Search

Purpose: Dovitinib (TKI258) is an orally available inhibitor of fibroblast growth factor (FGF), VEGF, and platelet-derived growth factor receptors. This phase I/II dose–escalation study was conducted to evaluate the safety, pharmacodynamics, and preliminary efficacy of dovitinib in the treatment of advanced melanoma.Experimental Design: Patients with advanced melanoma resistant or refractory to standard therapies or for whom no standard therapy was available were enrolled. Dovitinib was administered at doses ranging from 200 to 500 mg/d.Results: Forty-seven patients were enrolled. The most frequently reported adverse events were fatigue (77%; grade ≥3, 28%), diarrhea (77%; grade ≥3, 11%), and nausea (77%; grade ≥3, 9%). Six dose-limiting toxicities were observed in the 400-mg and 500-mg dose cohorts, which consisted of grade 3 nausea, fatigue, and diarrhea and grade 4 fatigue events. The maximum tolerated dose was 400 mg/d. The best tumor response was stable disease, which was observed in 12 patients. Increases in plasma FGF23, VEGF, and placental growth factor and decreases in soluble VEGF receptor 2 were noted during the first cycle of treatment, consistent with FGF receptor (FGFR) and VEGF receptor (VEGFR) inhibition. Dynamic contrast-enhanced MRI analysis showed a dose-dependent decrease in tumor blood flow and vascular permeability with dovitinib therapy. A decrease in FGFR phosphorylation was observed in paired tumor biopsy samples from a patient treated with dovitinib at a dose of 400 mg/d.Conclusions: At a dose of 400 mg/d, dovitinib showed an acceptable safety profile and limited clinical benefit and inhibited FGFR and VEGFR. Clin Cancer Res; 17(23); 7451–61. ©2011 AACR.

PDF file - 131K, Abbreviations: AUC0-t, area under the concentration-time curve from time zero to t; Cmax, maximum concentration; CV%, coefficient of variation; PK, pharmacokinetic; SD, standard deviation; T1/2, half-life.

Supplementary Figures 1-8 from The Mechanisms of Differential Sensitivity to an Insulin-like Growth Factor-1 Receptor Inhibitor (BMS-536924) and Rationale for Combining with EGFR/HER2 Inhibitors

Supplementary Tables 1-4 from The Mechanisms of Differential Sensitivity to an Insulin-like Growth Factor-1 Receptor Inhibitor (BMS-536924) and Rationale for Combining with EGFR/HER2 Inhibitors

Mobbing is a widespread but risky behavior where prey actually approach and may even attack their predators. Small songbirds gather in multi-species flocks to direct mobbing at birds of prey such as the Northern Pygmy-Owl (Glaucidium gnoma), a small diurnal species of owl in mountainous western North America. We hypothesized that intensity of mobbing behavior would vary according to risk to songbirds and that risk varied seasonally and across elevations. In particular, we expected mobbing intensity to change seasonally as a function of two primary sources of risk: seasonal dietary changes of pygmy-owls and distribution of pygmy-owls as a function of elevation. Pygmy-owls are known to shift their diet from mostly mammals in early spring to birds in early summer, so we hypothesized risk of predation would vary in parallel. Likewise, risk was expected to vary as the distribution of pygmy-owls was thought to vary seasonally across elevations. To elicit mobbing in a controlled manner, we conducted owl call playback experiments in the Oregon Coast Range mountains, United States. Overall, we found mobbing to be rare, observing it in 8.1% of 663 experiments. The frequency of mobbing did not appear to vary across elevations. Instead, mobbing varied mostly by season. The frequency of mobbing was highest during fall at lower elevations. Mobbing was rarest (1.3% of trials) during winter. Mobbing occurred during seasons when pygmy-owls tend to consume more birds, consistent with the hypothesis that seasonal variation in risk influences mobbing. In our study, mobbing happened when risk was higher. However, the increased risk may be offset by the influence of mobbing group size. Mobbing was more likely to occur at sites where the number of songbirds, especially chickadees (Poecile sp.) and nuthatches (Sitta sp.), was larger. Yet, even when songbird numbers were high, mobbing was rare during winter, suggesting an interaction between risk and energetic costs of mobbing. Additional experiments manipulating food resource availability may be able to reveal the strength and influence of the interaction on mobbing decisions.

