Search

High-resolution remote sensing image-based vegetation monitoring is a hot topic in remote sensing technology and applications. However, when facing large-scale monitoring across different sensors in broad areas, the current methods suffer from fragmentation and weak generalization capabilities. To address this issue, this paper proposes a multisource high-resolution remote sensing image-based vegetation extraction method that considers the comprehensive perception of multiple features. First, this method utilizes a random forest model to perform feature selection for the vegetation index, selecting an index that enhances the otherness between vegetation and other land features. Based on this, a multifeature synthesis perception convolutional network (MSCIN) is constructed, which enhances the extraction of multiscale feature information, global information interaction, and feature cross-fusion. The MSCIN network simultaneously constructs dual-branch parallel networks for spectral features and vegetation index features, strengthening multiscale feature extraction while reducing the loss of detailed features by simplifying the dense connection module. Furthermore, to facilitate global information interaction between the original spectral information and vegetation index features, a dual-path multihead cross-attention fusion module is designed. This module enhances the differentiation of vegetation from other land features and improves the network's generalization performance, enabling vegetation extraction from multisource high-resolution remote sensing data. To validate the effectiveness of this method, we randomly selected six test areas within Anhui Province and compared the results with three different data sources and other typical methods (NDVI, RFC, OCBDL, and HRNet). The results demonstrate that the MSCIN method proposed in this paper, under the premise of using only GF2 satellite images as samples, exhibits robust accuracy in extraction results across different sensors. It overcomes the rapid degradation of accuracy observed in other methods with various sensors and addresses issues such as internal fragmentation, false positives, and false negatives caused by sample generalization and image diversity. [ABSTRACT FROM AUTHOR]

This paper focuses on large-scale landslide susceptibility modelling in NW Croatia. The objective of this research was to provide new insight into stable and unstable area sampling strategies on a representative inventory of small and shallow landslides mainly occurring in soil and soft rock. Four strategies were tested for stable area sampling (random points, stable area polygon, stable polygon buffering and stable area centroid) in combination with four strategies for unstable area sampling (landslide polygon, smoothing digital terrain model derived landslide conditioning factors, polygon buffering and landslide centroid), resulting in eight sampling scenarios. Using Logistic Regression, Neural Network, Random Forest and Support Vector Machine algorithm, 32 models were derived and analysed. The main conclusions reveal that polygon sampling of unstable areas is an imperative in large-scale modelling, as well as that subjective and/or biased stable area sampling leads to misleading models. Moreover, Random Forest and Neural Network proved to be more favourable methods (0.804 and 0.805 AUC, respectively), but also showed extreme sensitivity to the tested sampling strategies. In the comprehensive comparison, the advantages and disadvantages of 32 derived models were analysed through quantitative and qualitative parameters to highlight their application to large-scale landslide zonation. The results yielded by this research are beneficial to the susceptibility modelling step in large-scale landslide susceptibility assessments as they enable the derivation of more reliable zonation maps applicable to spatial and urban planning systems. [ABSTRACT FROM AUTHOR]

On a global scale, wetlands are suffering from a steady decline in surface area and environmental quality. Protecting them is essential and requires a careful spatialisation of their natural habitats. Traditionally, in our study area, species discrimination for floristic mapping has been achieved through on-site field inventories, but this approach is very time-consuming in these difficult-to-access environments. Usually, the resulting maps are also not spatially exhaustive and are not frequently updated. In this paper, we propose to establish a complete map of the study area using remote sensors and set up a long-term and regular observatory of environmental changes to monitor the evolution of a major French wetland. This methodology combines three dataset acquisition technologies, airborne hyperspectral and WorldView-3 multispectral images, supplemented by LiDAR images, which we compared to evaluate the difference in performances. To do so, we applied the Random Forest supervised classification methods using ground reference areas and compared the out-of-bag score (OOB score) as well as the matrix of confusion resulting from each dataset. Thirteen habitats were discriminated at level 4 of the European Nature Information System (EUNIS) typology, at a spatial resolution of around 1.2 m. We first show that a multispectral image with 19 variables produces results which are almost as good as those produced by a hyperspectral image with 58 variables. The experiment with different features also demonstrates that the use of four bands derived from LiDAR datasets can improve the quality of the classification. Invasive alien species Ludwigia grandiflora and Crassula helmsii were also detected without error which is very interesting when applied to these endangered environments. Therefore, since WV-3 images provide very good results and are easier to acquire than airborne hyperspectral data, we propose to use them going forward for the regular observation of the Brière marshes habitat we initiated. [ABSTRACT FROM AUTHOR]

Effective planning and management strategies for restoring and conserving tropical peat swamp ecosystems require accurate and timely estimates of aboveground biomass (AGB), especially when monitoring the impacts of restoration interventions. The aim of this research is to assess changes in AGB and evaluate the effectiveness of restoration efforts in the North Selangor Peat Swamp Forest (NSPSF), one of the largest remaining peat swamp forests in Peninsular Malaysia, using advanced remote sensing techniques. A Random Forest machine learning method was employed to upscale AGB estimates, derived from a 'LiDAR AGB model', to larger landscape-scale areas with Sentinel-2 spectral and textural variables. The time period under investigation (2015–2018) marked a concentrated phase of restoration and regeneration efforts in NSPSF. The results demonstrate an overall increase in tropical peat swamp AGB during these years, where the total amount of estimated AGB stored in NSPSF increased from 19.3 Tg in 2015 to an estimated 19.8 Tg in 2018. The research found that a tailored variable selection approach improved predictions of AGB, with optimised input variables (n = 62) and parameter adjustments producing a good plausible result (R2 = 0.80; RMSE = 55.2 Mg/ha). This paper concludes by emphasizing the importance of long-term studies (>5 years) for analyzing the success of tropical peat swamp restoration methods, with a potential for integrating remote sensing technology. [ABSTRACT FROM AUTHOR]

The complexity of surface characteristics in rural areas poses challenges for accurate extraction of built-up areas from remote sensing images. The Artificial Surface Index (ASI) emerged as a novel and accurate built-up land index. However, the absence of short-wave infrared (SWIR) bands in most high-resolution (HR) images restricts the application of index-based methods in rural built-up land extraction. This paper presents a rapid extraction method for high-resolution built-up land in rural areas based on ASI. Through the downscaling techniques of random forest (RF) regression, high-resolution SWIR bands were generated. They were then combined with visible and near-infrared (VNIR) bands to compute ASI on GaoFen-2 (GF-2) images (called A S I G F ). Furthermore, a red roof index (RRI) was designed to reduce the probability of misclassifying built-up land with bare soil. The results demonstrated that SWIR downscaling effectively compensates for multispectral information absence in HR imagery and expands the applicability of index-based methods to HR remote sensing data. Compared with five other indices (UI, BFLEI, NDBI, BCI, and PISI), the combination of ASI and RRI achieved the optimal performance in built-up land enhancement and bare land suppression, particularly showcasing superior performance in rural built-up land extraction. [ABSTRACT FROM AUTHOR]

The emergency response is crucial in preventing and mitigating urban floods. Both remote sensing and social media data offer distinct advantages in large-scale flood monitoring and near-real-time flood monitoring. However, current research lacks a thorough exploration of the application of social media data and remote sensing imagery in the urban flood emergency response. To address this issue, this paper, while extracting disaster information based on social media data, deeply mines the spatiotemporal distribution characteristics and dynamic spatial accessibility of rescue points. Furthermore, SAR imagery and social media data for monitoring urban flooding are compared. This study took the Zhengzhou 7.20 urban flood as a case study and created a methodological framework to quickly extract flood disaster information (flood, landslide, and rescue points) using these two types of data; spatiotemporal analysis and random forest classification were also conducted to mine valuable information. Temporally, the study revealed that disaster information did not increase proportionally with the amount of rainfall during the rainfall process. Spatially, specific regions with higher susceptibility to flooding, landslides, and rescue points were identified, such as the central region characterized by low drainage standards and high-density urban areas, as well as the eastern region with low-lying terrain. Moreover, this study examined the spatial accessibility of rescue resources in real flood scenarios and found that their service coverage varied throughout the day during and after the disaster. In addition, social media excelled in high-density urban areas' flood point extraction, while SAR performed better in monitoring floods at the edges of low-density urban areas and large water bodies, allowing them to complement each other, to a certain extent. The findings of this study provide scientific reference value for the optimal selection of rescue paths and the allocation of resources in the emergency response to urban floods caused by extreme rainstorms. [ABSTRACT FROM AUTHOR]

