS in salmonids, they reinforce the importance of mechanisms reducing sneaker's lifetime reproductive success in favoring AMS coexistence within salmonid populations but also limit the prediction that, without any other selective mechanisms at play, strong female preference for mating with territorial males and differences in reproductive lifespan allow the stable coexistence of distinct AMS. [ABSTRACT FROM AUTHOR]

Scientific prediction of the penetration rate (PR) of tunnel boring machines (TBMs) is of great significance to the selection of tunnel construction methods, the prediction of construction progress, and the evaluation of benefits. In view of the high nonlinearity, fuzziness, and complexity of the TBM excavation process, this paper attempts to present a new algorithm that integrates partial least squares regression (PLSR) with boosted regression trees (BRT) for predicting the PR of TBMs. For this purpose, 150 datasets were obtained from the Lanzhou water conveyance tunnel project in China. Six impact factors were selected as the input layers of the proposed model by single-factor correlation analysis. To develop the PLSR-BRT model, two principal components of the influencing parameters were extracted via the PLSR method, and the BRT algorithm was employed to establish the predictive model. In addition, other models such as PLSR back propagation neural network (BPNN), BRT, PLSR, support vector regression (SVR), and artificial neural network (ANN) were adapted for use in this problem to verify the predictive accuracy of the proposed model. The results demonstrated that the PLSR-BRT model achieved the best predictive performance compared with the other models, with coefficient of determination value (R2) and root mean square error (RMSE) of 0.96 and 1.78, respectively, for the testing set. The PLSR-BRT model can maximally avoid both overfitting and inadequate fitting. In view of engineering applications, the complexity and redundancy of the field dataset can be solved via reducing the dimensionality of input parameters, and the training samples could be expanded by a boosted method so that the discontinuously acquired geological parameters are unable to restrain the model performance. This method serves as an effective approach for TBM PR prediction and has excellent potential for a variety of scientific and engineering applications. [ABSTRACT FROM AUTHOR]

Lianas (woody vines) are a key component of tropical forests, known to reduce forest carbon storage and sequestration and to be increasing in abundance. Analysing how and why lianas are distributed in forest canopies at landscape scales will help us determine the mechanisms driving changes in lianas over time. This will improve our understanding of liana ecology and projections of tropical forest carbon storage now and into the future. Despite competing hypotheses on the mechanisms driving spatial patterning of lianas, few studies have integrated multiple tree‐level biotic and abiotic factors in an analytical framework. None have done so in the Palaeotropics, which are biogeographically and evolutionarily distinct from the Neotropics, where most research on lianas has been conducted.We used an unoccupied aerial system (UAS; drone) to assess liana load in 50‐ha of Palaeotropical forest canopy in Southeast Asia. We obtained data on hypothesised drivers of liana spatial distribution in the forest canopy, including disturbance, tree characteristics, soil chemistry and topography, from the UAS, from airborne LiDAR and from ground surveys. We integrated these in a comprehensive analytical framework to extract variables at an individual‐tree level and evaluated the relative strengths of the hypothesised drivers and their ability to predict liana distributions through boosted regression tree (BRT) modelling.Tree height and distance to canopy gaps were the two most important predictors of liana load, with relative contribution values in BRT models of 34.60%–45.39% and 7.93%–10.19%, respectively. Our results suggest that taller trees were less often and less heavily infested by lianas than shorter trees, opposite to Neotropical findings. Lianas also occurred more often, and to a greater extent, in tree crowns close to canopy gaps and to neighbouring trees with lianas in their crown.Synthesis. Despite their known importance and prevalence in tropical forests, lianas are not well understood, particularly in the Palaeotropics. Examining 2428 trees across 50‐ha of Palaeotropical forest canopy in Southeast Asia, we find support for the hypothesis that canopy gaps promote liana infestation. However, we also found that liana presence and load declined with tree height, which is opposite to well‐established Neotropical findings. This suggests a fundamental difference between Neotropical and Southeast Asian forests. Considering that most liana literature has focused on the Neotropics, this highlights the need for additional studies in other biogeographic regions to clarify potential differences and enable us to better understand liana impacts on tropical forest ecology, carbon storage and sequestration. [ABSTRACT FROM AUTHOR]

The PM10 concentration is subject to significant changes brought on by both gaseous and meteorological variables. The aim of this research was to explore the performance of a hybrid model combining the support vector machine (SVM) and the boosted regression trees (BRT) technique in predicting the PM10 concentration for 3 consecutive days. The BRT model was trained by utilizing maximum daily data in the cities of Alor Setar, Klang, and Kuching from the years 2002 to 2017. The SVM–BRT model can optimize the number of predictors and predict PM10 concentration; it was shown to be capable of predicting air pollution based on the models' performance with NAE (0.15–0.33), RMSE (10.46–32.60), R2 (0.33–0.70), IA (0.59–0.91), and PA (0.50–0.84). This was accomplished while saving training time by reducing the feature size given in the data representation and preventing learning from noise (overfitting) to improve accuracy. This knowledge establishes the foundation for the development of efficient methods to prevent and/or minimize the health effects of PM10 exposure on one's health. [ABSTRACT FROM AUTHOR]

Deep‐water corals are protected in the seas around New Zealand by legislation that prohibits intentional damage and removal, and by marine protected areas where bottom trawling is prohibited. However, these measures do not protect them from the impacts of a changing climate and ocean acidification. To enable adequate future protection from these threats we require knowledge of the present distribution of corals and the environmental conditions that determine their preferred habitat, as well as the likely future changes in these conditions, so that we can identify areas for potential refugia. In this study, we built habitat suitability models for 12 taxa of deep‐water corals using a comprehensive set of sample data and predicted present and future seafloor environmental conditions from an earth system model specifically tailored for the South Pacific. These models predicted that for most taxa there will be substantial shifts in the location of the most suitable habitat and decreases in the area of such habitat by the end of the 21st century, driven primarily by decreases in seafloor oxygen concentrations, shoaling of aragonite and calcite saturation horizons, and increases in nitrogen concentrations. The current network of protected areas in the region appear to provide little protection for most coral taxa, as there is little overlap with areas of highest habitat suitability, either in the present or the future. We recommend an urgent re‐examination of the spatial distribution of protected areas for deep‐water corals in the region, utilising spatial planning software that can balance protection requirements against value from fishing and mineral resources, take into account the current status of the coral habitats after decades of bottom trawling, and consider connectivity pathways for colonisation of corals into potential refugia. [ABSTRACT FROM AUTHOR]

Ciliates represent a crucial link between phytoplankton and bacteria and mesozooplankton in pelagic food webs, but little is known about the processes influencing the dynamics of individual species. Using long-term, high-frequency observations, we compared the diversity and the temporal variability in biomass and species composition of the ciliate community in large, deep, mesotrophic Lake Constance to that of the phytoplankton and rotifer communities in the same lake. Furthermore, we used boosted regression trees to evaluate possible environmental predictors (temperature, three prey groups, four predator/competitor groups) influencing ciliate net growth. The biomass of all ciliate species showed a common, recurrent seasonal pattern, often with peaks in spring and summer. The ciliate community was more diverse than the rotifer community, exhibited highly synchronous dynamics and its species were regularly encountered during the season. The top-down control by copepods likely contributes to the ciliates' synchronized decline prior to the clear-water phase when food concentration is still high. The high temporal autocorrelation of the ciliate biomasses together with the inter-annual recurrent seasonal patterns and the low explanatory power of the environmental predictors suggest that the dynamics of individual ciliate species are strictly controlled, yet it remains difficult to determine the responsible factors. [ABSTRACT FROM AUTHOR]