Long-term changes in bird populations during winter are poorly evaluated in many parts of the world. We re-surveyed forest bird communities during winter, 2019-2021, in seven large plots originally surveyed from 1968 through to 1970, near Corvallis, Oregon, USA by Stanley Anderson, a graduate student at Oregon State University in the 1960s. Anderson counted birds and measured forest plant communities within the forests dominated by Douglas-fir (Pseudotsuga menziesii) in the Coast Range Mountain foothills. His thesis included plot locations, summaries of vegetation characteristics and point estimates of bird densities for each plot. To our knowledge, the Anderson data represent the oldest structured survey of Pacific Northwest winter forest bird communities with density estimates. Given the paucity of similar data, we re-surveyed his plots after aligning methods with his and adding modern components (distance and time interval sampling) to facilitate comparisons of changes in abundances. We preserved more extensive metadata than were preserved from Anderson's surveys, including georeferenced point count survey locations to facilitate more precisely repeatable future re-surveys. Original surveys of winter bird populations in the Pacific Northwest, USA, based on georeferenced locations within seven large plots originally surveyed, 1968-1970. In addition to raw count data of all bird species detected, we include information from distance sampling and time-interval sampling methods. To our knowledge, this is one of the only structured surveys of winter forest bird populations in the Coast Range Mountains, USA.

Cross‐ecosystem subsidies move substantial amounts of nutrients between ecosystems. Emergent aquatic insects are a particularly important prey source for riparian songbirds but may also move aquatic contaminants, such as mercury (Hg), to riparian food webs. While many studies focus on species that eat primarily emergent aquatic insects, we instead study riparian songbirds with flexible foraging strategies, exploiting both aquatic and terrestrial prey sources. The goal in this study is to trace reliance on aquatic prey sources and correlate it to Hg concentrations in common riparian arachnids (Families Tetragnathidae, Opiliones, and Salticidae) and songbirds (Common Yellowthroat Geothlypis trichas, Spotted Towhee Pipilo maculatus, Swainson's Thrush Catharus ustulatus, Song Sparrow Melospiza melodia, and Yellow Warbler Setophaga petechia). We used stable isotopes of δ13C and δ15N and Bayesian mixing models in MixSIAR to determine the reliance of riparian predators on aquatic prey sources. Using mixed effects models, we found that arachnid families varied in their reliance on aquatic prey sources. While songbird species varied in their reliance on aquatic prey sources, songbirds sampled earlier in the season consistently relied more on aquatic prey sources than those sampled later in the season. For both arachnids and songbirds, we found a positive correlation between the amount of the aquatic prey source in their diet and their Hg concentrations. While the seasonal pulse of aquatic prey to terrestrial ecosystems is an important source of nutrients to riparian species, our results show that aquatic prey sources are linked with higher Hg exposure. For songbirds, reliance on aquatic prey sources early in the breeding season (and subsequent higher Hg exposure) coincides with timing of egg laying and development, both of which may be impacted by Hg exposure., To understand how exploiting emergent aquatic prey sources could also expose the riparian community to aquatic‐based contaminants, we used stable isotopes of δ13C and δ15N in a MixSIAR Bayesian mixing model to trace emergent aquatic prey in riparian predators (songbirds and arachnids). We determined that individual reliance on aquatic prey was positively correlated with mercury exposure, with songbirds relying more in aquatic prey early in the season. Our results show the seasonal pulse of aquatic prey to terrestrial ecosystems is likely an important source of nutrients to riparian species but may also drive season‐dependent exposure to aquatic contaminants.

Cellular functions, such as division and migration, require cells to undergo robust shape changes. Through their contractility machinery, cells also sense, respond, and adapt to their physical surroundings. In the cytoplasm, the contractility machinery organizes into higher order assemblies termed contractility kits (CKs). Using Dictyostelium discoideum, we previously identified Discoidin I (DscI), a classic secreted lectin, as a CK component through its physical interactions with the actin crosslinker Cortexillin I (CortI) and the scaffolding protein IQGAP2. Here, we find that DscI ensures robust cytokinesis through regulating intracellular components of the contractile machinery. Specifically, DscI is necessary for normal cytokinesis, cortical tension, membrane–cortex connections, and cortical distribution and mechanoresponsiveness of CortI. The dscI deletion mutants also have complex genetic epistatic relationships with CK components, acting as a genetic suppressor of cortI and iqgap1, but as an enhancer of iqgap2. This work underscores the fact that proteins like DiscI contribute in diverse ways to the activities necessary for optimal cell function.

