Search

Mangrove ecosystems play an irreplaceable role in coastal environments by providing essential ecosystem services. Diverse mangrove species have different functions due to their morphological and physiological characteristics. A precise spatial distribution map of mangrove species is therefore crucial for biodiversity maintenance and environmental conservation of coastal ecosystems. Traditional satellite data are limited in fine-scale mangrove species classification due to low spatial resolution and less spectral information. This study employed unmanned aerial vehicle (UAV) technology to acquire high-resolution multispectral and hyperspectral mangrove forest imagery in Guangxi, China. We leveraged advanced algorithms, including RFE-RF for feature selection and machine learning models (Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Light Gradient Boosting Machine (LightGBM)), to achieve mangrove species mapping with high classification accuracy. The study assessed the classification performance of these four machine learning models for two types of image data (UAV multispectral and hyperspectral imagery), respectively. The results demonstrated that hyperspectral imagery had superiority over multispectral data by offering enhanced noise reduction and classification performance. Hyperspectral imagery produced mangrove species classification with overall accuracy (OA) higher than 91% across the four machine learning models. LightGBM achieved the highest OA of 97.15% and kappa coefficient (Kappa) of 0.97 based on hyperspectral imagery. Dimensionality reduction and feature extraction techniques were effectively applied to the UAV data, with vegetation indices proving to be particularly valuable for species classification. The present research underscored the effectiveness of UAV hyperspectral images using machine learning models for fine-scale mangrove species classification. This approach has the potential to significantly improve ecological management and conservation strategies, providing a robust framework for monitoring and safeguarding these essential coastal habitats. [ABSTRACT FROM AUTHOR]

Salinization is a major soil degradation process threatening ecosystems and posing a great challenge to sustainable agriculture and food security worldwide. This study aimed to evaluate the potential of state-of-the-art machine learning algorithms in soil salinity (EC1:5) mapping. Further, we predicted the distribution patterns of soil salinity under different future scenarios in the Yellow River Delta. A geodatabase comprising 201 soil samples and 19 conditioning factors (containing data based on remote sensing images such as Landsat, SPOT/VEGETATION PROBA-V, SRTMDEMUTM, Sentinel-1, and Sentinel-2) was used to compare the predictive performance of empirical bayesian kriging regression, random forest, and CatBoost models. The CatBoost model exhibited the highest performance with both training and testing datasets, with an average MAE of 1.86, an average RMSE of 3.11, and an average R2 of 0.59 in the testing datasets. Among explanatory factors, soil Na was the most important for predicting EC1:5, followed by the normalized difference vegetation index and soil organic carbon. Soil EC1:5 predictions suggested that the Yellow River Delta region faces severe salinization, particularly in coastal zones. Among three scenarios with increases in soil organic carbon content (1, 2, and 3 g/kg), the 2 g/kg scenario resulted in the best improvement effect on saline–alkali soils with EC1:5 > 2 ds/m. Our results provide valuable insights for policymakers to improve saline–alkali land quality and plan regional agricultural development. [ABSTRACT FROM AUTHOR]

Mangrove ecosystems play an irreplaceable role in coastal environments by providing essential ecosystem services. Diverse mangrove species have different functions due to their morphological and physiological characteristics. A precise spatial distribution map of mangrove species is therefore crucial for biodiversity maintenance and environmental conservation of coastal ecosystems. Traditional satellite data are limited in fine-scale mangrove species classification due to low spatial resolution and less spectral information. This study employed unmanned aerial vehicle (UAV) technology to acquire high-resolution multispectral and hyperspectral mangrove forest imagery in Guangxi, China. We leveraged advanced algorithms, including RFE-RF for feature selection and machine learning models (Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Light Gradient Boosting Machine (LightGBM)), to achieve mangrove species mapping with high classification accuracy. The study assessed the classification performance of these four machine learning models for two types of image data (UAV multispectral and hyperspectral imagery), respectively. The results demonstrated that hyperspectral imagery had superiority over multispectral data by offering enhanced noise reduction and classification performance. Hyperspectral imagery produced mangrove species classification with overall accuracy (OA) higher than 91% across the four machine learning models. LightGBM achieved the highest OA of 97.15% and kappa coefficient (Kappa) of 0.97 based on hyperspectral imagery. Dimensionality reduction and feature extraction techniques were effectively applied to the UAV data, with vegetation indices proving to be particularly valuable for species classification. The present research underscored the effectiveness of UAV hyperspectral images using machine learning models for fine-scale mangrove species classification. This approach has the potential to significantly improve ecological management and conservation strategies, providing a robust framework for monitoring and safeguarding these essential coastal habitats.

Salinization is a major soil degradation process threatening ecosystems and posing a great challenge to sustainable agriculture and food security worldwide. This study aimed to evaluate the potential of state-of-the-art machine learning algorithms in soil salinity (EC1:5) mapping. Further, we predicted the distribution patterns of soil salinity under different future scenarios in the Yellow River Delta. A geodatabase comprising 201 soil samples and 19 conditioning factors (containing data based on remote sensing images such as Landsat, SPOT/VEGETATION PROBA-V, SRTMDEMUTM, Sentinel-1, and Sentinel-2) was used to compare the predictive performance of empirical bayesian kriging regression, random forest, and CatBoost models. The CatBoost model exhibited the highest performance with both training and testing datasets, with an average MAE of 1.86, an average RMSE of 3.11, and an average R2 of 0.59 in the testing datasets. Among explanatory factors, soil Na was the most important for predicting EC1:5, followed by the normalized difference vegetation index and soil organic carbon. Soil EC1:5 predictions suggested that the Yellow River Delta region faces severe salinization, particularly in coastal zones. Among three scenarios with increases in soil organic carbon content (1, 2, and 3 g/kg), the 2 g/kg scenario resulted in the best improvement effect on saline–alkali soils with EC1:5 > 2 ds/m. Our results provide valuable insights for policymakers to improve saline–alkali land quality and plan regional agricultural development.

Lightning Electromagnetic Pulses, or LEMPs, propagate in the Earth–ionosphere waveguide and can be detected remotely by ground-based lightning electric field sensors. LEMPs produced by different types of lightning processes have different signatures. A single thunderstorm can produce thousands of LEMPs, which makes their classification virtually impossible to carry out manually. The lightning classification is important to distinguish the types of thunderstorms and to know their severity. Lightning type is also related to aerosol concentration and can reveal wildfires. Artificial Intelligence (AI) is a good approach to recognizing patterns and dealing with huge datasets. AI is the general denomination for different Machine Learning Algorithms (MLAs) including deep learning and others. The constant improvements in the AI field show us that most of the Lightning Location Systems (LLS) will soon incorporate those techniques to improve their performance in the lightning-type classification task. In this study, we assess the performance of different MLAs, including a SVM (Support Vector Machine), MLP (Multi-Layer Perceptron), FCN (Fully Convolutional Network), and Residual Neural Network (ResNet) in the task of LEMP classification. We also address different aspects of the dataset that can interfere with the classification problem, including data balance, noise level, and LEMP recorded length. [ABSTRACT FROM AUTHOR]

Mangrove forests, mostly found in the intertidal zone, are among the highest-productivity ecosystems and have great ecological and economic value. The accurate mapping of mangrove forests is essential for the scientific management and restoration of mangrove ecosystems. However, it is still challenging to perform the rapid and accurate information mapping of mangrove forests due to the complexity of mangrove forests themselves and their environments. Utilizing multi-source remote sensing data is an effective approach to address this challenge. Feature extraction and selection, as well as the selection of classification models, are crucial for accurate mangrove mapping using multi-source remote sensing data. This study constructs multi-source feature sets based on optical (Sentinel-2) and SAR (synthetic aperture radar) (C-band: Sentinel-1; L-band: ALOS-2) remote sensing data, aiming to compare the impact of three feature selection methods (RFS, random forest; ERT, extremely randomized tree; MIC, maximal information coefficient) and four machine learning algorithms (DT, decision tree; RF, random forest; XGBoost, extreme gradient boosting; LightGBM, light gradient-boosting machine) on classification accuracy, identify sensitive feature variables that contribute to mangrove mapping, and formulate a classification framework for accurately recognizing mangrove forests. The experimental results demonstrated that using the feature combination selected via the ERT method could obtain higher accuracy with fewer features compared to other methods. Among the feature combinations, the visible bands, shortwave infrared bands, and the vegetation indices constructed from these bands contributed the greatest to the classification accuracy. The classification performance of optical data was significantly better than SAR data in terms of data sources. The combination of optical and SAR data could improve the accuracy of mangrove mapping to a certain extent (0.33% to 4.67%), which is essential for the research of mangrove mapping in a larger area. The XGBoost classification model performed optimally in mangrove mapping, with the highest overall accuracy of 95.00% among all the classification models. The results of the study show that combining optical and SAR remote sensing data with the ERT feature selection method and XGBoost classification model has great potential for accurate mangrove mapping at a regional scale, which is important for mangrove restoration and protection and provides a reliable database for mangrove scientific management. [ABSTRACT FROM AUTHOR]