Northeast China plays a pivotal role in producing commodity grains. The precipitation and temperature distribution during the growth season is impacted by geographical and climate factors, rendering the region vulnerable to drought. However, relying on a single index does not reflect the severity and extent of drought in different regions. This research utilised the random forest (RF) model for screening remote sensing indices. Relative soil moisture (RSM) was employed to compare seven commonly used indices: the temperature vegetation dryness index (TVDI), vegetation supply water index (VSWI), vegetation condition index (VCI), temperature condition index (TCI), vegetation health index (VHI), multi-band drought index (MBDI), and normalised difference drought index (NDDI). The effectiveness of these indices for monitoring drought during different developmental stages of spring maize was evaluated. Trend rates were employed to investigate the temporal changes in drought patterns of spring maize from 2003 to 2020, and the Sen + Mann–Kendall test was used to analyse spatial variations. The results showed the following: (1) The seven remote sensing indices could accurately track drought during critical growth stages with the TVDI demonstrating higher applicability than the other six indices. (2) The application periods of two TVDIs with different parameters differed for the drought monitoring of spring maize in different developmental periods. The consistency and accuracy of the normalised difference vegetation index (NDVI)-based TVDI (TVDIN) were 5.77% and 34.62% higher than those of the enhanced vegetation index (EVI)-based TVDI (TVDIE), respectively, in the early stage. In contrast, the TVDIE exhibited 13.46% higher consistency than the TVDIN in the middle stage, and the accuracy was the same. During the later stage, the TVDIE showed significantly higher consistency and accuracy than the TVDIN with consistency increases of 9.61% and 38.64%, respectively. (3) The drought trend in northeast China increased from 2003 to 2020, exhibiting severe spring drought and a weakening of the drought in summer. The southern, southwestern, and northwestern parts of northeast China showed an upward drought trend; the drought-affected areas accounted for 37.91% of the study area. This paper identified the most suitable remote sensing indices for monitoring drought in different developmental stages of spring maize. The results provide a comprehensive understanding of the spatial–temporal patterns of drought during the past 18 years. These findings can be used to develop a dynamic agricultural drought monitoring model to ensure food security. [ABSTRACT FROM AUTHOR]

Mountain areas in China account for 69% of the total land area; however, it is still an urgent that we grasp the special ecological structure of mountain areas and maximize the resource advantages of mountain areas under the principle of maintaining a certain ecological level. In this paper, Landsat 5, Landsat 8 and Sentinel-2A images were used as data sources to monitor and analyze land development and ecological change in Gui 'an in 2010, 2013, 2016, 2019 and 2021, so as to explore ecological maintenance mechanisms. Firstly, random forest classification based on multi-source remote sensing data was used to classify land, and the five phases of land-use change were assessed using quantitative analysis, in order to analyze the mountain region's land-use-change characteristics at different stages of development. The results show that Gui 'an has the "two-stage", rapid-development, rapid-recovery mode. Each stage includes a development-and-expansion period and a construction-and-protection period. In the construction period, ecological recovery construction will be emphasized, and the change intensity and rate of the second stage are lower than that of the first stage. Secondly, using a remote sensing ecological index, vegetation coverage, and a landscape index, an ecological evaluation model of the study area was constructed to analyze changes in the ecological environment and its protection in the process of land development. The ecological maintenance status of the five stages was quantitatively monitored using the analysis methods of difference change and coefficient of variation. The results showed that in the first stage of land development and expansion, the landscape pattern and ecological quality fluctuated greatly, and the proportion of ecological quality of an excellent grade decreased by 28.46%. However, in the second stage, the change slowed down and remained unchanged, and gradually moved to the middle and upper level. The results show that there is a close relationship between ecological maintenance and the land development mode, and new mountain towns can maintain ecological quality and achieve sustainable development through a reasonable land development mode. At the end of this paper, the factors affecting the ecological maintenance capacity of Gui 'an are discussed, providing effective reference material and development models for the development of mountainous areas. [ABSTRACT FROM AUTHOR]

The continuous transformation from biodiverse natural forests and mixed-use farms into monoculture rubber plantations may lead to a series of hazards, such as natural forest habitats fragmentation, biodiversity loss, as well as drought and water shortage. Therefore, understanding the spatial distribution of rubber plantations is crucial to regional ecological security and a sustainable economy. However, the spectral characteristics of rubber tree is easily mixed with other vegetation such as natural forests, tea plantations, orchards and shrubs, which brings difficulty and uncertainty to regional scale identification. In this paper, we proposed a classification method combines multi-source phenology characteristics and random forest algorithm. On the basis of optimization of input samples and features, phenological spectrum, brightness, greenness, wetness, fractional vegetation cover, topography and other features of rubber were extracted. Five classification schemes were constructed for comparison, and the one with the highest classification accuracy was used to identify the spatial pattern of rubber plantations in 2014, 2016, 2018 and 2020 in Xishuangbanna. The results show that: (1) the identification results are in consistent with field survey and rubber plantations area generally shows a first increasing and then decreasing trend; (2) the Overall Accuracy (OA) and Kappa coefficient of the proposed method are 90.0% and 0.86, respectively, with a Producer's Accuracy (PA) and User's Accuracy (UA) of 95.2% and 88.8%, respectively; (3) cross-validation was employed to analyze the accuracy evaluation indexes of the identification results: both PA and UA of the rubber plantations stay stable over 85%, with the minimum fluctuation and best stability of UA value. The OA value and Kappa coefficient were stable in the range of 0.88–0.90 and 0.84–0.86, respectively. The method proposed provides reliable results on spatial distribution of rubber, and is potentially transferable to other mountainous areas as a robust approach for rapid monitoring of rubber plantations. [ABSTRACT FROM AUTHOR]

Affected by geographical location and climatic conditions, crop classification in the Yunnan Plateau of China is greatly restricted by the low utilization rate of annual optical data, complex crop planting structure, and broken cultivated land. This paper combines monthly Sentinel-2 optical remote sensing data with Sentinel-1 radar data to minimize cloud interference to conduct crop classification for plateau areas. However, pixel classification will inevitably produce a "different spectrum of the same object, foreign objects in the same spectrum". A principal component feature synthesis method is developed for multi-source remote sensing data (PCA-MR) to improve classification accuracy. In order to compare and analyze the classification effect of PCA-MR combined with multi-source remote sensing data, we constructed 11 classification scenarios using the Google Earth Engine platform and random forest algorithm (RF). The results show that: (1) the classification accuracy is 79.98% by using Sentinel-1 data and 91.18% when using Sentinel-2 data. When integrating Sentinel-1 and Sentinel-2 data, the accuracy is 92.31%. By analyzing the influence of texture features on classification under different feature combinations, it was found that optical texture features affected the recognition accuracy of rice to a lesser extent. (2) The errors will be reduced if the PCA-MR feature is involved in the classification, and the classification accuracy and Kappa coefficient are improved to 93.47% and 0.92, respectively. [ABSTRACT FROM AUTHOR]

Forest logging detection is important for sustainable forest management. The traditional optical satellite images with visible and near-infrared bands showed the ability to identify intensive timber logging. However, less intensive logging is still difficult to detect with coarse spatial resolution such as Landsat or high spatial resolution in fewer spectral bands. Although more high-resolution remote sensing images containing richer spectral bands can be easily obtained nowadays, the questions of whether they facilitate the detection of logging patterns and which spectral bands are more effective in detecting logging patterns, especially in selective logging, remain unresolved. Therefore, this paper aims to evaluate the combinations of visible, near-infrared, red-edge, and short-wave infrared bands in detecting three different logging intensity patterns, including unlogged (control check, CK), selective logging (SL), and clear-cutting (CC), in north subtropical plantation forests with the random forest algorithm using Sentinel-2 multispectral imagery. This study aims to explore the recognition performance of different combinations of spectral bands (visual (VIS) and near-infrared bands (NIR), VIS, NIR combined with red-edge, VIS, NIR combined with short-wave infrared bands (SWIR), and full-spectrum bands combined with VIS, NIR, red edge and SWIR) and to determine the best spectral variables to be used for identifying logging patterns, especially in SL. The study was conducted in Taizishan in Hubei province, China. A total of 213 subcompartments of different logging patterns were collected and the random forest algorithm was used to classify logging patterns. The results showed that full-spectrum bands which contain the red-edge and short-wave infrared bands improve the ability of conventional optical satellites to monitor forest logging patterns and can achieve an overall accuracy of 85%, especially for SL which can achieve 79% and 64% for precision and recall accuracy, respectively. The red-edge band (698–713 nm, B5 in Sentinel-2), short-wave infrared band (2100–2280 nm, B12 in Sentinel-2), and associated vegetation indices (NBR, NDre2, and NDre1) enhance the sensitivity of the spectral information to logging patterns, especially for the SL pattern, and the precision and recall accuracy can improve by 10% and 6%, respectively. Meanwhile, both clear-cutting and unlogged patterns could be well-classified whether adding a red-edge or SWIR band or both in VIS and NIR bands; the best precision and recall accuracies for clear-cutting were enhanced to 97%, 95% and 81%, 91% for unlogged, respectively. Our results demonstrate that the optical images have the potential ability to detect logging patterns especially for the clear-cutting and unlogged patterns, and the selective logging detection accuracy can be improved by adding red-edge and short-wave infrared spectral bands. [ABSTRACT FROM AUTHOR]