Species are influenced by factors operating at multiple scales, but multi-scale species distribution and abundance models are rarely used. Though multi-scale species distribution models outperform single-scale models, when compared through model selection, multi- and single-scale models built with computer learning algorithms have not been compared. We compared the performance of models using a simple and accessible, multi-scale, machine learning, species distribution and abundance modeling framework to pseudo-optimized and unoptimized single-scale models. We characterized environmental variables at four spatial scales and used boosted regression trees to build multi-scale and single-scale distribution and abundance models for 28 bird species. For each species and across species, we compared the performance of multi-scale models to pseudo-optimized and lowest-performing unoptimized single-scale models. Multi-scale distribution models consistently performed as well or better than pseudo-optimized single-scale models and significantly better than unoptimized single-scale models. Abundance model performance showed a similar, but less pronounced pattern. Mixed-effects models, that controlled for species, provided strong evidence that multi-scale models performed better than unoptimized single-scale models. Although mean improvement in model performance across species appeared minor, for individual species, arbitrary selection of scale could result in discrepancies of up to fourteen percent for area of suitable habitat and population estimates. Scale selection should be explicitly addressed in distribution and abundance modeling. The multi-scale species distribution and abundance modeling framework presented here provides a concise and accessible alternative to standard pseudo-scale optimization while addressing the scale-dependent response of species to their environment.

Context With greater accessibility and processing power from online platforms, summaries of remotely sensed data are increasingly used in species distribution models (SDMs). Comparisons of the predictive power of these environmental variables could inform SDMs moving forward. Objectives We evaluated the performance of freely available Landsat data as predictor sets for SDMs. Our objectives were to 1) compare the performance of single season SDMs built on mean values of raw spectral bands, Tasseled Cap transformations, and eight different indices, including NDVI, 2) evaluate the performance gain with the addition of standard deviation, textural metrics, and additional seasons, and 3) compare the performance of SDMs built on these continuous spectral predictor sets to SDMs built on classified land cover data (e.g., percent forest cover). Methods We used statewide point counts to build multi-scale SDMs for 13 avian species across Oregon, USA. We compared the performance of SDMs built on each predictor set based on our objectives. Results Of the Landsat-derived predictor sets, SDMs built on raw spectral bands had the highest overall performance with nearly equivalent performance in Tasseled-Cap models. While performance gains from standard deviations, textural metrics, and additional seasons were minimal in raw-band and Tasseled-Cap models, gains were appreciable in single-index models. Classified land cover models performed equivalently to raw band models. Conclusions When predictive performance is paramount, means of raw Landsat bands are strong predictors for avian SDMs. When parsimonious variables are essential, SDMs of single indices (e.g., NDVI) greatly benefit from additional information, such as standard deviation., This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature's AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/s10980-022-01406-y

Extensive networks of large plots have the potential to transform knowledge of avian community dynamics through time and across geographical space. In the Neotropics, the global hotspot of avian diversity, only six 100-ha plots, all located in lowland forests of Amazonia, the Guianan shield and Panama, have been inventoried sufficiently. We review the most important lessons learned about Neotropical forest bird communities from those big bird plots and explore opportunities for creating a more extensive network of additional plots to address questions in ecology and conservation, following the model of the existing ForestGEO network of tree plots. Scholarly impact of the big bird plot papers has been extensive, with the papers accumulating nearly 1,500 citations, particularly on topics of tropical ecology, avian conservation, and community organization. Comparisons of results from the plot surveys show no single methodological scheme works effectively for surveying abundances of all bird species at all sites; multiple approaches have been utilized and must be employed in the future. On the existing plots, abundance patterns varied substantially between the South American plots and the Central American one, suggesting different community structuring mechanisms are at work and that additional sampling across geographic space is needed. Total bird abundance in Panama, dominated by small insectivores, was double that of Amazonia and the Guianan plateau, which were dominated by large granivores and frugivores. The most common species in Panama were three times more abundant than those in Amazonia, whereas overall richness was 1.5 times greater in Amazonia. Despite these differences in community structure, other basic information, including uncertainty in population density estimates, has yet to be quantified. Results from existing plots may inform drivers of differences in community structure and create baselines for detection of long-term regional changes in bird abundances, but supplementation of the small number of plots is needed to increase generalizability of results and reveal the texture of geographic variation. We propose fruitful avenues of future research based on our current synthesis of the big bird plots. Collaborating with the large network of ForestGEO tree plots could be one approach to improve understanding of linkages between plant and bird diversity. Careful quantification of bird survey effort, recording of exact locations of survey routes or stations, and archiving detailed metadata will greatly enhance the value of benchmark data for future repeat surveys of the existing plots and initial surveys of newly established plots.