Aim: Over the past 50 years, anthropogenic activities have led to the disappearance of approximately one‐third of the world's mangrove forests and their associated ecosystem services. The synergetic combined effect of projected climate change is likely to further impact mangroves in the years to come, whether by range expansions associated with warming at higher latitudes or large‐scale diebacks linked to severe droughts. We provide an estimate of future changes in the extent and aboveground biomass (AGB) of mangrove forests at global scales by considering contrasting Representative Concentration Pathway scenarios (decade 2090–2100 under RCP 2.6 in line with the Paris Agreement expectations, and RCP 8.5 of higher emissions). Location: Global. Methods: Boosted regression trees fitted occurrence and AGB of mangroves against high‐resolution biologically meaningful data on air temperature, precipitation, wave energy, slope and distance to river Deltas. Results: On the global scale, models produced for present‐day conditions retrieved high accuracy scores and estimated a total area of 12,780,356 ha and overall biomass of 2.29 Pg, in line with previous estimates. Model projections showed poleward shifts along temperate regions, which translated into comparable gains in total area, regardless of the RCP scenario (area change RCP 2.6: 17.29%; RCP 8.5: 15.77%). However, biomass changes were dependent on the emission scenario considered, remaining stable or even increasing under RCP 2.6, or undergoing severe losses across tropical regions under RCP 8.5 (overall biomass change RCP 2.6: 12.97%; RCP 8.5: −11.51%). Such losses were particularly aggravated in countries located in the Tropical Atlantic and Eastern Pacific, and the Western and Eastern Indo‐Pacific regions (regions with losses above ~20% in overall biomass). Conclusions: Our global estimates highlight the potential effect of future climate changes on mangrove forests and how broad compliance with the Paris Agreement may counteract severe trajectories of loss. The projections made, also provided at the country level, serve as new baselines to evaluate changes in mangrove carbon sequestration and ecosystem services, strongly supporting policy‐making and management directives, as well as to guide restoration actions considering potential future changes in niche availability. [ABSTRACT FROM AUTHOR]

Ecological monitoring is critical for conservation efforts, particularly in marine ecosystems. Recently, greater emphasis on analyses of data resultant from long‐term ecological research has allowed for broader questions pertaining to climate change, species range shifts and reproductive phenology to be assessed, which may improve ecosystem management. Data collected via ecological monitoring, however, often feature strong class imbalances, complicating the development of models to predict such events.Here, we propose two modelling frameworks—a boosted regression tree (BRT) model and an artificial neural network (ANN)—for predicting exceptionally rare aggregatory behaviour of bull, Carcharhinus leucas and blacktip sharks, C. limbatus along the Gulf coast of Texas.In tandem with aggressive techniques for handling zero‐inflated data, both methods produced accurate predictions of aggregations of three or more individuals in one survey event, with the BRT outperforming the ANN in minimizing type I error. Additionally, both models maintained relatively high area under the receiver operating characteristic (ROC AUC) values when the threshold for defining aggregative behaviour was raised, though there was a measurable drop‐off in the precision‐recall (PR) AUC at each successive threshold increase.These results provide support for both modelling approaches as highly viable in generating predictions based on monitoring data, even in situations where negative cases outweigh positive cases by more than 10‐fold. This is promising for conservation and management of species that exhibit biologically and ecologically significant, but rare, behaviours like aggregations, and species that are rare in abundance and thus vulnerable to future declines. More accurately predicting aggregation events provides the information necessary to improve the protection of species that gather during key life‐history events (e.g. mating, parturition, migration), and assess the spatiotemporal consistency of such events, thereby improving the efficacy of adaptive management.Synthesis and applications. Conservation and management programmes serve a critical role in maintaining the health of ecosystems, and regularly make use of ecological monitoring to collect data relevant to population studies. In marine systems, particularly, monitoring is often expensive and time‐consuming, which can result in incomplete or sparse datasets. Especially where an ecological event of interest is rare, subsequent analyses are particularly affected by the many limitations of zero‐inflated datasets. When training predictive models to classify these events, special care must be taken to avoid simply predicting negative events in every case. Here, we propose and compare two machine learning approaches: gradient boosting and the artificial neural network (ANN), to predict aggregatory behaviour of two shark species: bull, Carcharhinus leucas and blacktip sharks, C. limbatus in the Gulf of Mexico. Applied to a large dataset considering many spatial and environmental variables, and in tandem with negative case downsampling, our results support the application of each method to improve analyses of sparse monitoring datasets, with the gradient boosting machine performing particularly well in classifying positive cases. [ABSTRACT FROM AUTHOR]

Questions: (1) What can be learned by extending a national classification into unsampled forest types? (2) Are both remotely sensed and environmental predictors needed to model and map associations? (3) For mapping, are LiDAR-generated canopy structure parameters or reflectance from spectral imagery more useful? (4) How can we assess uncertainty of a final map? Location: Warawara Forest, Northland, New Zealand. Methods: We sampled 205 vegetation plots and assigned them to an existing national classification using the fuzzy classification framework of noise clustering. Plots too distinct to be assigned were used to define new associations. We produced spatial models of each association using boosted regression trees. Predictors included 11 environmental, 11 canopy reflectance, and 17 canopy structure variables. We created a composite map by assigning each map pixel to the association with the highest occurrence probability. We evaluated uncertainty by examining locations where no class was predicted with probability above 0.2 and by creating a confusion map based on entropy. Results: Forty-five plots were assigned to six of 79 existing national associations and 147 plots were used to define two new forest associations. Three shrubland types are widespread nationally, whereas two young forest types are northern. Three mature forest types are narrowly distributed nationally, with the new "High-elevation hardwood forest" largely restricted to Warawara Forest. Three associations were mapped using remotely sensed predictors alone, whereas two also required environmental predictors. Overall, canopy reflectance predictors explained more deviance than canopy structure. Examining locations where no association was predicted well and where multiple associations were predicted equally showed areas mapped as younger forests to have greatest uncertainty. Conclusions: In answering our questions, we present a vegetation classification and map for Warawara Forest that provides a framework to guide the indigenous people's management responses to threats to valued communities and their species. [ABSTRACT FROM AUTHOR]