Urban forests maintain the ecological balance of cities and are significant in promoting the sustainable development of cities. Therefore, using advanced remote sensing technology to accurately extract forest green space in the city and monitor its change in real-time is very important. Taking Nanjing as the study area, this research extracted 55 vegetation phenological features from Sentinel-2A time series images and formed a feature set containing 81 parameters together with 26 features, including polarimetric- and texture-related information extracted from dual-polarization Sentinel-1A data. On the basis of the improved ABC (ABC-LIBSVM) feature selection method, the optimal feature subset was selected, and the forest coverage areas in the study area were accurately described. To verify the feasibility of the improved feature selection method and explore the potential for the development of multi-source time series remote sensing for urban forest feature extraction, this paper also used the random forest classification model to classify four different feature sets. The results revealed that the classification accuracy based on the feature set obtained by the ABC-LIBSVM algorithm was the highest, with an overall accuracy of 86.80% and a kappa coefficient of 0.8145. The producer accuracy and user accuracy of the urban forest were 93.21% and 82.45%, respectively. Furthermore, by combining the multi-source time series Sentinel-2A optical images with Sentinel-1A dual-polarization SAR images, urban forests can be distinguished from the perspective of phenology, and polarimetric- and texture-related features can contribute to the accurate identification of forests. [ABSTRACT FROM AUTHOR]

The class imbalance problem has been reported to exist in remote sensing and hinders the classification performance of many machine learning algorithms. Several technologies, such as data sampling methods, feature selection-based methods, and ensemble-based methods, have been proposed to solve the class imbalance problem. However, these methods suffer from the loss of useful information or from artificial noise, or result in overfitting. A novel double ensemble algorithm is proposed to deal with the multi-class imbalance problem of the hyperspectral image in this paper. This method first computes the feature importance values of the hyperspectral data via an ensemble model, then produces several balanced data sets based on oversampling and builds a number of classifiers. Finally, the classification results of these diversity classifiers are combined according to a specific ensemble rule. In the experiment, different data-handling methods and classification methods including random undersampling (RUS), random oversampling (ROS), Adaboost, Bagging, and random forest are compared with the proposed double random forest method. The experimental results on three imbalanced hyperspectral data sets demonstrate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In light of the need for fine-grained, accurate, and timely urban land use information, a per-field classification approach was proposed in this paper to automatically map fine-grained urban land use in a study area within Haidian District, Beijing, China, in 2016. High-resolution remote sensing imagery and multi-source social sensing data were used to provide both physical and socioeconomic information. Four categories of attributes were derived from both data sources for urban land use parcels segmented by the OpenStreetMap road network, including spectral/texture attributes, landscape metrics, Baidu Point-Of-Interest (POI) attributes, and Weibo attributes. The random forests technique was adopted to conduct the classification. The importance of each attribute, attribute category, and data source was evaluated for the classification as a whole and the classification of individual land use types. The results showed that a testing accuracy of 77.83% can be achieved. The approach is relatively good at classifying open space and residential parcels, and poor at classifying institutional parcels. While using solely remote sensing data or social sensing data can achieve equally high overall accuracy, their importance varies in terms of the classification of individual classes. Landscape metrics are the most important for open space parcels. Spectral/texture attributes are more important in identifying institutional and residential parcels. The classification of business parcels relies more on landscape metrics and social sensing data, and less on spectral/texture attributes. The classification accuracy can be potentially improved upon the acquisition of purer parcels and the addition of new attributes. It is expected that the proposed approach will be useful for the routine update of urban land use information and large-scale urban land use mapping. [ABSTRACT FROM AUTHOR]

Cloud detection of remote sensing imagery is quite challenging due to the influence of complicated underlying surfaces and the variety of cloud types. Currently, most of the methods mainly rely on prior knowledge to extract features artificially for cloud detection. However, these features may not be able to accurately represent the cloud characteristics under complex environment. In this paper, we adopt an innovative model named Fuzzy Autoencode Model (FAEM) to integrate the feature learning ability of stacked autoencode networks and the detection ability of fuzzy function for highly accurate cloud detection on remote sensing imagery. Our proposed method begins by selecting and fusing spectral, texture, and structure information. Thereafter, the proposed technique established a FAEM to learn the deep discriminative features from a great deal of selected information. Finally, the learned features are mapped to the corresponding cloud density map with a fuzzy function. To demonstrate the effectiveness of the proposed method, 172 Landsat ETM+ images and 25 GF-1 images with different spatial resolutions are used in this paper. For the convenience of accuracy assessment, ground truth data are manually outlined. Results show that the average RER (ratio of right rate and error rate) on Landsat images is greater than 29, while the average RER of Support Vector Machine (SVM) is 21.8 and Random Forest (RF) is 23. The results on GF-1 images exhibit similar performance as Landsat images with the average RER of 25.9, which is much higher than the results of SVM and RF. Compared to traditional methods, our technique has attained higher average cloud detection accuracy for either different spatial resolutions or various land surfaces. [ABSTRACT FROM AUTHOR]

Under the strong influence of climate change and human activities, the frequency and intensity of disturbance events in the forest ecosystem both show significant increasing trends. Pine wood nematode (Bursapherenchus xylophilus, PWN) is one of the major alien invasive species in China, which has rapidly infected the forest and spread. In recent years, its tendency has been to spread from south to north, causing serious losses to Pinus and non-Pinus coniferous forests. It is urgent to carry out remote sensing monitoring and prediction of pine wilt disease (PWD). Taking Anhui Province as the study area, we applied ground survey, satellite-borne optical remote sensing imagery and environmental factor statistics, relying on the Google Earth Engine (GEE) platform to build a new vegetation index NDFI based on time-series Landsat images to extract coniferous forest information and used a random forest classification algorithm to build a monitoring model of the PWD infection stage. The results show that the proposed NDFI differentiation threshold classification method can accurately extract the coniferous forest range, with the overall accuracy of 87.75%. The overall accuracy of the PWD monitoring model based on random forest classification reaches 81.67%, and the kappa coefficient is 0.622. High temperature and low humidity are conducive to the survival of PWN, which aggravates the occurrence of PWD. Under the background of global warming, the degree of PWD in Anhui Province has gradually increased, and has transferred from the southwest and south to the middle and northeast. Our results show that PWD monitoring and prediction at a regional scale can be realized by using long time-series multi-source remote sensing data, NDFI index can accurately extract coniferous forest information and grasp disease information in a timely manner, which is crucial for effective monitoring and control of PWD. [ABSTRACT FROM AUTHOR]

Leaf area index (LAI) is a key variable for monitoring crop growth. Compared with traditional measurement methods, unmanned aerial vehicle (UAV) remote sensing offers a cost-effective and efficient approach for rapidly obtaining crop LAI. Although there is extensive research on rice LAI estimation, many studies suffer from the limitations of models that are only applicable to specific scenarios with unclear applicability conditions. In this study, we selected commonly used RGB and multispectral (Ms) data sources, which contain three channels of color information and five multi-band information, respectively, combined with five different spatial resolutions of data at intervals of 20–100 m. We evaluated the effectiveness of models using single- and multi-feature variables for LAI estimation in rice. In addition, texture and coverage features other than spectra were introduced to further analyze their effects on the inversion accuracy of the LAI. The results show that the accuracy of the model established with multi-variables under single features is significantly higher than that of the model established with single variables under single features. The best results were obtained using the RFR (random forest regression) model, in which the model's R2 is 0.675 and RMSE is 0.886 for multi-feature VIs at 40 m. Compared with the analysis results of Ms and RGB data at different heights, the accuracy of Ms data estimation results fluctuates slightly and is less sensitive to spatial resolution, while the accuracy of the results based on RGB data gradually decreases with the increase in height. The estimation accuracies of both Ms and RGB data were improved by adding texture features and coverage features, and their R2 improved by 9.1% and 7.3% on average. The best estimation heights (spatial resolution) of the two data sources were 40 m (2.2 cm) and 20 m (0.4 cm), with R2 of 0.724 and 0.673, and RMSE of 0.810 and 0.881. This study provides an important reference for the estimation of rice LAI based on RGB and Ms data acquired using the UAV platform. [ABSTRACT FROM AUTHOR]

To optimize growth and management, precision agriculture relies on a deep understanding of agricultural dynamics, particularly crop water status analysis. Leveraging unmanned aerial vehicles, we can efficiently acquire high-resolution spatiotemporal samples by utilizing remote sensors. However, non-linear relationships among data features, localized within specific subgroups, frequently emerge in agricultural data. Interpreting these complex patterns requires sophisticated analysis due to the presence of noise, high variability, and non-stationarity behavior in the collected samples. Here, we introduce Local Biplot, a methodological framework tailored for discerning meaningful data patterns in non-stationary contexts for precision agriculture. Local Biplot relies on the well-known uniform manifold approximation and projection method, such as UMAP, and local affine transformations to codify non-stationary and non-linear data patterns while maintaining interpretability. This lets us find important clusters for transformation and projection within a single global axis pair. Hence, our framework encompasses variable and observational contributions within individual clusters. At the same time, we provide a relevance analysis strategy to help explain why those clusters exist, facilitating the understanding of data dynamics while favoring interpretability. We demonstrated our method's capabilities through experiments on both synthetic and real-world datasets, covering scenarios involving grass and rice crops. Moreover, we use random forest and linear regression models to predict water status variables from our Local Biplot-based feature ranking and clusters. Our findings revealed enhanced clustering and prediction capability while emphasizing the importance of input features in precision agriculture. As a result, Local Biplot is a useful tool to visualize, analyze, and compare the intricate underlying patterns and internal structures of complex agricultural datasets. [ABSTRACT FROM AUTHOR]