AIM: Sample size and species characteristics, including prevalence and habitat specialization, can influence the predictive performance of species distribution models (SDMs). There is little agreement, however, on which metric of model performance to use. Here, we directly compare AUC and partial ROC as metrics of SDM performance through analyses on the effects of species traits and sample size on SDM performance. LOCATION: Three counties dominated by agricultural lands and coniferous forest in Oregon's Willamette Valley and Coast Range ecoregions. METHODS: We systematically reduced a large avian point count dataset to alter sample sizes of 22 species of songbird. We used boosted regression trees to run SDMs for each species, quantified habitat specialization, and used mixed effects models to compare the influence of sample size, prevalence, and habitat specialization on SDM performance, calculated as AUC and partial ROC, across species. We calculated AUC and partial ROC with subset and independent evaluation data separately to more comprehensively investigate differences in metrics. RESULTS: We found a positive quadratic effect of sample size and a strongly positive effect of habitat specialization on both metrics of model performance. We found a weak effect of prevalence on partial ROC and no effect in AUC. Contrary to expectations, when evaluated with a subset evaluation data, partial ROC was consistently highest in models with the smallest sample sizes. These small sample size models had correspondingly small sample sizes in subset evaluation datasets. Partial ROC evaluated with independent data and AUC evaluated with subset or independent data showed the expected positive correlation between sample size and model performance. MAIN CONCLUSIONS: We found that small evaluation datasets can artificially inflate partial ROC. With literature recommended minimum SDM sample sizes as low as three, attention must be given to the effects of correspondingly low sample sizes in evaluation datasets.

Parental care in birds varies among species and geographic regions. Incubation behavior influences embryonic development rate and varies substantially among species.We studied attendance at the nest by videoing nests or collecting data from the literature for 112 species in north temperate and lowland tropical sites, then associated patterns of incubation on‐ and off‐bouts with species and environmental traits.Songbirds nesting at low elevations incubate their eggs for an average of 74.1% (±12.9 SD, n = 60 species) of the time in temperate regions and 71.0% (±12.2 SD, n = 52 species) in tropical regions during daylight hours, and 84.3% (±8.2 SD) and 85.3% (±6.2 SD), respectively, of each 24‐hr cycle.While these attendance percentages do not differ significantly between latitudes, our data also show that lowland tropical songbirds make fewer visits to the nest and, consequently, have longer on‐bouts and off‐bouts during incubation. This pattern in attendance reflects a latitudinal contrast in parental care strategy, where lowland tropical birds reduce visits to the nest by increasing on‐ and off‐bout lengths while maintaining the same proportion of time spent incubating their eggs (constancy).Similar constancy across latitude suggests that tropical and temperate birds may be similarly constrained to maintain elevated egg temperatures for normal embryo growth.The different attendance strategies adopted in each region may reflect differences in ambient temperature, adult foraging time, and nest predation rate. Consistently warm ambient temperatures likely allow tropical birds to take longer off‐bouts, and thereby to reduce activity around the nest, compared to temperate birds., We compared avian attendance data during incubation of 112 New World temperate and tropical passerine species. The amount of time that parents incubated their eggs did not differ between regions, but tropical birds employed a different attendance strategy. Tropical parents spent longer periods of time on and off of the eggs, made fewer trips to the nest, but incubated for the same percentage of time.

Synopsis Clearly and usefully defining the Rules of Life has long been an attractive yet elusive prospect for biologists. Life persists because requirements for existence and successful transmission of hereditary information are met. These requirements are met through mechanisms adopted by organisms, which produce solutions to environmentally imposed constraints on life. Yet, constraints and their suites of potential solutions are typically context-specific, operating at specific levels of organization, or holons, and having cascading effects across multiple levels, or the holarchy. We explore the idea that the interaction of constraints, mechanisms, and requirements within and across levels of organization may produce rules of life that can be productively defined. Although we stop short of listing specific rules, we provide a conceptual framework within which progress towards identifying rules might be made.