Remote sensing has emerged as a promising tool for monitoring water quality (WQ) in aquatic ecosystems. This study evaluates the effectiveness of remote sensing in assessing WQ parameters in Cajititlán and Zapotlán lakes in the state of Jalisco, Mexico. Over time, these lakes have witnessed a significant decline in WQ, necessitating the adoption of advanced monitoring techniques. In this research, satellite-based remote sensing data were combined with ground-based measurements from the National Water Quality Monitoring Network of Mexico (RNMCA). These data sources were harnessed to train and evaluate the performance of six distinct categories of machine learning (ML) algorithms aimed at estimating WQ parameters with active spectral signals, including chlorophyll-a (Chl-a), turbidity, and total suspended solids (TSS). Various limitations were encountered during the study, primarily due to atmospheric conditions and cloud cover. These challenges affected both the quality and quantity of the data. However, these limitations were overcome through rigorous data preprocessing, the application of ML techniques designed for data-scarce scenarios, and extensive hyperparameter tuning. The superlearner algorithm (SLA), which leverages a combination of individual algorithms, and the multilayer perceptron (MLP), capable of handling complex and non-linear problems, outperformed others in terms of predictive accuracy. Notably, in Lake Cajititlán, these models provided the most accurate predictions for turbidity (r2 = 0.82, RMSE = 9.93 NTU, MAE = 7.69 NTU), Chl-a (r2 = 0.60, RMSE = 48.06 mg/m3, MAE = 37.98 mg/m3), and TSS (r2 = 0.68, RMSE = 13.42 mg/L, MAE = 10.36 mg/L) when using radiometric data from Landsat-8. In Lake Zapotlán, better predictive performance was observed for turbidity (r2 = 0.75, RMSE = 2.05 NTU, MAE = 1.10 NTU) and Chl-a (r2 = 0.71, RMSE = 6.16 mg/m3, MAE = 4.97 mg/m3) with Landsat-8 radiometric data, while TSS (r2 = 0.72, RMSE = 2.71 mg/L, MAE = 2.12 mg/L) improved when Sentinel-2 data were employed. While r2 values indicate that the models do not exhibit a perfect fit, those approaching unity suggest that the predictor variables offer valuable insights into the corresponding responses. Moreover, the model's robustness could be enhanced by increasing the quantity and quality of input variables. Consequently, remote sensing emerges as a valuable tool to support the objectives of WQ monitoring systems. [ABSTRACT FROM AUTHOR]

It is important to improve the accuracy of models estimating aboveground biomass (AGB) in large areas with complex geography and high forest heterogeneity. In this study, k-nearest neighbors (k-NN), gradient boosting machine (GBM), random forest (RF), quantile random forest (QRF), regularized random forest (RRF), and Bayesian regularization neural network (BRNN) machine learning algorithms were constructed to estimate the AGB of four forest types based on environmental factors and the variables selected by the Boruta algorithm in Yunnan Province and using integrated Landsat 8 OLI and Sentinel 2A images. The results showed that (1) DEM was the most important variable for estimating the AGB of coniferous forests, evergreen broadleaved forests, deciduous broadleaved forests, and mixed forests; while the vegetation index was the most important variable for estimating deciduous broadleaved forests, the climatic factors had a higher variable importance for estimating coniferous and mixed forests, and texture features and vegetation index had a higher variable importance for estimating evergreen broadleaved forests. (2) In terms of specific model performance for the four forest types, RRF was the best model both in estimating the AGB of coniferous forests and mixed forests; the R2 and RMSE for coniferous forests were 0.63 and 43.23 Mg ha−1, respectively, and the R2 and RMSE for mixed forests were 0.56 and 47.79 Mg ha−1, respectively. BRNN performed the best in estimating the AGB of evergreen broadleaved forests; the R2 was 0.53 and the RMSE was 68.16 Mg ha−1. QRF was the best in estimating the AGB of deciduous broadleaved forests, with R2 of 0.43 and RMSE of 45.09 Mg ha−1. (3) RRF was the best model for the four forest types according to the mean values, with R2 and RMSE of 0.503 and 52.335 Mg ha−1, respectively. In conclusion, different variables and suitable models should be considered when estimating the AGB of different forest types. This study could provide a reference for the estimation of forest AGB based on remote sensing in complex terrain areas with a high degree of forest heterogeneity. [ABSTRACT FROM AUTHOR]

Soil moisture is a key factor in the water and heat exchange and energy transformation of the ecological systems and is of critical importance to the accurate obtainment of the soil moisture content for supervising water resources and protecting regional and global eco environments. In this study, we selected the soil moisture monitoring networks of Naqu, Maqu, and Tianjun on the Qinghai–Tibetan Plateau as the research areas, and we established a database of surface microwave scattering with the AIEM (advanced integral equation model) and the mathematical expressions for the backscattering coefficient, soil moisture, and surface roughness of the VV and VH polarizations.We proposed the soil moisture retrieval models of empirical and machine learnings algorithms (backpropagation neural network (BPNN), support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF)) for the ascending and descending orbits using Sentinel-1 and measurement data, and we also validated the accuracies of the retrieval model in the research areas. According to the results, there is a substantial logarithmic correlation among the backscattering coefficient, soil moisture, and combined roughness. Generally, we can use empirical models to estimate the soil moisture content, with an R² of 0.609, RMSE of 0.08, and MAE of 0.064 for the ascending orbit model and an R² of 0.554, RMSE of 0.086, and MAE of 0.071 for the descending orbit model. The soil moisture contents are underestimated when the volumetric water content is high. The soil moisture retrieval accuracy is improved with machine learning algorithms compared to the empirical model, and the performance of the RF algorithm is superior to those of the other machine learning algorithms. The RF algorithm also achieved satisfactory performances for the Maqu and Tianjun networks. The accuracies of the inversion models for the ascending orbit in the three soil moisture monitoring networks were better than those for the descending orbit. [ABSTRACT FROM AUTHOR]

Lightning Electromagnetic Pulses, or LEMPs, propagate in the Earth–ionosphere waveguide and can be detected remotely by ground-based lightning electric field sensors. LEMPs produced by different types of lightning processes have different signatures. A single thunderstorm can produce thousands of LEMPs, which makes their classification virtually impossible to carry out manually. The lightning classification is important to distinguish the types of thunderstorms and to know their severity. Lightning type is also related to aerosol concentration and can reveal wildfires. Artificial Intelligence (AI) is a good approach to recognizing patterns and dealing with huge datasets. AI is the general denomination for different Machine Learning Algorithms (MLAs) including deep learning and others. The constant improvements in the AI field show us that most of the Lightning Location Systems (LLS) will soon incorporate those techniques to improve their performance in the lightning-type classification task. In this study, we assess the performance of different MLAs, including a SVM (Support Vector Machine), MLP (Multi-Layer Perceptron), FCN (Fully Convolutional Network), and Residual Neural Network (ResNet) in the task of LEMP classification. We also address different aspects of the dataset that can interfere with the classification problem, including data balance, noise level, and LEMP recorded length.