The eastern coastline of James Bay is known to have been home to sizeable eelgrass beds (Zostera marina L.) which thrived in the bay's shallow, subarctic waters. The region was subjected to substantial hydroelectric dams, large fires, and other human activities in the past half-century. To assess the impact of these factors on eelgrass beds, a historical reconstruction of eelgrass bed distribution was performed from images acquired by Landsat-5 Thematic Mapper (TM) in 1988, 1991, and 1996 and images of the Landsat-8 Operational Land Imager (OLI) in 2019. All the images were classified using the Random Forests classifier (RF) and assessed for accuracy each year on a bay-wide scale using an independent field validation dataset. The validation data were extracted from an eelgrass bed map established using aerial photos and field surveys in 1986, 1991, and 1995 and from a field survey in 2019. The overall validation accuracy of the classified images (between 72% and 85%) showed good agreement with the other datasets for most locations, providing reassurance about the reliability of the research. This makes it possible to use satellite imagery to detect past changes to eelgrass distribution within a bay. The classified images of 1988 and 1996 were also compared to aerial photos taken in years close to each other at ten sites to determine their ability to assess small eelgrass beds' shape and presence. Such a comparison revealed that the classified images accurately portrayed eelgrass distribution even at finer scales. [ABSTRACT FROM AUTHOR]

Due to the country's rapid economic growth, the problem of air pollution in China is becoming increasingly serious. In order to achieve a win-win situation for the environment and urban development, the government has issued many policies to strengthen environmental protection. PM2.5 is the primary particulate matter in air pollution, so an accurate estimation of PM2.5 distribution is of great significance. Although previous studies have attempted to retrieve PM2.5 using geostatistical or aerosol remote sensing retrieval methods, the current rough resolution and accuracy remain as limitations of such methods. This paper proposes a fine-grained spatiotemporal PM2.5 retrieval method that comprehensively considers various datasets, such as Landsat 8 satellite images, ground monitoring station data, and socio-economic data, to explore the applicability of different machine learning algorithms in PM2.5 retrieval. Six typical algorithms were used to train the multi-dimensional elements in a series of experiments. The characteristics of retrieval accuracy in different scenarios were clarified mainly according to the validation index, R2. The random forest algorithm was shown to have the best numerical and PM2.5-based air-quality-category accuracy, with a cross-validated R2 of 0.86 and a category retrieval accuracy of 0.83, while both maintained excellent retrieval accuracy and achieved a high spatiotemporal resolution. Based on this retrieval model, we evaluated the PM2.5 distribution characteristics and hourly variation in the sample area, as well as the functions of different input variables in the model. The PM2.5 retrieval method proposed in this paper provides a new model for fine-grained PM2.5 concentration estimation to determine the distribution laws of air pollutants and thereby specify more effective measures to realize the high-quality development of the city. [ABSTRACT FROM AUTHOR]

Plastic mulching is an important technology in agricultural production both in China and the rest of the world. In spite of its benefit of increasing crop yields, the booming expansion of the plastic mulching area has been changing the landscape patterns and affecting the environment. Accurate and effective mapping of Plastic-Mulched Farmland (PMF) can provide useful information for leveraging its advantages and disadvantages. However, mapping the PMF with remote sensing is still challenging owing to its varying spectral characteristics with the crop growth and geographic spatial division. In this paper, we investigated the potential of Radarsat-2 data for mapping PMF.We obtained the backscattering intensity of different polarizations and multiple polarimetric decomposition descriptors. These remotely-sensed information was used as input features for Random Forest (RF) and Support Vector Machine (SVM) classifiers. The results indicated that the features from Radarsat-2 data have great potential for mapping PMF. The overall accuracies of PMF mapping with Radarsat-2 data were close to 75%. Although the classification accuracy with the back-scattering intensity information alone was relatively lower owing to the inherent speckle noise in SAR data, it has been improved significantly by introducing the polarimetric decomposition descriptors. The accuracy was nearly 75%. In addition, the features derived from the Entropy/Anisotropy/Alpha (H/A/Alpha) polarimetric decomposition, such as Alpha, entropy, and so on, made a greater contribution to PMF mapping than the Freeman decomposition, Krogager decomposition and the Yamaguchi4 decomposition. The performances of different classifiers were also compared. In this study, the RF classifier performed better than the SVM classifier. However, it is expected that the classification accuracy of PMF with SAR remote sensing data can be improved by combining SAR remote sensing data with optical remote sensing data. [ABSTRACT FROM AUTHOR]

Land cover information is necessary for a large range of environmental applications related to climate impacts and adaption, emergency response, wildlife habitat, etc. In Canada, a 2008 user survey indicated that the most practical land cover data is provided in a nationwide 30 m spatial resolution format, with an update frequency of five years. In response to this need, the Canada Centre for Remote Sensing (CCRS) has generated a 30 m land cover map of Canada for the base year 2010, as the first of a planned series of maps to be updated every five years, or more frequently. This land cover dataset is also the Canadian contribution to the 30 m spatial resolution 2010 Land Cover Map of North America, which is produced by Mexican, American and Canadian government institutions under a collaboration called the North American Land Change Monitoring System (NALCMS). This paper describes the mapping approach used for generating this land cover dataset for Canada from Thematic Mapper (TM) and Enhanced Thematic Mapper (ETM+) Landsat sensor observations. The innovative part of the mapping approach is the local optimization of the land cover classifier, which has resulted in increased spatial consistency and accuracy. Training and classifying with locally confined reference samples over a large number of partially overlapping areas (i.e., moving windows) ensures the optimization of the classifier to a local land cover distribution, and decreases the negative effect of signature extension. A weighted combination of labels, which is determined by the classifier in overlapping windows, defines the final label for each pixel. Since the approach requires extensive computation, it has been developed and deployed using the Government of Canada's High-Performance Computing Center (HPC). An accuracy assessment based on 2811 randomly distributed samples shows that land cover data produced with this new approach has achieved 76.60% accuracy with no marked spatial disparities. [ABSTRACT FROM AUTHOR]

The population of Africa is expected to rise to 2.5 billion by 2050, with more than 80% of this increase concentrated in cities. Africa's anticipated population growth has serious implications for urban resource utilization and management, necessitating multi-level monitoring efforts that can inform planning and decision-making. Commonly, broad extent (e.g., country level) urban change analyses only examine a homogenous "developed" or "built-up" area, which may not capture patterns influenced by the heterogeneity of landscape features within urban areas. Contrarily, studies examining landscape heterogeneity at a finer resolution are typically limited in spatial extent (e.g., single city level). The goal of this study was to develop and test a hierarchical integrated mapping framework using globally available Earth Observation data (e.g., Landsat, Sentinel-2, Sentinel-1, and nightlight imagery) and accessible methodologies to produce national-level land use (LU) and urban-level land cover (LC) map products which may support a range of global and local monitoring and planning initiatives. We test our multi-tier methodology across three rapidly urbanizing African countries for the 2016–2020 period: Ethiopia, Nigeria, and South Africa. The initial output of our methodology includes annual national land use maps (Tier 1) for the purpose of delineating the dynamic boundaries of individual urban areas and monitoring national LU change. To complement Tier 1 LU maps, we detailed urban heterogeneity through LC classifications within urban areas (Tier 2) delineated using Tier 1 LU maps. Based on country-optimized sets of selected features that leverage spatial/texture and temporal dimensions of available data, we obtained an overall map accuracy of between 65 and 80% for Tier 1 maps and between 60 and 80% for Tier 2 maps, dependent on the evaluation country, although with consistent performance across study years providing a solid foundation for monitoring changes. We demonstrate the potential applications for our products through various analyses, including urbanization-driven LU change, and examine LC urban patterns across the three African study countries. While our findings allude to general differences in urban patterns across national scales, further analyses are needed to better understand the complex drivers behind urban LC configurations and their change patterns across different countries, city sizes, and rates of urbanization. Our multi-tier mapping framework is a viable strategy for producing harmonious, multi-level LULC products in developing countries using publicly available data and methodologies, which can serve as a basis for a wide range of informative and insightful monitoring analyses. [ABSTRACT FROM AUTHOR]

The distribution of forest-dominant tree species is crucial for ecosystem assessment. Remote sensing monitoring requires annual ground sample data, but consistent field surveys are challenging. This study addresses this by combining sample migration learning and machine learning for multi-year tree species classification in the Three Gorges Reservoir area in China. Using the continuous change detection and classification (CCDC) algorithm, sample data from 2023 were successfully migrated to 2018–2022, achieving high migration accuracy ( R 2 = 0.8303, RMSE = 4.64). Based on migrated samples, random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB) algorithms classified forest tree species with overall accuracies above 70% and Kappa coefficients above 0.6. XGB. They outperformed other algorithms, with classification accuracy of over 80% and Kappa above 0.75 in almost all years. The final map indicates stable distribution from 2018 to 2023, with eucalyptus covering over 40% of the forest area, followed by horsetail pine, fir, cypress, and wetland pine. [ABSTRACT FROM AUTHOR]