Reliable water quality prediction can improve environmental flow monitoring and the sustainability of the stream ecosystem. In this study, we compared two machine learning methods to predict water quality parameters, such as total nitrogen (TN), total phosphorus (TP), and turbidity (TUR), for 97 watersheds located in the Southeast Atlantic region of the USA. The modeling framework incorporates multiple climate and watershed variables (characteristics) that often control the water quality indicators in different landscapes. Three techniques, such as stepwise regression (SR), Least Absolute Shrinkage and Selection Operator (LASSO), and genetic algorithm (GA), are implemented to identify appropriate predictors out of 28 climate and catchment-related variables. The selected predictors were then used to develop the Random Forest (RF) and Boosted regression tree (BRT) models for water quality predictions in selected watersheds. The results highlighted that while both algorithms provided reasonable results (based on statistical metrics), the RF algorithm was easier to train and robust to model overfitting. Partial dependence plots highlighted the complex and nonlinear relationships between the individual predictors and the water quality indicators. The thresholds obtained from partial dependence plots showed that the median values of total nitrogen (TN) and total phosphorus (TP) in streams increase significantly when the percentage of urban and agricultural lands is above 40% and 43% of the watershed area, respectively. Furthermore, when soil hydraulic conductivity increases, the reduction in runoff results in decreased Turbidity levels in streams. Therefore, identifying the key watershed characteristics and their critical thresholds can help watershed managers create appropriate regulations for managing and sustaining healthy stream ecosystems. Besides, the forecasting models can improve water quality predictions in ungauged watersheds. [ABSTRACT FROM AUTHOR]

• UAVs show promising utility in monitoring desert rodent activity on a regional scale. • Regional plant variation significantly influences desert rodent burrow density. • Significant lag effects of environmental factors on rodent burrow density. • Elevation, precipitation, vegetation and soil are the key factors influencing rodent. Timely and accurate prediction and early warning of rodent infestation are highly important for the sustainable development of desert ecosystems. This study combines data from 1376 UAV images of actual rodent burrows with natural environmental factor data, aiming to reveal the mechanism through which these factors affect rodent burrow density in the desert areas. The relationships between rodent burrow density and the 9 plant communities and 34 plant species in this area were analyzed by the K-W test and Spearman rank correlation analysis, respectively. The Boruta algorithm and the boosted regression trees (BRT) model were used to determine the six main factors influencing rodent burrow density from a total of 32 factors and to determine the distribution pattern of the burrows. The results show that (1) the density of rodent burrows in the Junggar Basin desert area gradually decreases from south to north and from west to east. (2) There were significant differences in rodent burrow density across the different plant community types (P = 0.048**). A total of 50.0 % of the species significantly influenced rodent burrow density at at least one level. (3) Among the 17 factors with lag effects, nine had the most significant correlation with rodent burrow density in April. Only two natural environmental factors demonstrated lag effects of less than one month. (4) The soil clay content, elevation, Normalized Difference Salinity Index (NDSI), vegetation cover, precipitation, and soil bulk density were the most important influencing factors on rodent burrow density. Considering the pairwise interactions among factors, the collective impact of these factors on rodent burrow density is at least sevenfold greater than the independent effect of a single factor. This study provides a theoretical basis for obtaining a timely and accurate understanding of the spatial distribution of rodent burrows, mitigating the degradation trend of desert ecosystems, and ensuring healthy and sustainable development. [ABSTRACT FROM AUTHOR]

Long-term trends in fisheries catch are useful to monitor effects of fishing on wild populations. However, fisheries catch data are often aggregated in multi-species complexes, complicating assessments of individual species. Non-target species are often grouped together in this way, but this becomes problematic when increasingly common shifts toward targeting incidental species demand closer management focus at the species level. Species distribution models (SDMs) offer an under-utilised tool to allocate aggregated catch data among species for individual assessments. Here, we present a case study of two shovel-nosed lobsters (Thenus spp.), previously caught incidentally and recorded together in logbook records, to illustrate the design and use of catch allocation SDMs to untangle multi-species data for stock assessments of individual species. We demonstrate how catch allocation SDMs reveal previously masked species-specific catch trends from aggregated data and can identify shifts in fishing behaviour, e.g., changes in target species. Finally, we review key assumptions and limitations of this approach that may arise when applied across a broad geographic or taxonomic scope. Our aim is to provide a template to assist researchers and managers seeking to assess stocks of individual species using aggregated multi-species data. [ABSTRACT FROM AUTHOR]

Aim: Species Distribution Models (SDMs) are correlative models that predict the occurrence or abundance of species in relation to predictor variables. SDMs have become an important part of resource management and conservation biology yet they rarely incorporate species' biology or demography into their predictions. To explore the possible influence of biotic relationships in explaining patterns of species' distribution, abundance and explanatory power of SDMs, we chose two intertidal shellfish species with overlapping but different environmental preferences (Austrovenus stutchburyi and Macomona liliana) and modelled their distributions with and without biotic variables. Location: New Zealand. Methods: The relationship between environmental and biotic variables on the abundance of our two species was investigated using Boosted Regression Trees (BRTs) with increasing model complexity: (1) BRT models using environmental variables were fitted to each species; (2) BRT models using environmental variables and the co‐occurring abundance of the study taxa not being modelled were fitted; (3) BRT models using environmental variables, the co‐occurring abundance and the estimated abundance of the species' patch of the study taxa not being modelled were fitted. Results: A strong, non‐linear effect of the abundance of Austrovenus on Macomona was observed but only a weak effect of Macomona on Austrovenus. The inclusion of biotic variables improved the model fit metrics for both species, as assessed by withheld evaluation data, markedly so for Macomona. The overall deviance explained by the models increased, the correlation of predicted vs observed abundance data increased and the variability in these measures decreased. Main conclusions: The combination of the improvement in model performance and changes in the influence of variables with the inclusion of biotic variables is of importance when predicting into unsampled space (e.g. when predicting impacts of climate change). Our approach improves classic SDMs by integrating ecological theories of how species interactions can alter species distributions across environmental gradients. [ABSTRACT FROM AUTHOR]

Aim: Researchers have debated impacts of past Native American land use on forests including upon tree species composition in north‐eastern United States (US), with estimates of impacts ranging from local to regional extent. This study examines tree relative abundances to assess whether Native Americans influenced geographic distributions prior to Euro‐American settlement. Location: North‐eastern United States (approx. 420,000 km2). Taxon: Ash (Fraxinus spp.), basswood (Tilia americana), beech (Fagus grandifolia), birch (Betula spp.), cherry (Prunus spp.), chestnut (Castanea dentata), dogwood (Cornus spp.), elm (Ulmus spp.), fir (Abies balsamea), hemlock (Tsuga canadensis), hickory (Carya spp.), ironwood (Carpinus caroliniana and Ostrya virginiana), maple (Acer spp.), oak (Quercus spp.), pine (Pinus spp.), spruce (Picea spp.), tamarack (Larix laricina) and walnut (Juglans spp.), Methods: We used boosted regression trees to model abundance patterns and to assess the importance of distance‐based proxies of Native American land use versus environmental variables. We trained models that included and excluded distance‐based proxies. Abundance estimates from original land survey records (1650–1850 CE) were acquired for taxa at 8 km spatial resolution, and related to Native American settlement locations (1500–1800 CE) and 27 environmental variables. Results: When evaluated upon test data, regional‐scale models of relative abundance that included distance‐based proxies performed only slightly better than models that excluded them, with mean improvements in RMSE of 0.1 percentage points. Models suggest that Native American land use modestly altered the relative abundance of taxa locally, extending no more than 50 km from settlement. Models also suggest slight increases near settlement of a few percentage points in relative abundance for fire‐tolerant and/or dietary taxa (e.g. oak, hickory and pine), and for early‐successional taxa (e.g. ash). Main conclusions Past Native American land use had no detectable effect on forest composition across a regional extent, but increased the abundance of fire‐tolerant, shade‐intolerant and nut‐producing trees locally. [ABSTRACT FROM AUTHOR]