Mangrove forests, mostly found in the intertidal zone, are among the highest-productivity ecosystems and have great ecological and economic value. The accurate mapping of mangrove forests is essential for the scientific management and restoration of mangrove ecosystems. However, it is still challenging to perform the rapid and accurate information mapping of mangrove forests due to the complexity of mangrove forests themselves and their environments. Utilizing multi-source remote sensing data is an effective approach to address this challenge. Feature extraction and selection, as well as the selection of classification models, are crucial for accurate mangrove mapping using multi-source remote sensing data. This study constructs multi-source feature sets based on optical (Sentinel-2) and SAR (synthetic aperture radar) (C-band: Sentinel-1; L-band: ALOS-2) remote sensing data, aiming to compare the impact of three feature selection methods (RFS, random forest; ERT, extremely randomized tree; MIC, maximal information coefficient) and four machine learning algorithms (DT, decision tree; RF, random forest; XGBoost, extreme gradient boosting; LightGBM, light gradient-boosting machine) on classification accuracy, identify sensitive feature variables that contribute to mangrove mapping, and formulate a classification framework for accurately recognizing mangrove forests. The experimental results demonstrated that using the feature combination selected via the ERT method could obtain higher accuracy with fewer features compared to other methods. Among the feature combinations, the visible bands, shortwave infrared bands, and the vegetation indices constructed from these bands contributed the greatest to the classification accuracy. The classification performance of optical data was significantly better than SAR data in terms of data sources. The combination of optical and SAR data could improve the accuracy of mangrove mapping to a certain extent (0.33% to 4.67%), which is essential for the research of mangrove mapping in a larger area. The XGBoost classification model performed optimally in mangrove mapping, with the highest overall accuracy of 95.00% among all the classification models. The results of the study show that combining optical and SAR remote sensing data with the ERT feature selection method and XGBoost classification model has great potential for accurate mangrove mapping at a regional scale, which is important for mangrove restoration and protection and provides a reliable database for mangrove scientific management.

Remote sensing has emerged as a promising tool for monitoring water quality (WQ) in aquatic ecosystems. This study evaluates the effectiveness of remote sensing in assessing WQ parameters in Cajititlán and Zapotlán lakes in the state of Jalisco, Mexico. Over time, these lakes have witnessed a significant decline in WQ, necessitating the adoption of advanced monitoring techniques. In this research, satellite-based remote sensing data were combined with ground-based measurements from the National Water Quality Monitoring Network of Mexico (RNMCA). These data sources were harnessed to train and evaluate the performance of six distinct categories of machine learning (ML) algorithms aimed at estimating WQ parameters with active spectral signals, including chlorophyll-a (Chl-a), turbidity, and total suspended solids (TSS). Various limitations were encountered during the study, primarily due to atmospheric conditions and cloud cover. These challenges affected both the quality and quantity of the data. However, these limitations were overcome through rigorous data preprocessing, the application of ML techniques designed for data-scarce scenarios, and extensive hyperparameter tuning. The superlearner algorithm (SLA), which leverages a combination of individual algorithms, and the multilayer perceptron (MLP), capable of handling complex and non-linear problems, outperformed others in terms of predictive accuracy. Notably, in Lake Cajititlán, these models provided the most accurate predictions for turbidity (r2 = 0.82, RMSE = 9.93 NTU, MAE = 7.69 NTU), Chl-a (r2 = 0.60, RMSE = 48.06 mg/m3, MAE = 37.98 mg/m3), and TSS (r2 = 0.68, RMSE = 13.42 mg/L, MAE = 10.36 mg/L) when using radiometric data from Landsat-8. In Lake Zapotlán, better predictive performance was observed for turbidity (r2 = 0.75, RMSE = 2.05 NTU, MAE = 1.10 NTU) and Chl-a (r2 = 0.71, RMSE = 6.16 mg/m3, MAE = 4.97 mg/m3) with Landsat-8 radiometric data, while TSS (r2 = 0.72, RMSE = 2.71 mg/L, MAE = 2.12 mg/L) improved when Sentinel-2 data were employed. While r2 values indicate that the models do not exhibit a perfect fit, those approaching unity suggest that the predictor variables offer valuable insights into the corresponding responses. Moreover, the model’s robustness could be enhanced by increasing the quantity and quality of input variables. Consequently, remote sensing emerges as a valuable tool to support the objectives of WQ monitoring systems.

In this era of free and open-access satellite and spatial data, modern innovations in cloud computing and machine-learning algorithms (MLAs) are transforming how Earth-observation (EO) datasets are utilized for geological mapping. This study aims to exploit the potentialities of the Google Earth Engine (GEE) cloud platform using powerful MLAs. The proposed method is implemented in three steps: (1) Based on GEE and Sentinel 2A imagery (spectral and textural features), that cover 1283 km2 area, a variety of lithological maps are generated using five supervised classifiers (random forest (RF), support vector machine (SVM), classification and regression tree (CART), minimum distance (MD), naïve Bayes (NB)); (2) the accuracy assessments for each class are performed, by estimating overall accuracy (OA) and kappa coefficient (K) for each classifier; (3) finally, the fusion of classification maps is performed using Dempster–Shafer Theory (DST) for mapping lithological units of the northern part of the complex Paleozoic massif of Rehamna, a large semi-arid region located in the SW of the western Moroccan Meseta. The results were quantitatively compared with existing geological maps, enhanced color composite and validated by field survey investigation. In comparison of individual classifiers, the SVM yields better accuracy of nearly 88%, which was 12% higher than the RF MLA; otherwise, the parametric MLAs produce the weakest lithological maps among other classifiers, with a lower OA of approximately 67%, 54% and 52% for CART, MD and NB, respectively. Noticeably, the highest OA value of 96% is achieved for the proposed approach. Therefore, we conclude that this method allows geoscientists to update previous geological maps and rapidly produce more precise lithological maps, especially for hard-to-reach regions. [ABSTRACT FROM AUTHOR]

It is important to improve the accuracy of models estimating aboveground biomass (AGB) in large areas with complex geography and high forest heterogeneity. In this study, k-nearest neighbors (k-NN), gradient boosting machine (GBM), random forest (RF), quantile random forest (QRF), regularized random forest (RRF), and Bayesian regularization neural network (BRNN) machine learning algorithms were constructed to estimate the AGB of four forest types based on environmental factors and the variables selected by the Boruta algorithm in Yunnan Province and using integrated Landsat 8 OLI and Sentinel 2A images. The results showed that (1) DEM was the most important variable for estimating the AGB of coniferous forests, evergreen broadleaved forests, deciduous broadleaved forests, and mixed forests; while the vegetation index was the most important variable for estimating deciduous broadleaved forests, the climatic factors had a higher variable importance for estimating coniferous and mixed forests, and texture features and vegetation index had a higher variable importance for estimating evergreen broadleaved forests. (2) In terms of specific model performance for the four forest types, RRF was the best model both in estimating the AGB of coniferous forests and mixed forests; the R2 and RMSE for coniferous forests were 0.63 and 43.23 Mg ha−1, respectively, and the R2 and RMSE for mixed forests were 0.56 and 47.79 Mg ha−1, respectively. BRNN performed the best in estimating the AGB of evergreen broadleaved forests; the R2 was 0.53 and the RMSE was 68.16 Mg ha−1. QRF was the best in estimating the AGB of deciduous broadleaved forests, with R2 of 0.43 and RMSE of 45.09 Mg ha−1. (3) RRF was the best model for the four forest types according to the mean values, with R2 and RMSE of 0.503 and 52.335 Mg ha−1, respectively. In conclusion, different variables and suitable models should be considered when estimating the AGB of different forest types. This study could provide a reference for the estimation of forest AGB based on remote sensing in complex terrain areas with a high degree of forest heterogeneity.