A'nyemaqen Snow Mountain (ASM) is the largest glacier area in the Yellow River source area and has been experiencing significant ablation in recent years. To investigate spatial–temporal elevation changes in ASM, a 21–year Digital Elevation Model (DEM) time series was obtained using the MicMac ASTER (MMASTER) algorithm and ASTER L1A V003 data. It covers the period from January 2002 to January 2023. The mean elevation of ASM decreased by −7.88 ± 3.37 m during this period, with highly spatial variation. The elevation decrease occurred mainly in the lower elevations and opposite in the higher elevations. The corresponding elevation decrease was −12.99 ± 11.29 and −4.45 ± 11.36 m at the southern Yehelong Glacier and the northern Weigeledangxiong Glacier, respectively. Moreover, there exists a temporal variation in ASM. The maximum elevation was observed in February for both ASM and the southern Yehelong Glacier but March for Weigeledangxiong Glacier, with about 1 month lagged. With the elevation time series and climate data from ERA5 datasets, we applied the random forest technique and found that the temperature is the main factor to elevation change in ASM. Furthermore, the response of elevation changes to temperature appeared with a lag and varied with the location. Based on the elevation time series, the ARIMA model was further used to forecast the elevation changes in the next 5 years. All regions will experience the elevation decrease, with a mean decline −1.74 ± 0.39 m and a corresponding rate −0.35 ± 0.08 m/a in ASM. This is similar to that of −0.38 ± 0.16 m/a between 2002 and 2003, showing its stability in the near future. [ABSTRACT FROM AUTHOR]

Cloud-based remote sensing has spurred the use of techniques to improve mapping accuracy where individual images may have lower quality, especially in areas with complex terrain or high cloud cover. This study investigates the influence of image compositing and multisource data fusion on the multitemporal land cover mapping of the Pagsanjan-Lumban and Baroro Watersheds in the Philippines. Ten random forest models for each study site were used, all using a unique combination of more than 100 different input features. These features fall under three general categories. First, optical features were derived from reflectance bands and ten spectral indices, which were further subdivided into annual percentile and seasonal median composites; second, radar features were derived from ALOS PALSAR by computing textural indices and a simple band ratio; and third, topographic features were computed from the ALOS GDSM. Then, accuracy metrics and McNemar's test were used to assess and compare the significance of about 90 pairwise model outputs. Data fusion significantly improved the accuracy of multitemporal land cover mapping in most cases. However, image composition had varied impacts for both sites. This could imply local characteristics and feature inputs as potential determinants of the ideal composite method. Hence, the iterative screening or optimization of both input features and composites is recommended to improve multitemporal mapping accuracy. [ABSTRACT FROM AUTHOR]

This study aims to establish a deep learning-based classification framework to efficiently and rapidly distinguish between coniferous and broadleaf forests across the Loess Plateau. By integrating the deep residual neural network (ResNet) architecture with transfer learning techniques and multispectral data from unmanned aerial vehicles (UAVs) and Landsat remote sensing data, the effectiveness of the framework was validated through well-designed experiments. The study began by selecting optimal spectral band combinations, using the random forest algorithm. Pre-trained models were then constructed, and model performance was optimized with different training strategies, considering factors such as image size, sample quantity, and model depth. The results indicated substantial improvements in the model's classification accuracy and efficiency for reasonable image dimensions and sample sizes, especially for an image size of 3 × 3 pixels and 2000 samples. In addition, the application of transfer learning and model fine-tuning strategies greatly enhanced the adaptability and universality of the model in different classification scenarios. The fine-tuned model achieved remarkable performance improvements in forest-type classification tasks, increasing classification accuracy from 85% to 93% in Zhengning, from 89% to 96% in Yongshou, and from 86% to 94% in Baishui, as well as exceeding 90% in all counties. These results not only confirm the effectiveness of the proposed framework, but also emphasize the roles of image size, sample quantity, and model depth in improving the generalization ability and classification accuracy of the model. In conclusion, this research has developed a technological framework for effective forest landscape recognition, using a combination of multispectral data from UAVs and Landsat satellites. This combination proved to be more effective in identifying forest types than was using Landsat data alone, demonstrating the enhanced capability and accuracy gained by integrating UAV technology. This research provides valuable scientific guidance and tools for policymakers and practitioners in forest management and sustainable development. [ABSTRACT FROM AUTHOR]

Winter wheat is one of the major cereal crops globally and one of the top three cereal crops in China. The precise forecasting of the yield of winter wheat holds significant importance in the realms of agricultural management and ensuring food security. The use of multi-temporal remote sensing data for crop yield prediction has gained increasing attention. Previous research primarily focused on utilizing remote sensing data from individual or a few growth stages as input parameters or integrated data across the entire growth period. However, a detailed analysis of the impact of different temporal combinations on the accuracy of yield prediction has not been extensively reported. In this study, we optimized the temporal sequence of growth stages using interpolation methods, constructed a yield prediction model incorporating the enhanced vegetation index (EVI) at different growth stages as input parameters, and employed a random forest (RF) algorithm. The results indicated that the RF model utilizing the EVI from all the temporal combinations throughout the growth period as input parameters accurately predicted the winter wheat yield with an R2 of the calibrated dataset exceeding 0.58 and an RMSE less than 1284 kg/ha. Among the 1023 yield models tested in this study with ten different growth stage combinations, the most accurate temporal combination comprised five stages corresponding to the regreening, erecting, jointing, heading, and filling stages, with an R2 of 0.81 and an RMSE of 1250 kg/ha and an NRMSE of 15%. We also observed a significant decrease in estimation accuracy when the number of growth stages was fewer than five and a certain degree of decline when the number exceeded five. Our findings confirmed the optimal number and combination of growth stages for the best yield prediction, providing substantial insights for winter wheat yield forecasting. [ABSTRACT FROM AUTHOR]

Powdery mildew significantly impacts the yield of natural rubber by being one of the predominant diseases that affect rubber trees. Accurate, non-destructive recognition of powdery mildew in the early stage is essential for the cultivation management of rubber trees. The objective of this study is to establish a technique for the early detection of powdery mildew in rubber trees by combining spectral and physicochemical parameter features. At three field experiment sites and in the laboratory, a spectroradiometer and a hand-held optical leaf-clip meter were utilized, respectively, to measure the hyperspectral reflectance data (350–2500 nm) and physicochemical parameter data of both healthy and early-stage powdery-mildew-infected leaves. Initially, vegetation indices were extracted from hyperspectral reflectance data, and wavelet energy coefficients were obtained through continuous wavelet transform (CWT). Subsequently, significant vegetation indices (VIs) were selected using the ReliefF algorithm, and the optimal wavelengths (OWs) were chosen via competitive adaptive reweighted sampling. Principal component analysis was used for the dimensionality reduction of significant wavelet energy coefficients, resulting in wavelet features (WFs). To evaluate the detection capability of the aforementioned features, the three spectral features extracted above, along with their combinations with physicochemical parameter features (PFs) (VIs + PFs, OWs + PFs, WFs + PFs), were used to construct six classes of features. In turn, these features were input into support vector machine (SVM), random forest (RF), and logistic regression (LR), respectively, to build early detection models for powdery mildew in rubber trees. The results revealed that models based on WFs perform well, markedly outperforming those constructed using VIs and OWs as inputs. Moreover, models incorporating combined features surpass those relying on single features, with an overall accuracy (OA) improvement of over 1.9% and an increase in F1-Score of over 0.012. The model that combines WFs and PFs shows superior performance over all the other models, achieving OAs of 94.3%, 90.6%, and 93.4%, and F1-Scores of 0.952, 0.917, and 0.941 on SVM, RF, and LR, respectively. Compared to using WFs alone, the OAs improved by 1.9%, 2.8%, and 1.9%, and the F1-Scores increased by 0.017, 0.017, and 0.016, respectively. This study showcases the viability of early detection of powdery mildew in rubber trees. [ABSTRACT FROM AUTHOR]