The terrestrial methane budget varies between different vegetation types and soil conditions and is highly uncertain for alpine grasslands. This work used eddy covariance techniques to continuously measure CH4 flux (NEEm) over a semiarid alpine meadow on the northeastern Qinghai-Tibetan Plateau from January 2017 to August 2019. The diel NEEm averaged 0.14 ± 0.98 nmol CH4 m−2 s−1 (mean ± S.D.), with a rough pattern of daytime release and nocturnal uptake. The 8-day NEEm exhibited a similar sinusoid variation, with a peak of 6.8 mg CH4 m−2 d−1 at the end of April and a minimum of −1.5 mg CH4 m−2 d−1 at the end of August. The maximum release probably coincided with the thawing of frozen soil in the root zone, and the peak uptake may be related to high soil temperature. Monthly CH4 uptake was highest from June to September and consumed 51.7 mg CH4 m−2 from the atmosphere. CH4 production in the other months totaled 647.6 mg CH4 m−2. The semiarid alpine meadow thus acted as a weak net CH4 source, releasing ca 0.6 g CH4 m−2 year−1 to the atmosphere. The boosted regression trees analysis shows that the sensible heat flux (H) is positively related to half-hour NEEm and accounted for 34% of its variability. The piecewise structural equation models reveal that the magnitude of the effects from soil temperature and vapor pressure deficit on 8-day and monthly NEEm were almost equal, but acted in opposite directions. Vegetation growth and soil moisture exerted little direct influence on NEEm variability at half-hour, 8-day, or monthly scales. Our results show that CH4 emissions of the nongrowing season dominate the annual methane budget for this alpine meadow area. Methane consumption during the growing season was significantly constrained by low soil temperature and high soil water content. These findings imply that semiarid alpine meadows may consume more methane during the growing season if soil temperatures increase and soil moisture levels decrease as projected by future warming scenarios, thus constituting a climate change negative feedback. [ABSTRACT FROM AUTHOR]

Globally, urban expansion and climate change interact to threaten stream ecosystems and are accelerating the loss of aquatic biodiversity. Waterway managers urgently need tools to understand the potential combined impacts of urbanization and climate change and to identify effective mitigating management interventions for protecting freshwater biota. We address this challenge using the semi‐aquatic mammal the platypus (Ornithorhynchus anatinus) as a focal species. We developed high‐resolution environmental spatial data for stream networks and spatially explicit habitat suitability models (HSMs) to explore the impact of threats and to identify the combination of management actions most likely to maintain or improve habitat suitability over the next 50 years in greater Melbourne, Australia. We developed and evaluated platypus HSMs (males‐and‐females and females‐only) including validation using an independent environmental DNA data set. Platypus occurred more commonly in larger, cooler streams with greater catchment‐weighted discharge, following periods of greater stream flow. They were positively associated with near‐stream forest cover and negatively associated with annual air temperature and urban stormwater runoff. Extensive reductions in suitable platypus habitat are predicted to occur under urbanization and climate change scenarios, with the greatest threat expected from reduced streamflows. This emphasizes the importance of maintaining flow regimes as part of conserving platypus in the region; however, substantial additional benefit is predicted by concurrent riparian revegetation and urban stormwater management efforts (that also have the potential to contribute to the streamflow objectives). Provision of adequate streamflows in a future with increasing water demands and water security requirements will likely require creative integrated water management solutions. Our high‐resolution stream network and HSMs have allowed predictions of potential range‐shifts due to urban expansion and climate change impacts at management‐relevant scales and at the whole‐of‐landscape scale. This has enabled systematic strategic planning, priority action planning and target setting in strategic policy development. [ABSTRACT FROM AUTHOR]

Species distribution modeling (SDM) is widely used in ecology and conservation. Currently, the most available data for SDM are species presence‐only records (available through digital databases). There have been many studies comparing the performance of alternative algorithms for modeling presence‐only data. Among these, a 2006 paper from Elith and colleagues has been particularly influential in the field, partly because they used several novel methods (at the time) on a global data set that included independent presence–absence records for model evaluation. Since its publication, some of the algorithms have been further developed and new ones have emerged. In this paper, we explore patterns in predictive performance across methods, by reanalyzing the same data set (225 species from six different regions) using updated modeling knowledge and practices. We apply well‐established methods such as generalized additive models and MaxEnt, alongside others that have received attention more recently, including regularized regressions, point‐process weighted regressions, random forests, XGBoost, support vector machines, and the ensemble modeling framework biomod. All the methods we use include background samples (a sample of environments in the landscape) for model fitting. We explore impacts of using weights on the presence and background points in model fitting. We introduce new ways of evaluating models fitted to these data, using the area under the precision‐recall gain curve, and focusing on the rank of results. We find that the way models are fitted matters. The top method was an ensemble of tuned individual models. In contrast, ensembles built using the biomod framework with default parameters performed no better than single moderate performing models. Similarly, the second top performing method was a random forest parameterized to deal with many background samples (contrasted to relatively few presence records), which substantially outperformed other random forest implementations. We find that, in general, nonparametric techniques with the capability of controlling for model complexity outperformed traditional regression methods, with MaxEnt and boosted regression trees still among the top performing models. All the data and code with working examples are provided to make this study fully reproducible. [ABSTRACT FROM AUTHOR]

BACKGROUND Free fractions of different blackberry varieties' extracts are high in phenolic compounds with antioxidant activities. However, the phenolic profiles and antioxidant activities against peroxyl radicals of bound fractions of different blackberry varieties' extracts have not been previously reported. In addition, what the key antioxidant phenolic compounds are in free and bound fractions of blackberry extracts remain unknown. This study aimed to investigate the phenolic profiles and antioxidant activities of free and bound fractions of eight blackberry varieties' extracts and reveal the key antioxidant phenolic compounds by boosted regression trees. RESULTS: Fifteen phenolics (three anthocyanins, four flavonols, three phenolic acids, two proanthocyanidins, and three ellagitannins) were identified in blackberry by ultra‐performance liquid chromatography coupled with quadrupole time‐of‐flight mass spectrometry. Ferulic acid, ellagic acid, procyanidin C1, kaempferol‐O‐hexoside, ellagitannins hex, and gallic acid were major bound phenolics. Bound fractions of eight blackberry varieties' extracts were high in phenolics and showed great antioxidant activity. Boosted regression trees analysis showed that cyanidin‐3‐O‐glucoside and chlorogenic acid were the most significant compounds, contributing 48.4% and 15.9% respectively to the antioxidant activity of free fraction. Ferulic acid was the most significant antioxidant compound in bound fraction, with a contribution of 61.5%. Principal component analysis showed that Kiowa was the best among the eight varieties due to its phenolic profile and antioxidant activity. CONCLUSION: It was concluded that blackberry varieties contained high amounts of bound phenolics, which confer health benefits through reducing oxidative stress. Ferulic acid was the key compound to explain the antioxidant activities of bound fractions. © 2021 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