Flooding is one of the catastrophic natural hazards worldwide that can easily cause devastating effects on human life and property. Remote sensing devices are becoming increasingly important in monitoring and assessing natural disaster susceptibility and hazards. The proposed research work pursues an assessment analysis of flood susceptibility in a tropical desert environment: a case study of Yemen. The base data for this research were collected and organized from meteorological, satellite images, remote sensing data, essential geographic data, and various data sources and used as input data into four machine learning (ML) algorithms. In this study, RS data (Sentinel-1 images) were used to detect flooded areas in the study area. We also used the Sentinel application platform (SNAP 7.0) for Sentinel-1 image analysis and detecting flood zones in the study locations. Flood spots were discovered and verified using Google Earth images, Landsat images, and press sources to create a flood inventory map of flooded areas in the study area. Four ML algorithms were used to map flash flood susceptibility (FFS) in Tarim city (Yemen): K-nearest neighbor (KNN), Naïve Bayes (NB), random forests (RF), and eXtreme gradient boosting (XGBoost). Twelve flood conditioning factors were prepared, assessed in multicollinearity, and used with flood inventories as input parameters to run each model. A total of 600 random flood and non-flood points were chosen, where 75% and 25% were used as training and validation datasets. The confusion matrix and the area under the receiver operating characteristic curve (AUROC) were used to validate the susceptibility maps. The results obtained reveal that all models had a high capacity to predict floods (AUC > 0.90). Further, in terms of performance, the tree-based ensemble algorithms (RF, XGBoost) outperform other ML algorithms, where the RF algorithm provides robust performance (AUC = 0.982) for assessing flood-prone areas with only a few adjustments required prior to training the model. The value of the research lies in the fact that the proposed models are being tested for the first time in Yemen to assess flood susceptibility, which can also be used to assess, for example, earthquakes, landslides, and other disasters. Furthermore, this work makes significant contributions to the worldwide effort to reduce the risk of natural disasters, particularly in Yemen. This will, therefore, help to enhance environmental sustainability. [ABSTRACT FROM AUTHOR]

This paper presented a review on the capabilities of machine learning algorithms toward Earth observation data modelling and information extraction. The main purpose was to identify new trends in the application of or research on machine learning and Earth observation—as well as to help researchers positioning new development in these domains, considering the latest peer-reviewed articles. A review of Earth observation concepts was presented, as well as current approaches and available data, followed by different machine learning applications and algorithms. Special attention was given to the contribution, potential and capabilities of Earth observation-machine learning approaches. The findings suggested that the combination of Earth observation and machine learning was successfully applied in several different fields across the world. Additionally, it was observed that all machine learning categories could be used to analyse Earth observation data or to improve acquisition processes and that RF, SVM, K-Means, NN (CNN and GAN) and A2C were among the most-used techniques. In conclusion, the combination of these technologies could prove to be crucial in a wide range of fields (e.g., agriculture, climate and biology) and should be further explored for each specific domain. [ABSTRACT FROM AUTHOR]

Although satellite remote sensing technology is intensively used for the monitoring of water quality, the inversion of coastal water bodies and non-optically active parameters is still a challenging issue. Few ongoing studies use remote sensing technology to analyze the driving forces of changes in water quality from multiple aspects based on inversion results. By the use of Landsat 5/8 imagery and measured in situ data of the total nitrogen (TN) and total phosphorus (TP) in the Shenzhen-Hong Kong Bay area from 1986 to 2020, this study evaluated the modeling effects of four machine learning methods named Tree Embedding (TE), Support Vector Regression (SVR), Gaussian Process Regression (GPR), and Back-propagation Neural Network (BPNN). The results show that the BPNN creates the most reliable and robust results. The values of the obtained correlation coefficients (r) are 0.83, 0.92, 0.84, and 0.90, and that of the coefficients of determination (R2) are 0.70, 0.84, 0.70, and 0.81. The calculated mean absolute errors (MAEs) are 0.41, 0.16, 0.06, and 0.02, while the root mean square errors (RMSEs) are 0.78, 0.29, 0.12, and 0.03. The concentrations of TN and TP (CTN, CTP) in the Shenzhen Bay, the Starling Inlet, and the Tolo Harbor were relatively high, fluctuated from 1986 to 2010, and decreased significantly after 2010. The CTN and CTP in the Mirs Bay kept continuously at a low level. We found that urbanization and polluted river discharges were the main drivers of spatial and inter-annual differences of CTN and CTP. Temperature, precipitation, and wind are further factors that influenced the intra-annual changes of CTN and CTP in the Shenzhen Bay, whilethe expansion of oyster rafts and mangroves had little effect. Our research confirms that machine learning algorithms are well suited for the inversion of non-optical activity parameters of coastal water bodies, and also shows the potential of remote sensing for large-scale, long-term monitoring of water quality and the subsequent comprehensive analysis of the driving forces. [ABSTRACT FROM AUTHOR]

Groundwater pollution poses a severe threat and issue to the environment and humanity overall. That is why mitigative strategies are urgently needed. Today, studies mapping groundwater risk pollution assessment are being developed. In this study, five new hybrid/ensemble machine learning (ML) models are developed, named DRASTIC-Random Forest (RF), DRASTIC-Support Vector Machine (SVM), DRASTIC-Multilayer Perceptron (MLP), DRASTIC-RF-SVM, and DRASTIC-RF-MLP, for groundwater pollution assessment in the Saiss basin, in Morocco. The performances of these models are evaluated using the Receiver Operating Characteristic curve (ROC curve), precision, and accuracy. Based on the results of the ROC curve method, it is indicated that the use of hybrid/ensemble machine learning (ML) models improves the performance of the individual machine learning (ML) algorithms. In effect, the AUC value of the original DRASTIC is 0.51. Furthermore, both hybrid/ensemble models, DRASTIC-RF-MLP (AUC = 0.953) and DRASTIC-RF-SVM, (AUC = 0.901) achieve the best accuracy among the other models, followed by DRASTIC-RF (AUC = 0.852), DRASTIC-SVM (AUC = 0.802), and DRASTIC-MLP (AUC = 0.763). The results delineate areas vulnerable to pollution, which require urgent actions and strategies to improve the environmental and social qualities for the local population. [ABSTRACT FROM AUTHOR]

Highland Andean ecosystems sustain high levels of floral and faunal biodiversity in areas with diverse topography and provide varied ecosystem services, including the supply of water to cities and downstream agricultural valleys. Google (™) has developed a product specifically designed for mapping purposes (Earth Engine), which enables users to harness the computing power of a cloud-based solution in near-real time for land cover change mapping and monitoring. We explore the feasibility of using this platform for mapping land cover types in topographically complex terrain with highly mixed vegetation types (Nor Yauyos Cochas Landscape Reserve located in the central Andes of Peru) using classification machine learning (ML) algorithms in combination with different sets of remote sensing data. The algorithms were trained using 3601 sampling pixels of (a) normalized spectral bands between the visible and near infrared spectrum of the Landsat 8 OLI sensor for the 2018 period, (b) spectral indices of vegetation, soil, water, snow, burned areas and bare ground and (c) topographic-derived indices (elevation, slope and aspect). Six ML algorithms were tested, including CART, random forest, gradient tree boosting, minimum distance, naïve Bayes and support vector machine. The results reveal that ML algorithms produce accurate classifications when spectral bands are used in conjunction with topographic indices, resulting in better discrimination among classes with similar spectral signatures such as pajonal (tussock grass-dominated cover) and short grasses or rocky groups, and moraines, agricultural and forested areas. The model with the highest explanatory power was obtained from the combination of spectral bands and topographic indices using the random forest algorithm (Kappa = 0.81). Our study presents a first approach of its kind in topographically complex Cordilleran terrain and we show that GEE is particularly useful in large-scale land cover mapping and monitoring in mountainous ecosystems subject to rapid changes and conversions, with replicability and scalability to other areas with similar characteristics. [ABSTRACT FROM AUTHOR]

The red turpentine beetle (Dendroctonus valens LeConte) has caused severe ecological and economic losses since its invasion into China. It gradually spreads northeast, resulting in many Chinese pine (Pinus tabuliformis Carr.) deaths. Early detection of D. valens infestation (i.e., at the green attack stage) is the basis of control measures to prevent its outbreak and spread. This study examined the changes in spectral reflectance after initial attacking of D. valens. We also explored the possibility of detecting early D. valens infestation based on spectral vegetation indices and machine learning algorithms. The spectral reflectance of infested trees was significantly different from healthy trees (p < 0.05), and there was an obvious decrease in the near-infrared region (760–1386 nm; p < 0.01). Spectral vegetation indices were input into three machine learning classifiers; the classification accuracy was 72.5–80%, while the sensitivity was 65–85%. Several spectral vegetation indices (DID, CUR, TBSI, DDn2, D735, SR1, NSMI, RNIR•CRI550 and RVSI) were sensitive indicators for the early detection of D. valens damage. Our results demonstrate that remote sensing technology could be successfully applied to early detect D. valens infestation and clarify the sensitive spectral regions and vegetation indices, which has important implications for early detection based on unmanned airborne vehicle and satellite data. [ABSTRACT FROM AUTHOR]