Land cover information extraction through object-based image analysis (OBIA) has become an important trend in remote sensing, thanks to the increasing availability of high-resolution imagery. Segmented objects have a large number of features that cause high-dimension and low-sample size problems in the classification process. In this study, on the basis of a partial least squares generalized linear regression (PLSGLR), we propose a group corrected PLSGLR, known as G-PLSGLR, that aims to reduce the redundancy of object features for land cover identifications. Using Gaofen-2 images, the area of interest was segmented and sampled to generate small sample-size training datasets with 51 object features. The features selected by G-PLSGLR were compared against a guided regularized random forest (GRRF) in metrics of reduction rate, feature redundancy, and accuracy assessment of classification. Three indicators of overall accuracy (OA), user's accuracy (UA), and producer's accuracy (PA) were applied for accuracy assessment in this paper. The result shows that the G-PLSGLR achieved a reduction rate of 9.27 with a feature redundancy of 0.29, and a value of OA 90.63%. The GRRF achieved a reduction rate of 1.61 with a feature redundancy of 0.42, and a value of OA 85.56%. The PA of each land cover category was more than 95% using features selected by G-PLSGLR, while the PA ranged from 77 to 96% using features selected by GRRF. The UA of G-PLSGLR-selected features ranged from 70 to 80% except for grass land and bare land, which achieved 10% higher UA than GRRF-selected features. The G-PLSGLR method we proposed has the advantages of a large reduction rate, low feature redundancy, and high classification performance, which can be applied in OBIA-based land cover classification. [ABSTRACT FROM AUTHOR]

Slum identification in urban settlements is a crucial step in the process of formulation of pro-poor policies. However, the use of conventional methods for slum detection such as field surveys can be time-consuming and costly. This paper explores the possibility of implementing a low-cost standardized method for slum detection. We use spectral, texture and structural features extracted from very high spatial resolution imagery as input data and evaluate the capability of three machine learning algorithms (Logistic Regression, Support Vector Machine and Random Forest) to classify urban areas as slum or no-slum. Using data from Buenos Aires (Argentina), Medellin (Colombia) and Recife (Brazil), we found that Support Vector Machine with radial basis kernel delivers the best performance (with F2-scores over 0.81). We also found that singularities within cities preclude the use of a unified classification model. [ABSTRACT FROM AUTHOR]

Building type information is crucial to many urban studies, including fine-resolution population estimation, urban planning, and management. Although scientists have developed many methods to extract buildings via remote sensing data, only a limited number of them focus on further classification of the extracted results. This paper presents a novel building type classification scheme based on the integration of building height information from LiDAR, textural, spectral, and geometric information from high-resolution remote sensing images, and super-object information from the integrated dataset. Building height information is firstly extracted from LiDAR point clouds using a progressive morphological filter and then combined with high-resolution images for object-oriented segmentation. Multi-resolution segmentation of the combined image is performed to collect super-object information, which provides more information for classification in the next step. Finally, the segmentation results, as well as their super-object information, are inputted into the random forest classifier to obtain building type classification results. The classification scheme proposed in this study is tested through applications in two urban village areas, a type of slum-like land use characterized by dense buildings of different types, heights, and sizes, in Guangzhou, China. Segment level classification of the study area and validation area reached accuracies of 80.02% and 76.85%, respectively, while the building-level results reached accuracies of 98.15% and 87.50%, respectively. The results indicate that the proposed building type classification scheme has great potential for application in areas with multiple building types and complex backgrounds. This study also proves that both building height information and super-object information play important roles in building type classification. More accurate results could be obtained by incorporating building height information and super-object information and using the random forest classifier. [ABSTRACT FROM AUTHOR]

Mapping benthic habitats with bathymetric, acoustic, and spectral data requires georeferenced ground-truth information about habitat types and characteristics. New technologies like autonomous underwater vehicles (AUVs) collect tens of thousands of images per mission making image-based ground truthing particularly attractive. Two types of machine learning (ML) models, random forest (RF) and deep neural network (DNN), were tested to determine whether ML models could serve as an accurate substitute for manual classification of AUV images for substrate type interpretation. RF models were trained to predict substrate class as a function of texture, edge, and intensity metrics (i.e., features) calculated for each image. Models were tested using a manually classified image dataset with 9-, 6-, and 2-class schemes based on the Coastal and Marine Ecological Classification Standard (CMECS). Results suggest that both RF and DNN models achieve comparable accuracies, with the 9-class models being least accurate (~73–78%) and the 2-class models being the most accurate (~95–96%). However, the DNN models were more efficient to train and apply because they did not require feature estimation before training or classification. Integrating ML models into benthic habitat mapping process can improve our ability to efficiently and accurately ground-truth large areas of benthic habitat using AUV or similar images. [ABSTRACT FROM AUTHOR]

Snow plays a crucial role in the global water cycle, providing water to over 20% of the world's population and serving as a vital component for flora, fauna, and climate regulation. Changes in snow patterns due to global warming have far-reaching impacts on water management, agriculture, and other economic sectors such as winter tourism. Additionally, they have implications for environmental stability, prompting migration and cultural shifts in snow-dependent communities. Accurate information on snow and its variables is, thus, essential for both scientific understanding and societal planning. This review explores the potential of remote sensing in monitoring snow water equivalent (SWE) on a large scale, analyzing 164 selected publications from 2000 to 2023. Categorized by methodology and content, the analysis reveals a growing interest in the topic, with a concentration of research in North America and China. Methodologically, there is a shift from passive microwave (PMW) inversion algorithms to artificial intelligence (AI), particularly the Random Forest (RF) and neural network (NN) approaches. A majority of studies integrate PMW data with auxiliary information, focusing thematically on remote sensing and snow research, with limited incorporation into broader environmental contexts. Long-term studies (>30 years) suggest a general decrease in SWE in the Northern Hemisphere, though regional and seasonal variations exist. Finally, the review suggests potential future SWE research directions such as addressing PMW data issues, downsampling for detailed analyses, conducting interdisciplinary studies, and incorporating forecasting to enable more widespread applications. [ABSTRACT FROM AUTHOR]

Monitoring salt marshes with remote sensing is necessary to evaluate their state and restoration. Determining appropriate techniques for this can be overwhelming. Our study provides insight into whether a pixel- or object-based Random Forest classification approach is best for mapping vegetation in north temperate salt marshes. We used input variables from drone images (raw reflectances, vegetation indices, and textural features) acquired in June, July, and August 2021 of a salt marsh restoration and reference site in Aulac, New Brunswick, Canada. We also investigated the importance of input variables and whether using landcover classes representing areas of change was a practical way to evaluate variation in the monthly images. Our results indicated that (1) the classifiers achieved overall validation accuracies of 91.1–95.2%; (2) pixel-based classifiers outperformed object-based classifiers by 1.3–2.0%; (3) input variables extracted from the August images were more important than those extracted from the June and July images; (4) certain raw reflectances, vegetation indices, and textural features were among the most important variables; and (5) classes that changed temporally were mapped with user's and producer's validation accuracies of 86.7–100.0%. Knowledge gained during this study will inform assessments of salt marsh restoration trajectories spanning multiple years. [ABSTRACT FROM AUTHOR]

Remote sensing-based models usually have difficulty in generating spatio-temporally continuous terrestrial evapotranspiration (ET) due to cloud cover and model failures. To overcome this problem, machine learning methods have been widely used to reconstruct ET. Therefore, studies comparing and evaluating the accuracy and effectiveness of reconstruction among different machine learning methods at the basin scale are necessary. In this study, four popular machine learning methods, including deep forest (DF), deep neural network (DNN), random forest (RF) and extreme gradient boosting (XGB), were used to reconstruct the ET product, addressing gaps resulting from cloud cover and model failure. The ET reconstructed by the four methods was evaluated and compared for Heihe River Basin. The results showed that the four methods performed well for Heihe River Basin, but the RF method was particularly robust. It not only performed well compared with ground measurements (R = 0.73) but also demonstrated the ability to fully reconstruct gaps generated by the TSEB model across the entire basin. Validation based on ground measurements showed that the DNN and XGB models performed well (R > 0.70). However, some gaps still existed in the desert after reconstruction using the DNN and XGB models, especially for the XGB model. The DF model filled these gaps throughout the basin, but this model had lower consistency compared with ground measurements (R = 0.66) and yielded many low values. The results of this study suggest that machine learning methods have considerable potential in the reconstruction of ET at the basin scale. [ABSTRACT FROM AUTHOR]

The savannas of Southern Africa are an important dryland ecosystem as they cover up to 54% of the landscape and support a rich variety of biodiversity. This paper evaluates landscape change in savanna vegetation along Chobe Riverfront within Chobe National Park Botswana, from 1982 to 2011 to understand what change may be occurring in land cover. Classifying land cover in savanna environments is challenging because the vegetation spectral signatures are similar across distinct vegetation covers. With vegetation species and even structural groups having similar signatures in multispectral imagery difficulties exist in making discrete classifications in such landscapes. To address this issue, a Random Forest classification algorithm was applied to predict land-cover classes. Additionally, time series vegetation indices were used to support the findings of the discrete land cover classification. Results indicate that a landscape level vegetation shift has occurred across the Chobe Riverfront, with results highlighting a shift in land cover towards more woody vegetation. This represents a degradation of vegetation cover within this savanna landscape environment, largely due to an increasing number of elephants and other herbivores utilizing the Riverfront. The forested area along roads at a further distance from the River has also had a loss of percent cover. The continuous analysis during 1982-2011, utilizing monthly AVHRR (Advanced Very High Resolution Radiometer) NDVI (Normalized Difference Vegetation Index) values, also verifies this change in amount of vegetation is a continuous and ongoing process in this region. This study provides land use planners and managers with a more reliable, efficient and relatively inexpensive tool for analyzing land-cover change across these highly sensitive regions, and highlights the usefulness of a Random Forest classification in conjunction with time series analysis for monitoring savanna landscapes. [ABSTRACT FROM AUTHOR]