Selenium (Se) is an essential micronutrient that is both hazardous and beneficial to living organisms. However, few studies have examined soil Se distribution and its driving mechanisms on a large basin scale. Thus, multivariate statistics, geostatistics, boosted regression trees, and structural equation models were used to investigate the spatial distribution, driving factors, and multivariate interactions of soil Se based on 1753 topsoil samples (0–20 cm) from the Taihu Lake Basin. The results indicated that the soil Se concentration ranged from 0.12 to 57.26 mg kg−1, with a mean value of 0.90 mg kg − 1. Overall, the spatial pattern of soil Se gradually decreased from south to north with approximately 1.06% of the soil contaminated with Se. Moisture index (MI), soil moisture (SM), and ≥ 0 ℃ accumulative temperature (AAT0) were the main determinants of soil Se accumulation. Additionally, the substantial effect of SM∩AAT0 on soil Se concentrations demonstrated that climate-soil interactions largely governed the spatial pattern of soil Se. The Se-enriched and Se-contaminated soils occurred mainly in regions with high precipitation, MI, SM, AAT0, and soil organic matter. This study provides a theoretical basis and practical guidance for the remediation of soil Se contamination and the sustainable development of Se-enriched agriculture. [Display omitted] • Soil Se concentration and distribution in Taihu Lake Basin were first reported. • Approximately 1.06% of the soils in Taihu Lake Basin were contaminated with Se. • The spatial pattern of soil Se was largely governed by climate-soil interactions. • Soil Se enrichment and contamination in Taihu Lake Basin require special attention. [ABSTRACT FROM AUTHOR]

• Gross Rainfall Partitioning (GPR) patterns show no significant differences among stands of various species or forest origins. • Stand structure has more influence than hydrometeorological factors on GPR as the on-tree rainfall residence time increases. • Stand structure attributes play predominant roles in predicting GPR. • A Boost Regression Tree method is well-fitted for modeling GPR at a regional scale. Large-scale ecological restoration in the arid and semi-arid Loess Plateau region of northern China is challenged by the intensifying water stress due to the changes in precipitation regimes. Although the importance of Gross Precipitation Partitioning (GRP) has been well recognized in forest hydrology, especially in dry areas, the processes are not understood because site- or region-specific factors complicate the accurate quantifications. This study integrates meta-analysis and field observation to compare patterns of GRP in forest stands that had different origins (plantations vs. native forests) and tree species (deciduous vs. evergreen) compositions. We aimed at quantifying the dominant biotic and abiotic factors controlling each of the GRP components to form empirical relationships between the GRP components and the influencing factors via the Boosted Regression Trees (BRT) model. We found a convergence in the GRP components among the examined stands that have diverse tree species and origins. Our results indicated that, unlike stem flow (SF) and canopy interception (I c), the throughfall (TF) did not differ between natural and plantation stands. Meanwhile, from the perspective of species composition, the broadleaf forest stands had significantly higher SF rates than the coniferous stands. We found that stand structures exerted limited influence on TF, but significantly affected SF and I c. We hypothesized that the residence time of the GRP components was important in explaining the matrix of influencing factors. The cumulative influences of stand structure factors played a more important role than species in most conditions. Based on the most influential factors (cumulative explanatory power > 70 %) selected from the BRT model, we successfully built a general formula to represent the GRP processes across the diverse forest stands in the Loess Plateau. Our study provides insights into the underlying mechanism of GRP for developing more realistic forest hydrological models. An improved understanding of GRP and better models are important for guiding large scale reforestation efforts that account for hydrological processes across stand species and origins. [ABSTRACT FROM AUTHOR]

Complemented croplands are a crucial component of cropland resources and play a significant role in ensuring national food security. In recent decades, to counter the loss of prime farmland caused by urban construction, the Chinese government introduced a requisition–compensation balance policy, leading to the substantial expansion of new croplands. Therefore, there is an urgent need to determine whether these complemented croplands can be effectively used. Taking Southwest China as a case study, we used high-precision long-term land-use data from 1990 to 2020 to reveal the dynamics of complemented cropland utilization, evaluate the efficiency of complemented cropland utilization from the perspective of abandoned farmland, and identify the factors driving complemented cropland use efficiency based on more than 13 million land parcels. The results showed that: (1) From 1990 to 2020, complemented cropland amounted to approximately 1170.07 × 104 hm2, accounting for 32.67% of the total arable land area in 1990. The potential grain production capacity of these complemented croplands was significantly lower than that of base croplands. (2) The abandonment of complemented croplands was more serious than that of base croplands, and 47.03% of the complemented croplands experienced abandonment at least once during the study period, and the average efficiency of the complemented croplands was 75.61%. (3) The labor population ratio, elevation, and land parcel size played pivotal roles in influencing the complemented cropland utilization efficiency; however, there was substantial variation among the different provinces. Labor replacement, overcoming farming difficulties brought by mountainous terrain, and improving farmers' income are the keys to alleviating cropland abandonment in mountainous areas and improving cropland utilization efficiency. This study provides novel insights into the efficiency assessment and exploration of the mechanisms driving complemented croplands and can provide references for cropland management. [Display omitted] • A novel perspective for the evaluation of cropland use efficiency was developed. • Complemented cropland abandonment was more serious than that of base cropland. • Average use efficiency of complemented cropland was 75.61% in Southwest China. • Labor force ratio, elevation, and land parcel size were the primary driving factors. [ABSTRACT FROM AUTHOR]

Ecological restoration is an essential strategy for mitigating the current biodiversity crisis, yet restoration actions are costly. We used systematic conservation planning principles to design an approach that prioritizes restoration sites for birds and tested it in a riparian forest restoration program in the Colorado River Delta. Restoration goals were to maximize the abundance and diversity of 15 priority birds with a variety of habitat preferences. We built abundance models for priority birds based on the current landscape, and predicted bird distributions and relative abundances under a scenario of complete riparian forest restoration throughout our study area. Then, we used Zonation conservation planning software to rank this restored landscape based on core areas for all priority birds. The locations with the highest ranks represented the highest priorities for restoration and were located throughout the river reach. We optimized how much of the available landscape to restore by simulating restoration of the top 10–90% of ranked sites in 10% intervals. We found that total diversity was maximized when 40% of the landscape was restored, and mean relative abundance was maximized when 80% of the landscape was restored. The results suggest that complete restoration is not optimal for this community of priority birds and restoration of approximately 60% of the landscape would provide a balance between maximum relative abundance and diversity. Subsequent planning efforts will combine our results with an assessment of restoration costs to provide further decision support for the restoration-siting process. Our approach can be applied to any landscape-scale restoration program to improve the return on investment of limited economic resources for restoration. • Systematic conservation planning tools can be useful in landscape-scale restoration planning. • Bird-community abundance was maximized when 80% of the landscape was restored and diversity was maximized when 40% of the landscape was restored. • Six species were positively associated with increasing restoration area. • Five species were positively associated with intermediate levels of restoration. • Three species were negatively associated with increasing restoration area. [ABSTRACT FROM AUTHOR]