Soil moisture is a key factor in the water and heat exchange and energy transformation of the ecological systems and is of critical importance to the accurate obtainment of the soil moisture content for supervising water resources and protecting regional and global eco environments. In this study, we selected the soil moisture monitoring networks of Naqu, Maqu, and Tianjun on the Qinghai–Tibetan Plateau as the research areas, and we established a database of surface microwave scattering with the AIEM (advanced integral equation model) and the mathematical expressions for the backscattering coefficient, soil moisture, and surface roughness of the VV and VH polarizations.We proposed the soil moisture retrieval models of empirical and machine learnings algorithms (backpropagation neural network (BPNN), support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF)) for the ascending and descending orbits using Sentinel-1 and measurement data, and we also validated the accuracies of the retrieval model in the research areas. According to the results, there is a substantial logarithmic correlation among the backscattering coefficient, soil moisture, and combined roughness. Generally, we can use empirical models to estimate the soil moisture content, with an R² of 0.609, RMSE of 0.08, and MAE of 0.064 for the ascending orbit model and an R² of 0.554, RMSE of 0.086, and MAE of 0.071 for the descending orbit model. The soil moisture contents are underestimated when the volumetric water content is high. The soil moisture retrieval accuracy is improved with machine learning algorithms compared to the empirical model, and the performance of the RF algorithm is superior to those of the other machine learning algorithms. The RF algorithm also achieved satisfactory performances for the Maqu and Tianjun networks. The accuracies of the inversion models for the ascending orbit in the three soil moisture monitoring networks were better than those for the descending orbit.

In this era of free and open-access satellite and spatial data, modern innovations in cloud computing and machine-learning algorithms (MLAs) are transforming how Earth-observation (EO) datasets are utilized for geological mapping. This study aims to exploit the potentialities of the Google Earth Engine (GEE) cloud platform using powerful MLAs. The proposed method is implemented in three steps: (1) Based on GEE and Sentinel 2A imagery (spectral and textural features), that cover 1283 km2 area, a variety of lithological maps are generated using five supervised classifiers (random forest (RF), support vector machine (SVM), classification and regression tree (CART), minimum distance (MD), naïve Bayes (NB)); (2) the accuracy assessments for each class are performed, by estimating overall accuracy (OA) and kappa coefficient (K) for each classifier; (3) finally, the fusion of classification maps is performed using Dempster–Shafer Theory (DST) for mapping lithological units of the northern part of the complex Paleozoic massif of Rehamna, a large semi-arid region located in the SW of the western Moroccan Meseta. The results were quantitatively compared with existing geological maps, enhanced color composite and validated by field survey investigation. In comparison of individual classifiers, the SVM yields better accuracy of nearly 88%, which was 12% higher than the RF MLA; otherwise, the parametric MLAs produce the weakest lithological maps among other classifiers, with a lower OA of approximately 67%, 54% and 52% for CART, MD and NB, respectively. Noticeably, the highest OA value of 96% is achieved for the proposed approach. Therefore, we conclude that this method allows geoscientists to update previous geological maps and rapidly produce more precise lithological maps, especially for hard-to-reach regions.

Although satellite remote sensing technology is intensively used for the monitoring of water quality, the inversion of coastal water bodies and non-optically active parameters is still a challenging issue. Few ongoing studies use remote sensing technology to analyze the driving forces of changes in water quality from multiple aspects based on inversion results. By the use of Landsat 5/8 imagery and measured in situ data of the total nitrogen (TN) and total phosphorus (TP) in the Shenzhen-Hong Kong Bay area from 1986 to 2020, this study evaluated the modeling effects of four machine learning methods named Tree Embedding (TE), Support Vector Regression (SVR), Gaussian Process Regression (GPR), and Back-propagation Neural Network (BPNN). The results show that the BPNN creates the most reliable and robust results. The values of the obtained correlation coefficients (r) are 0.83, 0.92, 0.84, and 0.90, and that of the coefficients of determination (R2) are 0.70, 0.84, 0.70, and 0.81. The calculated mean absolute errors (MAEs) are 0.41, 0.16, 0.06, and 0.02, while the root mean square errors (RMSEs) are 0.78, 0.29, 0.12, and 0.03. The concentrations of TN and TP (CTN, CTP) in the Shenzhen Bay, the Starling Inlet, and the Tolo Harbor were relatively high, fluctuated from 1986 to 2010, and decreased significantly after 2010. The CTN and CTP in the Mirs Bay kept continuously at a low level. We found that urbanization and polluted river discharges were the main drivers of spatial and inter-annual differences of CTN and CTP. Temperature, precipitation, and wind are further factors that influenced the intra-annual changes of CTN and CTP in the Shenzhen Bay, whilethe expansion of oyster rafts and mangroves had little effect. Our research confirms that machine learning algorithms are well suited for the inversion of non-optical activity parameters of coastal water bodies, and also shows the potential of remote sensing for large-scale, long-term monitoring of water quality and the subsequent comprehensive analysis of the driving forces.

This paper presented a review on the capabilities of machine learning algorithms toward Earth observation data modelling and information extraction. The main purpose was to identify new trends in the application of or research on machine learning and Earth observation—as well as to help researchers positioning new development in these domains, considering the latest peer-reviewed articles. A review of Earth observation concepts was presented, as well as current approaches and available data, followed by different machine learning applications and algorithms. Special attention was given to the contribution, potential and capabilities of Earth observation-machine learning approaches. The findings suggested that the combination of Earth observation and machine learning was successfully applied in several different fields across the world. Additionally, it was observed that all machine learning categories could be used to analyse Earth observation data or to improve acquisition processes and that RF, SVM, K-Means, NN (CNN and GAN) and A2C were among the most-used techniques. In conclusion, the combination of these technologies could prove to be crucial in a wide range of fields (e.g., agriculture, climate and biology) and should be further explored for each specific domain.

Flooding is one of the catastrophic natural hazards worldwide that can easily cause devastating effects on human life and property. Remote sensing devices are becoming increasingly important in monitoring and assessing natural disaster susceptibility and hazards. The proposed research work pursues an assessment analysis of flood susceptibility in a tropical desert environment: a case study of Yemen. The base data for this research were collected and organized from meteorological, satellite images, remote sensing data, essential geographic data, and various data sources and used as input data into four machine learning (ML) algorithms. In this study, RS data (Sentinel-1 images) were used to detect flooded areas in the study area. We also used the Sentinel application platform (SNAP 7.0) for Sentinel-1 image analysis and detecting flood zones in the study locations. Flood spots were discovered and verified using Google Earth images, Landsat images, and press sources to create a flood inventory map of flooded areas in the study area. Four ML algorithms were used to map flash flood susceptibility (FFS) in Tarim city (Yemen): K-nearest neighbor (KNN), Naïve Bayes (NB), random forests (RF), and eXtreme gradient boosting (XGBoost). Twelve flood conditioning factors were prepared, assessed in multicollinearity, and used with flood inventories as input parameters to run each model. A total of 600 random flood and non-flood points were chosen, where 75% and 25% were used as training and validation datasets. The confusion matrix and the area under the receiver operating characteristic curve (AUROC) were used to validate the susceptibility maps. The results obtained reveal that all models had a high capacity to predict floods (AUC > 0.90). Further, in terms of performance, the tree-based ensemble algorithms (RF, XGBoost) outperform other ML algorithms, where the RF algorithm provides robust performance (AUC = 0.982) for assessing flood-prone areas with only a few adjustments required prior to training the model. The value of the research lies in the fact that the proposed models are being tested for the first time in Yemen to assess flood susceptibility, which can also be used to assess, for example, earthquakes, landslides, and other disasters. Furthermore, this work makes significant contributions to the worldwide effort to reduce the risk of natural disasters, particularly in Yemen. This will, therefore, help to enhance environmental sustainability.

Groundwater pollution poses a severe threat and issue to the environment and humanity overall. That is why mitigative strategies are urgently needed. Today, studies mapping groundwater risk pollution assessment are being developed. In this study, five new hybrid/ensemble machine learning (ML) models are developed, named DRASTIC-Random Forest (RF), DRASTIC-Support Vector Machine (SVM), DRASTIC-Multilayer Perceptron (MLP), DRASTIC-RF-SVM, and DRASTIC-RF-MLP, for groundwater pollution assessment in the Saiss basin, in Morocco. The performances of these models are evaluated using the Receiver Operating Characteristic curve (ROC curve), precision, and accuracy. Based on the results of the ROC curve method, it is indicated that the use of hybrid/ensemble machine learning (ML) models improves the performance of the individual machine learning (ML) algorithms. In effect, the AUC value of the original DRASTIC is 0.51. Furthermore, both hybrid/ensemble models, DRASTIC-RF-MLP (AUC = 0.953) and DRASTIC-RF-SVM, (AUC = 0.901) achieve the best accuracy among the other models, followed by DRASTIC-RF (AUC = 0.852), DRASTIC-SVM (AUC = 0.802), and DRASTIC-MLP (AUC = 0.763). The results delineate areas vulnerable to pollution, which require urgent actions and strategies to improve the environmental and social qualities for the local population.