Citrus is an important commercial crop in many areas. The management and planning of citrus growing can be supported by timely and efficient monitoring of citrus-growing regions. Their complex planting structure and the weather are likely to cause problems for extracting citrus-growing regions from remote sensing images. To accurately extract citrus-growing regions, deep learning is employed, because it has a strong feature representation ability and can obtain rich semantic information. A novel model for extracting citrus-growing regions by UNet that incorporates an image pyramid structure is proposed on the basis of the Sentinel-2 satellite imagery. A pyramid-structured encoder, a decoder, and multiscale skip connections are the three main components of the model. Additionally, atrous spatial pyramid pooling is used to prevent information loss and improve the ability to learn spatial features. The experimental results show that the proposed model has the best performance, with the precision, the intersection over union, the recall, and the F1-score reaching 88.96%, 73.22%, 80.55%, and 84.54%, respectively. The extracted citrus-growing regions have regular boundaries and complete parcels. Furthermore, the proposed model has greater overall accuracy, kappa, producer accuracy, and user accuracy than the object-oriented random forest algorithm that is widely applied in various fields. Overall, the proposed method shows a better generalization ability, higher robustness, greater accuracy, and less fragmented extraction results. This research can support the rapid and accurate mapping of large-scale citrus-growing regions. [ABSTRACT FROM AUTHOR]

Remote sensing technologies have been successfully used for deforestation monitoring, and with the wide availability of satellite products from different platforms, forest monitoring applications have grown in recent years. The observed potential in these technologies motivates the development of forest mapping and monitoring tools that could also be used for neighboring applications like agriculture or land-use mapping. A literature review confirmed the research areas of interest in deforestation monitoring using synthetic aperture radar (SAR) and data fusion techniques, which guided the formulation of the method developed in this article consisting of a data preprocessing workflow for SAR (Sentinel-1) and multispectral (Sentinel-2) data and a procedure for the selection of a machine learning model for forest/nonforest segmentation evaluated in different combinations of Sentinel-1 and Sentinel-2 bands. The selected model is a random forest algorithm that uses C-band SAR dual-polarimetric bands, intensity features, and vegetation indices derived from optical/multispectral data. The selected random forest classifier's balanced accuracies were 79–81%, and the f1-scores were 0.72–0.76 for the validation set. The results allow the obtention of yearly forest/nonforest and forest loss maps in the study area of Bajo Cauca in Colombia, a region with a documented high deforestation rate. [ABSTRACT FROM AUTHOR]

Bare permafrost refers to permafrost with almost no vegetation on the surface, which is an essential part of the ecosystem of the Tibetan Plateau. An accurate extraction of the boundaries of bare permafrost is vital for studying how it is being impacted by climate change. The accuracy of permafrost and bare land distribution maps is inadequate, and the spatial and temporal resolution is low. This is due to the challenges associated with obtaining significant amounts of data in high-altitude and alpine regions and the limitations of current mapping techniques in effectively integrating multiple factors. This study introduces a novel approach to extracting information about the distribution of bare permafrost. The approach introduced here involves amalgamating a sample extraction method, the fusion of multi-source remote sensing information, and a hierarchical classification strategy. Initially, the available multi-source permafrost data, expert knowledge, and refinement rules for training samples are integrated to produce extensive and consistent permafrost training samples. Using the random forest method, these samples are then utilized to create features and classify permafrost. Subsequently, a methodology utilizing a hierarchical classification approach in conjunction with machine learning techniques is implemented to identify an appropriate threshold for fractional vegetation cover, thereby facilitating the extraction of bare land. The bare permafrost boundary is ultimately derived through layer overlay analysis. The permafrost classification exhibits an overall accuracy of 90.79% and a Kappa coefficient of 0.806. The overall accuracies of the two stratified extractions in bare land were 97.47% and 96.99%, with Kappa coefficients of 0.954 and 0.911. The proposed approach exhibits superiority over the extant bare land and permafrost distribution maps. It is well-suited for retrieving vast bare permafrost regions and is valuable for acquiring bare permafrost distribution data across a vast expanse. It offers technical assistance in acquiring extended-term data on the distribution of exposed permafrost on the Tibetan Plateau. Furthermore, it facilitates the elucidation of the impact of climate change on exposed permafrost. [ABSTRACT FROM AUTHOR]

Remote sensing techniques are frequently applied for the surveying of remote areas, where the use of conventional surveying techniques remains difficult and impracticable. In this paper, we focus on one of the remote glacier areas, namely the Tyndall Glacier area in the Southern Patagonian Icefield in Chile. Based on optical remote sensing data in the form of multi-spectral Sentinel-2 imagery, we analyze the extent of different snow and ice classes on the surface of the glacier by means of pixel-wise classification. Our study comprises three main steps: (1) Labeled Sentinel-2 compliant data are obtained from theoretical spectral reflectance curves, as there are no training data available for the investigated area; (2) Four different classification approaches are used and compared in their ability to identify the defined five snow and ice types, thereof two unsupervised approaches (k-means clustering and rule-based classification via snow and ice indices) and two supervised approaches (Linear Discriminant Analysis and Random Forest classifier); (3) We first focus on the pixel-wise classification of Sentinel-2 imagery, and we then use the best-performing approach for a multi-temporal analysis of the Tyndall Glacier area. While the achieved classification results reveal that all of the used classification approaches are suitable for detecting different snow and ice classes on the glacier surface, the multi-temporal analysis clearly reveals the seasonal development of the glacier. The change of snow and ice types on the glacier surface is evident, especially between the end of ablation season (April) and the end of accumulation season (September) in Southern Chile. [ABSTRACT FROM AUTHOR]

Accurate cotton maps are crucial for monitoring cotton growth and precision management. The paper proposed a county-scale cotton mapping method by using random forest (RF) feature selection algorithm and classifier based on selecting multi-features, including spectral, vegetation indices, and texture features. The contribution of texture features to cotton classification accuracy was also explored in addition to spectral features and vegetation index. In addition, the optimal classification time, feature importance, and the best classifier on the cotton extraction accuracy were evaluated. The results showed that the texture feature named the gray level co-occurrence matrix (GLCM) is effective for improving classification accuracy, ranking second in contribution among all studied spectral, VI, and texture features. Among the three classifiers, the RF showed higher accuracy and better stability than support vector machines (SVM) and artificial neural networks (ANN). The average overall accuracy (OA) of the classification combining multiple features was 93.36%, 7.33% higher than the average OA of the single-time spectrum, and 2.05% higher than the average OA of the multi-time spectrum. The classification accuracy after feature selection by RF can still reach 92.12%, showing high accuracy and efficiency. Combining multiple features and random forest methods may be a promising county-scale cotton classification method. [ABSTRACT FROM AUTHOR]

The type of algorithm employed to classify remote sensing imageries plays a great role in affecting the accuracy. In recent decades, machine learning (ML) has received great attention due to its robustness in remote sensing image classification. In this regard, random forest (RF) and support vector machine (SVM) are two of the most widely used ML algorithms to generate land cover (LC) maps from satellite imageries. Although several comparisons have been conducted between these two algorithms, the findings are contradicting. Moreover, the comparisons were made on local-scale LC map generation either from high or medium resolution images using various software, but not Python. In this paper, we compared the performance of these two algorithms for large area LC mapping of parts of Africa using coarse resolution imageries in the Python platform by the employing Scikit-Learn (sklearn) library. We employed a big dataset, 297 metrics, comprised of systematically selected 9-month composite FegnYun-3C (FY-3C) satellite images with 1 km resolution. Several experiments were performed using a range of values to determine the best values for the two most important parameters of each classifier, the number of trees and the number of variables, for RF, and penalty value and gamma for SVM, and to obtain the best model of each algorithm. Our results showed that RF outperformed SVM yielding 0.86 (OA) and 0.83 (k), which are 1–2% and 3% higher than the best SVM model, respectively. In addition, RF performed better in mixed class classification; however, it performed almost the same when classifying relatively pure classes with distinct spectral variation, i.e., consisting of less mixed pixels. Furthermore, RF is more efficient in handling large input datasets where the SVM fails. Hence, RF is a more robust ML algorithm especially for heterogeneous large area mapping using coarse resolution images. Finally, default parameter values in the sklearn library work well for satellite image classification with minor/or no adjustment for these algorithms. [ABSTRACT FROM AUTHOR]