Ecological research heavily relies on coarse‐gridded climate data based on standardized temperature measurements recorded at 2 m height in open landscapes. However, many organisms experience environmental conditions that differ substantially from those captured by these macroclimatic (i.e. free air) temperature grids. In forests, the tree canopy functions as a thermal insulator and buffers sub‐canopy microclimatic conditions, thereby affecting biological and ecological processes. To improve the assessment of climatic conditions and climate‐change‐related impacts on forest‐floor biodiversity and functioning, high‐resolution temperature grids reflecting forest microclimates are thus urgently needed. Combining more than 1200 time series of in situ near‐surface forest temperature with topographical, biological and macroclimatic variables in a machine learning model, we predicted the mean monthly offset between sub‐canopy temperature at 15 cm above the surface and free‐air temperature over the period 2000–2020 at a spatial resolution of 25 m across Europe. This offset was used to evaluate the difference between microclimate and macroclimate across space and seasons and finally enabled us to calculate mean annual and monthly temperatures for European forest understories. We found that sub‐canopy air temperatures differ substantially from free‐air temperatures, being on average 2.1°C (standard deviation ± 1.6°C) lower in summer and 2.0°C higher (±0.7°C) in winter across Europe. Additionally, our high‐resolution maps expose considerable microclimatic variation within landscapes, not captured by the gridded macroclimatic products. The provided forest sub‐canopy temperature maps will enable future research to model below‐canopy biological processes and patterns, as well as species distributions more accurately. [ABSTRACT FROM AUTHOR]

1. Resources in the ocean are ephemeral, and effective management must therefore account for the dynamic spatial and temporal patterns of ecosystems and species of concern. We focus on the South Taranaki Bight (STB) of New Zealand, where upwelling generates productivity and prey to support an important foraging ground for blue whales that overlaps with anthropogenic pressure from industrial activities. 2. We incorporate regional ecological knowledge of upwelling dynamics, physical-biological coupling and associated lags in models to forecast sea surface temperature (SST) and net primary productivity (NPP) with up to 3 weeks lead time. Forecasted environmental layers are then implemented in species distribution models to predict suitable blue whale habitat in the STB. Models were calibrated using data from the austral summers of 2009-2019, and ecological forecast skill was evaluated by predicting to withheld data. 3. Boosted regression tree models skilfully forecasted SST (CV deviance explained = 0.969-0.970) and NPP (CV deviance explained = 0.738-0.824). The subsequent blue whale distribution forecast models had high predictive performance (AUC = 0.889), effectively forecasting suitable habitat on a daily scale with 1-3 weeks lead time. 4. The spatial location and extent of forecasted blue whale habitat were variable, with the proportion of petroleum and mineral permit areas that overlapped with daily suitable habitat ranging from 0% to 70%. Hence, the STB and these forecast models are well-suited for dynamic management that could reduce anthropogenic threats to whales while decreasing regulatory burdens to industry users relative to a traditional static protected area. 5. Synthesis and applications. We develop and test ecological forecast models that predict sea surface temperature, net primary productivity and blue whale suitable habitat up to 3 weeks in the future within New Zealand's South Taranaki Bight region. These forecasts of whale distribution can be effectively applied for dynamic spatial management due to model foundation on quantified links and lags between physical forcing and biological responses. A framework to operationalize these forecasts through a user-driven application is in development to proactively inform conservation management decisions. This framework is implemented through stakeholder engagement, allows flexibility based on management objectives, and is amenable to improvement as new knowledge and feedback are received. [ABSTRACT FROM AUTHOR]

Aim: The invasion process is a complex, context‐dependent phenomenon; nevertheless, it can be described using the PAB framework. This framework encompasses the joint effect of propagule pressure (P), abiotic characteristics of the environment (A), and biotic characteristics of both the invader and recipient vegetation (B). We analyzed the effectiveness of proxies of PAB factors to explain the spatial pattern of Solidago canadensis and S. gigantea invasion using invasive species distribution models. Location: Carpathian Mountains and their foreground, Central Europe. Methods: The data on species presence or absence were from an atlas of neophyte distribution based on a 2 × 2 km grid, covering approximately 31,200 km2 (7,752 grid cells). Proxies of PAB factors, along with data on historical distribution of invaders, were used as explanatory variables in Boosted Regression Trees models to explain the distribution of invasive Solidago. The areas with potentially lower sampling effort were excluded from analysis based on a target species approach. Results: Proxies of the PAB factors helped to explain the distribution of both S. canadensis and S. gigantea. Distributions of both species were limited climatically because a mountain climate is not conducive to their growth; however, the S. canadensis distribution pattern was correlated with proxies of human pressure, whereas S. gigantea distribution was connected with environmental characteristics. The varied responses of species with regard to distance from their historical distribution sites indicated differences in their invasion drivers. Main conclusions: Proxies of PAB are helpful in the choice of explanatory variables as well as the ecological interpretation of species distribution models. The results underline that human activity can cause variation in the invasion of ecologically similar species. [ABSTRACT FROM AUTHOR]

Aim: Stemflow has been increasingly recognized as an indispensable component in water and nutrient budgets within vegetated ecosystems. Here we aim to quantify the stemflow percentage (St, %) of incident precipitation (i.e. stemflow production) at a global scale, and to provide a systematic evaluation on how biotic and abiotic factors affect St. Location: Global. Time period: 1970–2019. Major taxa studied: Woody plants (trees and shrubs). Methods: We compiled a global stemflow dataset from 234 peer‐reviewed papers, which included 488 observations of St and the related biotic (stand characteristics) and abiotic factors (climate variables) at 283 sites within terrestrial woody plant ecosystems. We explored the global pattern of St and performed a machine learning method (boosted regression trees) to model the effects of biotic and abiotic variables on St. Results: Globally, the median (interquartile range, IQR) St was 2.7% (1.0–6.3%). We found that St in arid zones (type B in the Köppen‐Geiger climate classification) was significantly higher (p <.01) than in other climate types, and we also detected a significant difference (p <.01) in St between trees (median: 2.4%; IQR: 1.0–5.3%) and shrubs (median: 7.2%; IQR: 5.2–11.9%). Predictor variables that substantially accounted for the explained deviance of the final model included vegetation height (27.0%), mean annual precipitation (16.1%), mean annual temperature (14.4%), stand density (10.8%), stand age (8.9%) and bark type (5.5%). In contrast, leaf area index, diameter at breast height, basal area, phenology type, life‐form and leaf type were classified as low importance. Main conclusions: Our synthesis provides a cross‐site comparison of St, and gives a holistic view on how climate variables and stand characteristics contribute to and affect global stemflow production. [ABSTRACT FROM AUTHOR]