The red turpentine beetle (Dendroctonus valens LeConte) has caused severe ecological and economic losses since its invasion into China. It gradually spreads northeast, resulting in many Chinese pine (Pinus tabuliformis Carr.) deaths. Early detection of D. valens infestation (i.e., at the green attack stage) is the basis of control measures to prevent its outbreak and spread. This study examined the changes in spectral reflectance after initial attacking of D. valens. We also explored the possibility of detecting early D. valens infestation based on spectral vegetation indices and machine learning algorithms. The spectral reflectance of infested trees was significantly different from healthy trees (p < 0.05), and there was an obvious decrease in the near-infrared region (760–1386 nm; p < 0.01). Spectral vegetation indices were input into three machine learning classifiers; the classification accuracy was 72.5–80%, while the sensitivity was 65–85%. Several spectral vegetation indices (DID, CUR, TBSI, DDn2, D735, SR1, NSMI, RNIR•CRI550 and RVSI) were sensitive indicators for the early detection of D. valens damage. Our results demonstrate that remote sensing technology could be successfully applied to early detect D. valens infestation and clarify the sensitive spectral regions and vegetation indices, which has important implications for early detection based on unmanned airborne vehicle and satellite data.

Highland Andean ecosystems sustain high levels of floral and faunal biodiversity in areas with diverse topography and provide varied ecosystem services, including the supply of water to cities and downstream agricultural valleys. Google (™) has developed a product specifically designed for mapping purposes (Earth Engine), which enables users to harness the computing power of a cloud-based solution in near-real time for land cover change mapping and monitoring. We explore the feasibility of using this platform for mapping land cover types in topographically complex terrain with highly mixed vegetation types (Nor Yauyos Cochas Landscape Reserve located in the central Andes of Peru) using classification machine learning (ML) algorithms in combination with different sets of remote sensing data. The algorithms were trained using 3601 sampling pixels of (a) normalized spectral bands between the visible and near infrared spectrum of the Landsat 8 OLI sensor for the 2018 period, (b) spectral indices of vegetation, soil, water, snow, burned areas and bare ground and (c) topographic-derived indices (elevation, slope and aspect). Six ML algorithms were tested, including CART, random forest, gradient tree boosting, minimum distance, naïve Bayes and support vector machine. The results reveal that ML algorithms produce accurate classifications when spectral bands are used in conjunction with topographic indices, resulting in better discrimination among classes with similar spectral signatures such as pajonal (tussock grass-dominated cover) and short grasses or rocky groups, and moraines, agricultural and forested areas. The model with the highest explanatory power was obtained from the combination of spectral bands and topographic indices using the random forest algorithm (Kappa = 0.81). Our study presents a first approach of its kind in topographically complex Cordilleran terrain and we show that GEE is particularly useful in large-scale land cover mapping and monitoring in mountainous ecosystems subject to rapid changes and conversions, with replicability and scalability to other areas with similar characteristics.

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.

Quantitatively mapping forest aboveground biomass (AGB) is of great significance for the study of terrestrial carbon storage and global carbon cycles, and remote sensing-based data are a valuable source of estimating forest AGB. In this study, we evaluated the potential of machine learning algorithms (MLAs) by integrating Gaofen-1 (GF1) images, Sentinel-1 (S1) images, and topographic data for AGB estimation in the Dabie Mountain region, China. Variables extracted from GF1 and S1 images and digital elevation model data from sample plots were used to explain the field AGB value variations. The prediction capability of stepwise multiple regression and three MLAs, i.e., support vector machine (SVM), random forest (RF), and backpropagation neural network were compared. The results showed that the RF model achieved the highest prediction accuracy (R2 = 0.70, RMSE = 16.26 t/ha), followed by the SVM model (R2 = 0.66, RMSE = 18.03 t/ha) for the testing datasets. Some variables extracted from the GF1 images (e.g., normalized differential vegetation index, band 1-blue, the mean texture feature of band 3-red with windows of 3 × 3), S1 images (e.g., vertical transmit-horizontal receive and vertical transmit-vertical receive backscatter coefficient), and altitude had strong correlations with field AGB values (p < 0.01). Among the explanatory variables in MLAs, variables extracted from GF1 made a greater contribution to estimating forest AGB than those derived from S1 images. These results indicate the potential of the RF model for evaluating forest AGB by combining GF1 and S1, and that it could provide a reference for biomass estimation using multi-source images.

Wetland vegetation is an important component of wetland ecosystems and plays a crucial role in the ecological functions of wetland environments. Accurate distribution mapping and dynamic change monitoring of vegetation are essential for wetland conservation and restoration. The development of unoccupied aerial vehicles (UAVs) provides an efficient and economic platform for wetland vegetation classification. In this study, we evaluated the feasibility of RGB imagery obtained from the DJI Mavic Pro for wetland vegetation classification at the species level, with a specific application to Honghu, which is listed as a wetland of international importance. A total of ten object-based image analysis (OBIA) scenarios were designed to assess the contribution of five machine learning algorithms to the classification accuracy, including Bayes, K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), and random forest (RF), multi-feature combinations and feature selection implemented by the recursive feature elimination algorithm (RFE). The overall accuracy and kappa coefficient were compared to determine the optimal classification method. The main results are as follows: (1) RF showed the best performance among the five machine learning algorithms, with an overall accuracy of 89.76% and kappa coefficient of 0.88 when using 53 features (including spectral features (RGB bands), height information, vegetation indices, texture features, and geometric features) for wetland vegetation classification. (2) The RF model constructed by only spectral features showed poor classification results, with an overall accuracy of 73.66% and kappa coefficient of 0.70. By adding height information, VIs, texture features, and geometric features to construct the RF model layer by layer, the overall accuracy was improved by 8.78%, 3.41%, 2.93%, and 0.98%, respectively, demonstrating the importance of multi-feature combinations. (3) The contribution of different types of features to the RF model was not equal, and the height information was the most important for wetland vegetation classification, followed by the vegetation indices. (4) The RFE algorithm effectively reduced the number of original features from 53 to 36, generating an optimal feature subset for wetland vegetation classification. The RF based on the feature selection result of RFE (RF-RFE) had the best performance in ten scenarios, and provided an overall accuracy of 90.73%, which was 0.97% higher than the RF without feature selection. The results illustrate that the combination of UAV-based RGB imagery and the OBIA approach provides a straightforward, yet powerful, approach for high-precision wetland vegetation classification at the species level, in spite of limited spectral information. Compared with satellite data or UAVs equipped with other types of sensors, UAVs with RGB cameras are more cost efficient and convenient for wetland vegetation monitoring and mapping.

Land use and land cover change (LUCC) modeling has continuously been a major research theme in the field of land system science, which interprets the causes and consequences of land use dynamics. In particular, models that can obtain long-term land use data with high precision are of great value in research on global environmental change and climate impact, as land use data are important model input parameters for evaluating the effect of human activity on nature. However, the accuracy of existing reconstruction and prediction models is inadequate. In this context, this study proposes an integrated convolutional neural network (CNN) LUCC reconstruction and prediction model (CLRPM), which meets the demand for fine-scale LUCC reconstruction and prediction. This model applies the deep learning method, which far exceeds the performance of traditional machine learning methods, and uses CNN to extract spatial features and provide greater proximity information. Taking Baicheng city in Northeast China as an example, we verify that CLRPM achieved high-precision annual LUCC reconstruction and prediction, with an overall accuracy rate 9.38% higher than that of the existing models. Additionally, the error rate was reduced by 49.5%. Moreover, this model can perform multilevel LUCC classification category reconstructions and predictions. This study casts light on LUCC models within the high-precision and fine-grained LUCC categories, which will aid LUCC analyses and help decision-makers better understand complex land-use systems and develop better land management strategies.