Despite being recognized as a key component of shallow-water ecosystems, submerged aquatic vegetation (SAV) remains difficult to monitor over large spatial scales. Because of SAV's structuring capabilities, high-resolution monitoring of submerged landscapes could generate highly valuable ecological data. Until now, high-resolution remote sensing of SAV has been largely limited to applications within costly image analysis software. In this paper, we propose an example of an adaptable open-sourced object-based image analysis (OBIA) workflow to generate SAV cover maps in complex aquatic environments. Using the R software, QGIS and Orfeo Toolbox, we apply radiometric calibration, atmospheric correction, a de-striping correction, and a hierarchical iterative OBIA random forest classification to generate SAV cover maps based on raw DigitalGlobe multispectral imagery. The workflow is applied to images taken over two spatially complex fluvial lakes in Quebec, Canada, using Quickbird-02 and Worldview-03 satellites. Classification performance based on training sets reveals conservative SAV cover estimates with less than 10% error across all classes except for lower SAV growth forms in the most turbid waters. In light of these results, we conclude that it is possible to monitor SAV distribution using high-resolution remote sensing within an open-sourced environment with a flexible and functional workflow. [ABSTRACT FROM AUTHOR]

Present approaches in PV (Photovoltaic) detection are known to be scalable to a larger area using machine learning classification and have improved accuracy on a regional scale with deep learning diagnostics. However, it may cause false detection, time, and cost-consuming when regional deep learning models are directly scaled to a larger area, particularly in large-scale, highly urbanized areas. Thus, a novel two-step downscaling methodology integrating machine learning broad spatial partitioning (step-1) and detailed deep learning diagnostics (step-2) is designed and applied in highly urbanized Jiangsu Province, China. In the first step, this methodology selects suitable feature combinations using the recursive feature elimination with distance correlation coefficient (RFEDCC) strategy for the random forest (RF), considering not only feature importance but also feature independence. The results from RF (overall accuracy = 95.52%, Kappa = 0.91) indicate clear boundaries and little noise. Furthermore, the post-processing of noise removal with a morphological opening operation for the extraction result of RF is necessary for the purpose that less high-resolution remote sensing tiles should be applied in the second step. In the second step, tiles intersecting with the results of the first step are selected from a vast collection of Google Earth tiles, reducing the computational complexity of the next step in deep learning. Then, the improved HRNet with high performance on the test data set (Intersection over Union around 94.08%) is used to extract PV plants from the selected tiles, and the results are mapped. In general, for Jiangsu province, the detection rate of the previous PV database is higher than 92%, and this methodology reduces false detection noise and time consumption (around 95%) compared with a direct deep learning methodology. [ABSTRACT FROM AUTHOR]

Regression algorithms are regularly used for improving the accuracy of satellite precipitation products. In this context, satellite precipitation and topography data are the predictor variables, and gauged-measured precipitation data are the dependent variables. Alongside this, it is increasingly recognised in many fields that combinations of algorithms through ensemble learning can lead to substantial predictive performance improvements. Still, a sufficient number of ensemble learners for improving the accuracy of satellite precipitation products and their large-scale comparison are currently missing from the literature. In this study, we work towards filling in this specific gap by proposing 11 new ensemble learners in the field and by extensively comparing them. We apply the ensemble learners to monthly data from the PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks) and IMERG (Integrated Multi-satellitE Retrievals for GPM) gridded datasets that span over a 15-year period and over the entire contiguous United States (CONUS). We also use gauge-measured precipitation data from the Global Historical Climatology Network monthly database, version 2 (GHCNm). The ensemble learners combine the predictions of six machine learning regression algorithms (base learners), namely the multivariate adaptive regression splines (MARS), multivariate adaptive polynomial splines (poly-MARS), random forests (RF), gradient boosting machines (GBM), extreme gradient boosting (XGBoost) and Bayesian regularized neural networks (BRNN), and each of them is based on a different combiner. The combiners include the equal-weight combiner, the median combiner, two best learners and seven variants of a sophisticated stacking method. The latter stacks a regression algorithm on top of the base learners to combine their independent predictions. Its seven variants are defined by seven different regression algorithms, specifically the linear regression (LR) algorithm and the six algorithms also used as base learners. The results suggest that sophisticated stacking performs significantly better than the base learners, especially when applied using the LR algorithm. It also beats the simpler combination methods. [ABSTRACT FROM AUTHOR]

There is a critical need for a global monitoring capability for Tailings Storage Facilities (TSFs), to help protect the surrounding communities and the environment. Satellite Synthetic Aperture Radar Interferometry (InSAR) shows much promise towards this ambition. However, extracting meaningful information and interpreting the deformation patterns from InSAR data can be a challenging task. One approach to address this challenge is through the use of data science techniques. In this study, the representation of InSAR metadata as Entity Embeddings within a Deep Learning framework (EE-DL) is investigated for modelling the spatio-temporal deformation response. Entity embeddings are commonly used in natural-language-processing tasks. They represent discrete objects, such as words, as continuous, low-dimensional vectors that can be manipulated mathematically. We demonstrate that EE-DL can be used to predict anomalous patterns in the InSAR time series. To evaluate the performance of the EE-DL approach in SAR interferometry, we conducted experiments over a mining test site (Cadia, Australia), which has been subject to a TSF failure. This study demonstrated that EE-DL can detect and predict the fine spatial movement patterns that eventually resulted in the failure. We also compared the results with deformation predictions from common baseline models, the Random Forest model and Gaussian Process Regression (GPR). Both EE-DL and GPR greatly outperform Random Forest. While GPR is also able to predict displacement patterns with millimetric accuracy, it detects a significantly lower number of anomalies compared to EE-DL. Overall, our study showed that EE-DL is a promising approach for building early-warning systems for critical infrastructures that use InSAR to predict ground deformations. [ABSTRACT FROM AUTHOR]

Weeds have a significant impact on the growth of rice. Accurate information about weed infestations can provide farmers with important information to facilitate the precise use of chemicals. In this study, we utilized visible light images captured by UAVs to extract information about weeds in areas of two densities on farmland. First, the UAV images were segmented using an optimal segmentation scale, and the spectral, texture, index, and geometric features of each segmented object were extracted. Cross-validation and recursive feature elimination techniques were combined to reduce the dimensionality of all features to obtain a better feature set. Finally, we analyzed the extraction effect of different feature dimensions based on the random forest (RF) algorithm to determine the best feature dimensions, and then we further analyzed the classification result of machine learning algorithms, such as random forest, support vector machine (SVM), decision tree (DT), and K-nearest neighbors (KNN) and compared them based on the best feature dimensions. Using the extraction results of the best classifier, we created a zoning map of the weed infestations in the study area. The results indicated that the best feature subset achieved the highest accuracy, with respective overall accuracies of 95.38% and 91.33% for areas with dense and sparse weed densities, respectively, and F1-scores of 94.20% and 90.57. Random forest provided the best extraction results for each machine learning algorithm in the two experimental areas. When compared to the other algorithms, it improved the overall accuracy by 1.74–12.14% and 7.51–11.56% for areas with dense and sparse weed densities, respectively. The F1-score improved by 1.89–17.40% and 7.85–10.80%. Therefore, the combination of object-based image analysis (OBIA) and random forest based on UAV remote sensing accurately extracted information about weeds in areas with different weed densities for farmland, providing effective information support for weed management. [ABSTRACT FROM AUTHOR]

Salt pans are unique wetland ecosystems. In the Austrian Seewinkel region, salt pans are in an increasingly vulnerable state due to groundwater drainage and heightened climatic pressures. It is crucial to model how seasonal and long-term hydrological and climatological variations affect the salt pan dynamics in Seewinkel, yet a comprehensive understanding of the driving processes is lacking. The goal of this study is to develop random forest machine learning models driven by hydrological and meteorological data that allow us to predict in early spring (March) of each year the inundation state in the subsequent summer and fall. We utilize Earth observation data from Landsat 5 (L5), 8 (L8), and 9 (L9) to derive the time series of the inundation state for 34 salt pans for the period 1984–2022. Furthermore, we demonstrate that the groundwater level observed in March is the strongest predictor of the salt pan inundation state in summer and fall. Utilizing local groundwater data yields a Matthews correlation coefficient of 0.59. Models using globally available meteorological data, either instead of or in addition to groundwater data, provide comparable results. This allows the global transfer of the approach to comparable ecosystems where no in situ data are available. [ABSTRACT FROM AUTHOR]

With growing global concern for food and water insecurity, an efficient method to monitor irrigation projects is essential, especially in the developing world where irrigation performance is often suboptimal. In Nepal, the irrigated area has not been objectively recorded, although their assessment has substantial implications for national policy, project's annual budgets, and donor funding. Here, we present the application of Landsat images to measure irrigated areas in Nepal for the past 17 years to contribute to the assessment of the irrigation performance. Landsat 5 TM (2006–2011) and Landsat 8 OLI (2013–2022) images were used to develop a machine learning model, which classifies irrigated and non-irrigated areas in the study areas. The random forest classification achieved an overall accuracy of 82.2% and kappa statistics of 0.72. For the class of irrigation areas, the producer's accuracy and consumer's accuracy were 79% and 96%, respectively. Our regionally trained machine learning model outperforms the existing global cropland map, highlighting the need for such models for local irrigation project evaluations. We assess irrigation project performance and its drivers by combining long-term changes in satellite-derived irrigated areas with local data related to irrigation performance, such as annual budget, irrigation service fee, crop yield, precipitation, and main canal discharge. [ABSTRACT FROM AUTHOR]