Questions: Semi-natural habitats are threatened by shifts in management with worrying effects on multiple facets of biodiversity. We revisited sites once representing a reference for a calcareous semi-natural grassland habitat aiming to: (a) identify the drivers of taxonomic, functional and phylogenetic diversity, and habitat conservation state; (b) assess the role of characteristic and derived diversity in determining these patterns; and (c) discuss the possibility of reconciling the goals of habitat conservation and enhancement of different facets of plant diversity. Location: Seven sites along the Apennines (Italy), from Mt. Catria (43.46206° N, 12.70397° E) to Mt. Alpi (40.11768° N, 15.98341° E). Methods: For 132 revisited plots, we calculated vascular plant taxonomic, functional and phylogenetic diversity using Hill numbers, and used boosted regression trees to investigate their response to the compositional dissimilarity from historical plots, to grazing intensity and to environmental variables. We identified characteristic and derived diversity and summarized them in an index of habitat conservation state whose drivers were investigated using the same approach. Results: Plant diversity was influenced by the site, whereas the habitat conservation state responded more markedly to vegetation type. Grazing intensity, slope and soil variables drove taxonomic and functional diversity, and the habitat conservation state, with some differences in their relative importance. Phylogenetic diversity responded only partly to grazing intensity, while it showed a major response to increasing temperatures. Conclusions: Patterns and drivers of different facets of plant diversity partially differ from those of the habitat conservation state, suggesting that the management of semi-natural habitats should be carefully tailored on specific conservation objectives. Generalized actions on grazing regimes and litter removal can promote habitat conservation, whereas the outcomes of these actions for plant diversity may differ across sites. Identifying areas particularly subjected to land-use changes and/or climate warming may drive conservation actions. [ABSTRACT FROM AUTHOR]

Aims: Species distribution models (SDMs) are often used to forecast potential distributions of important invasive or rare species. However, situations where models could be the most valuable ecologically or economically, such as for predicting invasion risk, often pose the greatest challenges to SDM building. These challenges include non‐equilibrium range expansion, low or uneven prevalence, and projecting distributions into environments that are non‐analogous to the environments used for model building. Location: Minnesota, USA. Taxon: Cardamine impatiens (Narrowleaf Bittercress), Celastrus orbiculatus (Oriental Bittersweet), and Humulus japonicus (Japanese Hops). Methods: We took a novel approach to build robust species distribution models of invasive species using occurrence‐environment correlations between invasive species and co‐occurring native community members. The correlations were obtained from a joint species distribution model (JSDM) of a densely sampled database of 10,336 MN plant communities from across the state of Minnesota, USA. Positively and negatively associated native species were incorporated into the model as surrogate presences and pseudoabsences (weighted by their environmental correlations) along with invasive species occurrences records (surrogate SDMs). Results: Surrogate models performed better than traditional SDMs in predicting occurrences along the northern invasion margin (outside the training area). Both types of models had similarly high cross‐validation metrics in the area of training. Surrogate models also predicted greater range expansion beyond the current geographic range. Main conclusions: These results demonstrate that modelers can take advantage of detailed community data to develop SDMs that leverage surrogate native species as phytometers of environments beyond the current area of occupancy. The additional information in surrogate models generates highly effective predictions of invasive species along expanding range margins. [ABSTRACT FROM AUTHOR]

Documenting responses of biotic assemblages to coal‐mining impacts is crucial to informing regulatory and reclamation actions. However, attributing biotic patterns to specific stressors is difficult given the dearth of preimpact studies and prevalence of confounding factors. Analysing species distributions and abundances, especially stratified by species traits, provides insights into how assemblage composition shifts occur. We evaluated stream habitats and fish assemblages along a mining intensity gradient in 83 headwater (2nd‐ and 3rd‐order) streams of the upper Clinch and Powell river basins in Virginia. Our multivariate gradient (MINE.PC1) was based on percentages of watershed area covered by surface mine, underground mine and valley fill to represent spatial variance in mining intensity. MINE.PC1 was positively correlated with conductivity and percentage of substrate as cobble. Forty fish‐assemblage metrics were analysed via boosted regression trees to assess assemblage responses to mining intensity, while accounting for environmental variation and spatial structure among sites. Conductivity and MINE.PC1 were strongly negatively related to occurrences of Fantail Darter (Etheostoma flabellare) and sculpin (Cottus) spp. Several taxonomic, trophic and reproductive metrics of assemblage composition responded strongly to mining intensity or its instream correlates. For example, coal mining favoured omnivore‐herbivores, but inhibited invertivores, simple lithophils and nonsimple nonlithophils. We revealed distinct negative and positive responses to mining‐related stressors, which suggest changes to macroinvertebrate prey availability and/or contaminant loads contribute to fish extirpations in coalfield streams. Future assessments of mining impacts on fish assemblages could be more instructive by including characterisations of physicochemical stressors and regionally calibrated biotic metrics with demonstrated sensitivity to mining. [ABSTRACT FROM AUTHOR]

Background: The COVID-19 pandemic is affecting nations globally, but with an impact exhibiting significant spatial and temporal variation at the sub-national level. Identifying and disentangling the drivers of resulting hospitalisation incidence at the local scale is key to predict, mitigate and manage epidemic surges, but also to develop targeted measures. However, this type of analysis is often not possible because of the lack of spatially-explicit health data and spatial uncertainties associated with infection. Methods: To overcome these limitations, we propose an analytical framework to investigate potential drivers of the spatio–temporal heterogeneity in COVID-19 hospitalisation incidence when data are only available at the hospital level. Specifically, the approach is based on the delimitation of hospital catchment areas, which allows analysing associations between hospitalisation incidence and spatial or temporal covariates. We illustrate and apply our analytical framework to Belgium, a country heavily impacted by two COVID-19 epidemic waves in 2020, both in terms of mortality and hospitalisation incidence. Results: Our spatial analyses reveal an association between the hospitalisation incidence and the local density of nursing home residents, which confirms the important impact of COVID-19 in elderly communities of Belgium. Our temporal analyses further indicate a pronounced seasonality in hospitalisation incidence associated with the seasonality of weather variables. Taking advantage of these associations, we discuss the feasibility of predictive models based on machine learning to predict future hospitalisation incidence. Conclusion: Our reproducible analytical workflow allows performing spatially-explicit analyses of data aggregated at the hospital level and can be used to explore potential drivers and dynamic of COVID-19 hospitalisation incidence at regional or national scales. [ABSTRACT FROM AUTHOR]

The type and extent of habitats along the shoreline specify the distribution of fish in the littoral zone of lakes, but effects are likely species and size-specific and might be overwhelmed by lake-level environmental factors that drive fish abundance (e.g. trophic state). We applied a replicated transect-sampling design by electrofishing assessing fish abundance and distribution along the banks of 20 gravel pit lakes in Lower Saxony (Germany). Boosted regression trees were used to analyse the impact of different characteristic habitat types (e.g. vegetated, woody or open water zones), shoreline water depth and lake-level environmental variables on species-specific fish abundances. In contrast to earlier studies, lake-level environment and transect-level habitat type similarly influenced the abundances of differently sized fish species in the littoral zone of gravel pit lakes. The abundance of almost all fish species increased with lake productivity and extent of structured littoral habitats, mostly following non-linear relationships. Our work suggests that investments into the quality of littoral habitat, and not merely the control of nutrient inputs or other lake-level environmental factors, can promote abundance of most gravel pit lake fish species, in particular those who depend on the littoral zone for at least part of their life-cycle. [ABSTRACT FROM AUTHOR]