Depredation of birds by domestic cats is hypothesized to be one of many significant sources of mortality leading to global bird declines. Direct observations are relatively rarely documented compared with large numbers of birds hypothesized to be killed or wounded by cats. We analyzed data from two wildlife rehabilitation centers located in Salem and Grants Pass, Oregon USA, to understand which species were most likely to interact with a cat, and the species traits associated with cat interactions and habitats (urban vs. rural) of rescued birds. Interaction with a cat was the second-most commonly reported cause of admission, representing 12.3% of 6345 admissions. Half to two-thirds of birds were rescued from cats in urban settings and were usually species foraging on or near the ground. Most species were admitted to rehabilitation centers in direct proportion to their regional abundance. An exception was the absence of common species weighing less than 70 g, which we conclude is an effect of sampling bias. We conclude that cats most often interact with regionally common near-ground-dwelling bird species in both urban and rural habitats. Wildlife rehabilitation centers can provide valuable sources of data for cat-bird interactions but potential sources of uncertainty and bias in their data need to be considered carefully.

Highly efficient and concurrent flexible operation are heavy demands on today's centrifugal compressor units. Diffuser end wall contouring is a measure to delay the incipience of instability and therefore to extend the compressor's operating range while maintaining efficient performance. In the presented paper, a hub-side wall contouring, applied in the vaneless space upstream the diffuser vane's leading edge and within the diffuser passage of a state-of-the-art centrifugal compressor stage with an open impeller, is examined. Computational fluid dynamics computations are performed for both a baseline diffuser design with parallel channel walls and the hub-side wall contoured diffuser design. Comparisons of characteristic and diffuser stability decisive flow variables are made in perpendicular sections along an extrapolated camber line of the diffuser vane for full span, near shroud and near hub wall. In operating points near the stability limit at two different stage Mach numbers, the stabilizing effect of the hub-side wall contouring on the diffuser flow is clearly shown. In a scale-model test rig, experimental data including pneumatic five-hole probe data for a full diffuser blade-to-blade passage, static wall pressures at various planes as well as total temperatures were measured. The experimental data are utilized for the validation of the presented numerical calculations. The flow stabilizing effect of the hub-wall contouring is clearly visible in the measurements, which showed 8% range extension at highest stage Mach number Mu2 = 1.16 and a range extension of 2% at design stage Mach number Mu2 = 1.

Human alteration of landscapes leads to attrition of biodiversity. Recommendations for maximizing retention of species richness typically focus on protection and preservation of large habitat patches. Despite a century of protection from human disturbance, 27% of the 228 bird species initially detected on Barro Colorado Island (BCI), Panama, a large hilltop forest fragment isolated by waters of Gatun Lake, are now absent. Lost species were more likely to be initially uncommon and terrestrial insectivores. Analyses of the regional avifauna, exhaustively inventoried and mapped across 24 subregions, identified strong geographical discontinuities in species distributions associated with a steep transisthmian rainfall gradient. Having lost mostly species preferring humid forests, the BCI species assemblage continues to shift from one originally typical of wetter forests toward one now resembling bird communities in drier forests. Even when habitat remnants are large and protected for 100 years, altered habitat characteristics resulting from isolation produce non-random loss of species linked with their commonness, dietary preferences and subtle climatic sensitivities.

The growth of biodiversity data sets generated by citizen scientists continues to accelerate. The availability of such data has greatly expanded the scale of questions researchers can address. Yet, error, bias, and noise continue to be serious concerns for analysts, particularly when data being contributed to these giant online data sets are difficult to verify. Counts of birds contributed to eBird, the world’s largest biodiversity online database, present a potentially useful resource for tracking trends over time and space in species’ abundances. We quantified counting accuracy in a sample of 1,406 eBird checklists by comparing numbers contributed by birders (N= 246) who visited a popular birding location in Oregon, USA, with numbers generated by a professional ornithologist engaged in a long-term study creating benchmark (reference) measurements of daily bird counts. We focused on waterbirds, which are easily visible at this site. We evaluated potential predictors of count differences, including characteristics of contributed checklists, of each species, and of time of day and year. Count differences were biased toward undercounts, with more than 75% of counts being below the daily benchmark value. Median count discrepancies were −29.1% (range: 0 to −42.8%;N= 20 species). Model sets revealed an important influence of each species’ reference count, which varied seasonally as waterbird numbers fluctuated, and of percent of species known to be present each day that were included on each checklist. That is, checklists indicating a more thorough survey of the species richness at the site also had, on average, smaller count differences. However, even on checklists with the most thorough species lists, counts were biased low and exceptionally variable in their accuracy. To improve utility of such bird count data, we suggest three strategies to pursue in the future. (1) Assess additional options for analytically determining how to select checklists that include less biased count data, as well as exploring options for correcting bias during the analysis stage. (2) Add options for users to provide additional information that helps analysts choose checklists, such as an option for users to tag checklists where they focused on obtaining accurate counts. (3) Explore opportunities to effectively calibrate citizen-science bird count data by establishing a formalized network of marquis sites where dedicated observers regularly contribute carefully collected benchmark data.