Plant Ecological Unit’s (PEUs) are the abstraction of vegetation communities that occur on a site which similarly respond to management actions and natural disturbances. Identification and monitoring of PEUs in a heterogeneous landscape is the most difficult task in medium resolution satellite images datasets. The main objective of this study is to compare pixel-based classification versus object-based classification for accurately classifying PEUs with four selected different algorithms across heterogeneous rangelands in Central Zagros, Iran. We used images of Landsat-8 OLI that were pan-sharpened to 15 m to classify four PEU classes based on a random dataset collected in the field (40%). In the first stage, we applied the following classification algorithms to distinguish PEUs: Minimum Distance (MD), Maximum Likelihood Classification (MLC), Neural Network-Multi Layer Perceptron (NN-MLP) and Classification Tree Analysis (CTA) for pixel based method and object based method. Then, by using the most accurate classification approach, in the second stage auxiliary data (Principal Component Analysis (PCA)) was incorporated to improve the accuracy of the PEUs classification process. At the end, test data (60%) were used for accuracy assessment of the resulting maps. Object-based maps clearly outperformed pixel-based maps, especially with CTA, NN-MLP and MD algorithms with overall accuracies of 86%, 72% and 59%, respectively. The MLC algorithm did not reveal any significant difference between the object-based and pixel-based analyses. Finally, complementing PCA auxiliary bands to the CTA algorithms offered the most successful PEUs classification strategy, with the highest overall accuracy (89%). The results clearly underpin the importance of object-based classification with the CTA classifier together with PCA auxiliary data to optimize identification of PEU classes.

Many studies have attempted to predict soil organic matter (SOM), whereas mapping high-precision and high-resolution SOM maps remains a challenge due to the difficulty of selecting appropriate satellite data sources and prediction algorithms. This study aimed to investigate the influence of different remotely sensed images and machine learning algorithms on SOM prediction. We constructed two comparative experiments, i.e., full-band and common-band variable datasets of Sentinel-2A and MODIS images using Google Earth Engine (GEE). The predictive performances of random forest (RF), artificial neural network (ANN), and support vector regression (SVR) algorithms were evaluated, and the SOM map was generated for the Songnen Plain. Results showed that the model based on the full-band Sentinel-2A dataset achieved the best performance. The application of Sentinel-2A data resulted in mean relative improvements (RIs) of 7.67% and 5.87%, respectively. The RF achieved a lower root mean squared error (RMSE = 0.68%) and a higher coefficient of determination (R2 = 0.67) in all of the predicted scenarios than ANN and SVR. The resultant SOM map accurately characterized the SOM spatial distribution. Therefore, the Sentinel-2A data have obvious advantages over MODIS due to their higher spectral and spatial resolutions, and the combination of the RF algorithm and GEE is an effective approach to SOM mapping.

In this study, a machine learning algorithm was introduced to fuse gridded snow depth datasets. The input variables of the machine learning method included geolocation (latitude and longitude), topographic data (elevation), gridded snow depth datasets and in situ observations. A total of 29,565 in situ observations were used to train and optimize the machine learning algorithm. A total of five gridded snow depth datasets—Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E) snow depth, Global Snow Monitoring for Climate Research (GlobSnow) snow depth, Long time series of daily snow depth over the Northern Hemisphere (NHSD) snow depth, ERA-Interim snow depth and Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2) snow depth—were used as input variables. The first three snow depth datasets are retrieved from passive microwave brightness temperature or assimilation with in situ observations, while the last two are snow depth datasets obtained from meteorological reanalysis data with a land surface model and data assimilation system. Then, three machine learning methods, i.e., Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Random Forest Regression (RFR), were used to produce a fused snow depth dataset from 2002 to 2004. The RFR model performed best and was thus used to produce a new snow depth product from the fusion of the five snow depth datasets and auxiliary data over the Northern Hemisphere from 2002 to 2011. The fused snow-depth product was verified at five well-known snow observation sites. The R2 of Sodankylä, Old Aspen, and Reynolds Mountains East were 0.88, 0.69, and 0.63, respectively. At the Swamp Angel Study Plot and Weissfluhjoch observation sites, which have an average snow depth exceeding 200 cm, the fused snow depth did not perform well. The spatial patterns of the average snow depth were analyzed seasonally, and the average snow depths of autumn, winter, and spring were 5.7, 25.8, and 21.5 cm, respectively. In the future, random forest regression will be used to produce a long time series of a fused snow depth dataset over the Northern Hemisphere or other specific regions.

This study provided a comprehensive evaluation of eight machine learning regression algorithms for forest aboveground biomass (AGB) estimation from satellite data based on leaf area index, canopy height, net primary production, and tree cover data, as well as climatic and topographical data. Some of these algorithms have not been commonly used for forest AGB estimation such as the extremely randomized trees, stochastic gradient boosting, and categorical boosting (CatBoost) regression. For each algorithm, its hyperparameters were optimized using grid search with cross-validation, and the optimal AGB model was developed using the training dataset (80%) and AGB was predicted on the test dataset (20%). Performance metrics, feature importance as well as overestimation and underestimation were considered as indicators for evaluating the performance of an algorithm. To reduce the impacts of the random training-test data split and sampling method on the performance, the above procedures were repeated 50 times for each algorithm under the random sampling, the stratified sampling, and separate modeling scenarios. The results showed that five tree-based ensemble algorithms performed better than the three nonensemble algorithms (multivariate adaptive regression splines, support vector regression, and multilayer perceptron), and the CatBoost algorithm outperformed the other algorithms for AGB estimation. Compared with the random sampling scenario, the stratified sampling scenario and separate modeling did not significantly improve the AGB estimates, but modeling AGB for each forest type separately provided stable results in terms of the contributions of the predictor variables to the AGB estimates. All the algorithms showed forest AGB were underestimated when the AGB values were larger than 210 Mg/ha and overestimated when the AGB values were less than 120 Mg/ha. This study highlighted the capability of ensemble algorithms to improve AGB estimates and the necessity of improving AGB estimates for high and low AGB levels in future studies.

The number and areal extent of marine protected areas worldwide is rapidly increasing as a result of numerous national targets that aim to see up to 30% of their waters protected by 2030. Automated seabed classification algorithms are arising as faster and objective methods to generate benthic habitat maps to monitor these areas. However, no study has yet systematically compared their repeatability. Here we aim to address that problem by comparing the repeatability of maps derived from acoustic datasets collected on consecutive days using three automated seafloor classification algorithms: (1) Random Forest (RF), (2) K–Nearest Neighbour (KNN) and (3) K means (KMEANS). The most robust and repeatable approach is then used to evaluate the change in seafloor habitats between 2012 and 2015 within the Greater Haig Fras Marine Conservation Zone, Celtic Sea, UK. Our results demonstrate that only RF and KNN provide statistically repeatable maps, with 60.3% and 47.2% agreement between consecutive days. Additionally, this study suggests that in low-relief areas, bathymetric derivatives are non-essential input parameters, while backscatter textural features, in particular Grey Level Co-occurrence Matrices, are substantially more effective in the detection of different habitats. Habitat persistence in the test area between 2012 and 2015 was 48.8%, with swapping of habitats driving the changes in 38.2% of the area. Overall, this study highlights the importance of investigating the repeatability of automated seafloor classification methods before they can be fully used in the monitoring of benthic habitats.

Sown Biodiverse Pastures (SBP) are the basis of a high-yield grazing system tailored for Mediterranean ecosystems and widely implemented in Southern Portugal. The application of precision farming methods in SBP requires cost-effective monitoring using remote sensing (RS). The main hurdle for the remote monitoring of SBP is the fact that the bulk of the pastures are installed in open Montado agroforestry systems. Sparsely distributed trees cast shadows that hinder the identification of the underlaying pasture using Unmanned Aerial Vehicles (UAV) imagery. Image acquisition in the Spring is made difficult by the presence of flowers that mislead the classification algorithms. Here, we tested multiple procedures for the geographical, object-based image classification (GEOBIA) of SBP, aiming to reduce the effects of tree shadows and flowers in open Montado systems. We used remotely sensed data acquired between November 2017 and May 2018 in three Portuguese farms. We used three machine learning supervised classification algorithms: Random Forests (RF), Support Vector Machine (SVM) and Artificial Neural Networks (ANN). We classified SBP based on: (1) a single-period image for the maximum Normalized Difference Vegetation Index (NDVI) epoch in each of the three farms, and (2) multi-temporal image stacking. RF, SVM and ANN were trained using some visible (red, green and blue bands) and near-infrared (NIR) reflectance bands, plus NDVI and a Digital Surface Model (DSM). We obtained high overall accuracy and kappa index (higher than 79% and 0.60, respectively). The RF algorithm had the highest overall accuracy (more than 92%) for all farms. Multitemporal image classification increased the accuracy of the algorithms. as it helped to correctly identify as SBP the areas covered by tree shadows and flower patches, which would be misclassified using single image classification. This study thus established the first workflow for SBP monitoring based on remotely sensed data, suggesting an operational approach for SBP identification. The workflow can be applied to other types of pastures in agroforestry regions to reduce the effects of shadows and flowering in classification problems.