The East Maui Watershed (EMW) is a > 60,000-ha forested watershed with wide temperature and precipitation gradients being invaded by miconia (Miconia calvescens DC.). Current miconia management efforts focus on protecting important watershed and critical habitat areas from miconia invasion. Herein, we report on a miconia species distribution model to predict unoccupied areas that may be still vulnerable to invasion. This suitable habitat model was developed from an ensemble of five algorithms associating five physical features of EMW with miconia occurrence data from a 26-yr management history (1991-2016; n = 114,953). All of the algorithms performed well based on model evaluation statistics (e.g. AUC = 0.83; TSS = 0.36). Elevation, slope and rainfall were consistently important predictors, while aspect indices were non-contributors. The binary ensemble model suggests a total of ~ 56.9% of the area of interest is susceptible to invasion by miconia. An independent dataset collected in 2017-2018 (n = 5,222) was used to field validate the ensemble habitat suitability model (EHSM) and found that the model could correctly predict suitable habitat 94% of the time. All five of the model algorithms were updated using this new management data, and the predicted suitable area decreased 2.3%. While binary models are useful for risk assessment, the classification of an area as suitable or not suitable has limitations for land managers adopting for management activities. Utilizing the mean weighted consensus probability surface representation of the model allows for more scrutiny of potential suitable habitat. We suggest using this approach when planning future monitoring efforts, especially if specific areas have a higher prioritization for conservation than others. [ABSTRACT FROM AUTHOR]

Globally, reef manta rays (Mobula alfredi) are in decline and are particularly vulnerable to exploitation and disturbance at aggregation sites. Here, passive acoustic telemetry and a suite of advanced oceanographic technologies were used for the first time to investigate the fine‐scale (5‐min) influence of oceanographic drivers on the visitation patterns of 19 tagged M. alfredi to a feeding aggregation site at Egmont Atoll in the Chagos Archipelago. Boosted regression trees indicate that tag detection probability increased with the intrusion of cold‐water bores propagating up the atoll slope through the narrow lagoon inlet during flood tide, potentially transporting zooplankton from the thermocline. Tag detection probability also increased with warmer near‐surface temperature close to low tide, with near‐surface currents flowing offshore, and with high levels of backscatter (a proxy of zooplankton biomass). These combinations of processes support the proposition that zooplankton carried from the thermocline into the lagoon during the flood may be pumped back out through the narrow inlet during an ebb tide. These conditions provide temporally limited feeding opportunities for M. alfredi, which are tied on the tides. Results also provide some evidence of the presence of Langmuir Circulation, which transports and concentrates zooplankton, and may partly explain why M. alfredi occasionally remained at the feeding location for longer than that two hours. Identification of these correlations provides unique insight into the dynamic synthesis of fine‐scale oceanographic processes which are likely to influence the foraging ecology of M. alfredi at Egmont Atoll, and elsewhere throughout their range. [ABSTRACT FROM AUTHOR]

Accurate quantification of vegetation carbon turnover time (τveg) is critical for reducing uncertainties in terrestrial vegetation response to future climate change. However, in the absence of global information of litter production, τveg could only be estimated based on net primary productivity under the steady‐state assumption. Here, we applied a machine‐learning approach to derive a global dataset of litter production by linking 2401 field observations and global environmental drivers. Results suggested that the observation‐based estimate of global natural ecosystem litter production was 44.3 ± 0.4 Pg C year−1. By contrast, land‐surface models (LSMs) overestimated the global litter production by about 27%. With this new global litter production dataset, we estimated global τveg (mean value 10.3 ± 1.4 years) and its spatial distribution. Compared to our observation‐based τveg, modelled τveg tended to underestimate τveg at high latitudes. Our empirically derived gridded datasets of litter production and τveg will help constrain global vegetation models and improve the prediction of global carbon cycle. [ABSTRACT FROM AUTHOR]

Freshwater ecosystems in North America have been greatly affected by invasive species, including invasive amphipods, which has motivated the development of predictive models to inform where invaders are likely to establish. Here, we provide the first predictive model using freshwater-specific habitat layers for the non-native amphipod Apocorophium lacustre (Vanhoffen, 1911) in the Mississippi, Laurentian Great Lakes, and Upper Saint Lawrence river basins, USA, and evaluate its current distribution in the Chicago Area Waterway System (CAWS), Illinois, USA. In the summers of 2017, 2018, and 2019, we sampled for A. lacustre at 45 sites in the CAWS. Next, we used boosted regression trees to develop an ensembled species distribution model combining A. lacustre occurrence data with the EarthEnv GIS layers to model habitats suitable for this species. We did not find A. lacustre at any of our sampling sites in the CAWS in 2017 nor 2018, but we did find the species at 7 sites in 2019. Our ensemble species distribution model evaluated habitat associations and predicted the potential distribution of A. lacustre with an average area-under-the-curve value of 0.996 and an average true skills statistic of 0.956. The model predicts that A. lacustre could establish throughout much of the Mississsippi River basin and in the Upper Saint Lawrence River basin. These predictions of habitat suitability for A. lacustre can guide management efforts by facilitating monitoring and early detection to prevent further spread and establishment of this species. [ABSTRACT FROM AUTHOR]

• The environmental niche model was used to explain and predict the potential distribution of fishing effort. • Environmental preferences of squid-jigging fleet could be characterized by several environmental variables. • Potential fishing areas of squid-jigging fleet could be identified in other sea areas. • The selected variable and its relative contribution vary in each month. • The BRT shows specific nonlinear response thresholds for different driving factors. The vast number of fishing fleets and limited regulatory capacity pose challenges to the effective monitoring and management of marine fishery resources. To understand the fishing characteristics of spatial distribution for squid-jigging fleets in the North Pacific Ocean (NPO), satellite-based automatic identification system (AIS) data during 2016 ∼ 2020 and marine environmental data were applied to explore the drivers of fishing activities based on the boosted regression tree (BRT) and generalized additive model (GAM). The results showed that the BRT model has better performance than the GAM. The spatial distribution of squid-jigging fleets has a significant seasonality. Specifically, the spatial distribution of Fishing effort (FE) gradually shifted to the northwest from May to September, while gradually shifted to the southwest from October to November. The favourable area for focusing FE was the 150 ° E ∼ 165 ° E, 40 ° N ∼ 44 ° N. The latitudinal distribution of FE was not wide and the longitudinal distribution was long. Variations in the marine environment constantly influenced the FE of the squid-jigging fleets. Overall, the influence of sea surface temperature ( T 0 ) on FE was most significant. The favourable range of T 0 for FE was 12 ∼ 20 ° C. Water temperature at the 300 m depth ( T 300 ) was also an important factor through the fishing season. The favourable range of T 300 for FE was 3 ∼ 6 ° C. There were obvious differences in the influence of other environmental factors on FE in different months. Different environmental variables drive the spatial distribution of fishing effort in different months. This study may help to scientifically and effectively guide fishery management and sustainable development by evaluating the spatial variations in fishing activity. [ABSTRACT FROM AUTHOR]