The effects of forest degradation, fragmentation, and climate change occur over long time periods, yet relatively few data are available to evaluate the long-term effects of these disturbances on tropical species occurrence. Here, we quantified changes in occupancy of 50 bird species over 17 years on Barro Colorado Island (BCI), Panama, a model system for the long-term effects of habitat fragmentation. The historical data set (2002&ndash, 2005) was based on point counts, whereas the contemporary data set (2018) was based on acoustic monitoring. For most species, there was no significant change in occupancy, however, the occupancy of four species (Tinamus major, Polioptila plumbea, Myiarchus tuberculifer, and Ceratopipra mentalis) increased significantly, and the occupancy of three species (Saltator grossus, Melanerpes pucherani, and Cyanoloxia cyanoides) decreased significantly. Forest age explained the majority of occupancy variation and affected the occupancy of more bird species than survey period or elevation. Approximately 50% of the species seem to favor old-growth forest, and 15 species (30%) had a significantly higher occupancy in old-growth forest sites. Elevation had no significant impact on the occupancy of the majority of bird species. Although BCI has been a protected reserve for approximately 100 years, land-use legacies (i.e., forest age) continue to influence bird distribution.

The capacity for flight varies widely among bird species and influences their ecology, evolution, and conservation. Variation in vagility is influenced by behavioral responses to the nature of gaps between habitat elements as well as intrinsic characteristics of the species, particularly physiological traits influencing the physical capacity for sustained flight. Here, we briefly summarize the current state of knowledge revealing the wide variety of movement capacities of Neotropical birds. We then review current knowledge of avian muscle physiology and the role that muscle characteristics may play in influencing movement behavior. We argue that fundamental shifts in our understanding of avian muscle physiology and the influence of physiology on movement behavior remain to be elucidated, in part because knowledge from other vertebrates is being inappropriately applied to birds. In particular, critical evaluation of assumptions applied to birds from detailed studies of mammals is needed. Moving away from simple binary categorizations of avian flight muscles as “red vs. white” or “fast vs. slow” to characterize the cellular mechanisms and specific isoforms active at various life stages or seasons is also needed. An increasingly large number of avian species with a wide array of flight styles from hummingbirds to soaring raptors are appearing in GenBank, facilitating detailed physiological and evolutionary comparisons among species. Properly assessing the muscle physiological characteristics of Neotropical bird species with a wide array of movement capacities may improve our abilities to predict which species are most sensitive to landscape fragmentation and other factors that influence dispersal and migration.

This paper focuses on a core task in computational sustainability and statistical ecology: species distribution modeling (SDM). In SDM, the occurrence pattern of a species on a landscape is predicted by environmental features based on observations at a set of locations. At first, SDM may appear to be a binary classification problem, and one might be inclined to employ classic tools (e.g., logistic regression, support vector machines, neural networks) to tackle it. However, wildlife surveys introduce structured noise (especially under-counting) in the species observations. If unaccounted for, these observation errors systematically bias SDMs. To address the unique challenges of SDM, this paper proposes a framework called StatEcoNet. Specifically, this work employs a graphical generative model in statistical ecology to serve as the skeleton of the proposed computational framework and carefully integrates neural networks under the framework. The advantages of StatEcoNet over related approaches are demonstrated on simulated datasets as well as bird species data. Since SDMs are critical tools for ecological science and natural resource management, StatEcoNet may offer boosted computational and analytical powers to a wide range of applications that have significant social impacts, e.g., the study and conservation of threatened species., Comment: To appear in the Proceeding of the 35th AAAI Conference on Artificial Intelligence (AAAI-21); Added supplemental material