The accurate classification and 3D mapping of benthic habitats in coastal ecosystems are vital for developing management strategies for these valuable shallow water environments. However, both automatic and semiautomatic approaches for deriving ecologically significant information from a towed video camera system are quite limited. In the current study, we demonstrate a semiautomated framework for high-resolution benthic habitat classification and 3D mapping using Structure from Motion and Multi View Stereo (SfM-MVS) algorithms and automated machine learning classifiers. The semiautomatic classification of benthic habitats was performed using several attributes extracted automatically from labeled examples by a human annotator using raw towed video camera image data. The Bagging of Features (BOF), Hue Saturation Value (HSV), and Gray Level Co-occurrence Matrix (GLCM) methods were used to extract these attributes from 3000 images. Three machine learning classifiers (k-nearest neighbor (k-NN), support vector machine (SVM), and bagging (BAG)) were trained by using these attributes, and their outputs were assembled by the fuzzy majority voting (FMV) algorithm. The correctly classified benthic habitat images were then geo-referenced using a differential global positioning system (DGPS). Finally, SfM-MVS techniques used the resulting classified geo-referenced images to produce high spatial resolution digital terrain models and orthophoto mosaics for each category. The framework was tested for the identification and 3D mapping of seven habitats in a portion of the Shiraho area in Japan. These seven habitats were corals (Acropora and Porites), blue corals (H. coerulea), brown algae, blue algae, soft sand, hard sediments (pebble, cobble, and boulders), and seagrass. Using the FMV algorithm, we achieved an overall accuracy of 93.5% in the semiautomatic classification of the seven habitats.

This research aimed at exploiting the joint use of machine learning and polarimetry for improving the retrieval of surface soil moisture content (SMC) from synthetic aperture radar (SAR) acquisitions at C-band. The study was conducted on two agricultural areas in Canada, for which a series of RADARSAT-2 (RS2) images were available along with direct measurements of SMC from in situ stations. The analysis confirmed the sensitivity of RS2 backscattering (σ°) to SMC. The comparison of SMC with the compact polarimetry (CP) parameters, computed from the RS2 acquisitions by the CP data simulator, pointed out that some CP parameters had a sensitivity to SMC equal or better than σ°, with correlation coefficients up to R ≃ 0.4. Based on these results, the potential of machine learning (ML) for SMC retrieval was exploited by implementing and testing on the available data an artificial neural network (ANN) algorithm. The algorithm was implemented using several combinations of σ° and CP parameters. Validation results of the algorithm with in situ observations confirmed the promising capabilities of the ML techniques for SMC monitoring. Furthermore, results pointed out the potential of CP in improving the SMC retrieval accuracy, especially when used in combination with linearly polarized σ°. Depending on the considered input combination, the ANN algorithm was able to estimate SMC with Root Mean Square Error (RMSE) between 3% and 7% of SMC and R between 0.7 and 0.9.

Due to the complex interaction of light with the Earth’s surface, reflectance spectra can be described as highly nonlinear mixtures of the reflectances of the material constituents occurring in a given resolution cell of hyperspectral data. Our aim is to estimate the fractional abundance maps of the materials from the nonlinear hyperspectral data. The main disadvantage of using nonlinear mixing models is that the model parameters are not properly interpretable in terms of fractional abundances. Moreover, not all spectra of a hyperspectral dataset necessarily follow the same particular mixing model. In this work, we present a supervised method for nonlinear spectral unmixing. The method learns a mapping from a true hyperspectral dataset to corresponding linear spectra, composed of the same fractional abundances. A simple linear unmixing then reveals the fractional abundances. To learn this mapping, ground truth information is required, in the form of actual spectra and corresponding fractional abundances, along with spectra of the pure materials, obtained from a spectral library or available in the dataset. Three methods are presented for learning nonlinear mapping, based on Gaussian processes, kernel ridge regression, and feedforward neural networks. Experimental results conducted on an artificial dataset, a data set obtained by ray tracing, and a drill core hyperspectral dataset shows that this novel methodology is very promising.

Terrestrial latent heat flux (LE) is a key component of the global terrestrial water, energy, and carbon exchanges. Accurate estimation of LE from moderate resolution imaging spectroradiometer (MODIS) data remains a major challenge. In this study, we estimated the daily LE for different plant functional types (PFTs) across North America using three machine learning algorithms: artificial neural network (ANN); support vector machines (SVM); and, multivariate adaptive regression spline (MARS) driven by MODIS and Modern Era Retrospective Analysis for Research and Applications (MERRA) meteorology data. These three predictive algorithms, which were trained and validated using observed LE over the period 2000-2007, all proved to be accurate. However, ANNoutperformed the other two algorithms for the majority of the tested configurations for most PFTs and was the only method that arrived at 80% precision for LE estimation. We also applied three machine learning algorithms for MODIS data and MERRA meteorology to map the average annual terrestrial LE of North America during 2002-2004 using a spatial resolution of 0.05°, which proved to be useful for estimating the long-term LE over North America. [ABSTRACT FROM AUTHOR]

This paper investigates the reliability of free and open-source algorithms used in the geographical object-based image classification (GEOBIA) of very high resolution (VHR) imagery surveyed by unmanned aerial vehicles (UAVs). UAV surveys were carried out in a cork oak woodland located in central Portugal at two different periods of the year (spring and summer). Segmentation and classification algorithms were implemented in the Orfeo ToolBox (OTB) configured in the QGIS environment for the GEOBIA process. Image segmentation was carried out using the Large-Scale Mean-Shift (LSMS) algorithm, while classification was performed by the means of two supervised classifiers, random forest (RF) and support vector machines (SVM), both of which are based on a machine learning approach. The original, informative content of the surveyed imagery, consisting of three radiometric bands (red, green, and NIR), was combined to obtain the normalized difference vegetation index (NDVI) and the digital surface model (DSM). The adopted methodology resulted in a classification with higher accuracy that is suitable for a structurally complex Mediterranean forest ecosystem such as cork oak woodlands, which are characterized by the presence of shrubs and herbs in the understory as well as tree shadows. To improve segmentation, which significantly affects the subsequent classification phase, several tests were performed using different values of the range radius and minimum region size parameters. Moreover, the consistent selection of training polygons proved to be critical to improving the results of both the RF and SVM classifiers. For both spring and summer imagery, the validation of the obtained results shows a very high accuracy level for both the SVM and RF classifiers, with kappa coefficient values ranging from 0.928 to 0.973 for RF and from 0.847 to 0.935 for SVM. Furthermore, the land cover class with the highest accuracy for both classifiers and for both flights was cork oak, which occupies the largest part of the study area. This study shows the reliability of fixed-wing UAV imagery for forest monitoring. The study also evidences the importance of planning UAV flights at solar noon to significantly reduce the shadows of trees in the obtained imagery, which is critical for classifying open forest ecosystems such as cork oak woodlands.

Benthic habitat monitoring is essential for many applications involving biodiversity, marine resource management, and the estimation of variations over temporal and spatial scales. Nevertheless, both automatic and semi-automatic analytical methods for deriving ecologically significant information from towed camera images are still limited. This study proposes a methodology that enables a high-resolution towed camera with a Global Navigation Satellite System (GNSS) to adaptively monitor and map benthic habitats. First, the towed camera finishes a pre-programmed initial survey to collect benthic habitat videos, which can then be converted to geo-located benthic habitat images. Second, an expert labels a number of benthic habitat images to class habitats manually. Third, attributes for categorizing these images are extracted automatically using the Bag of Features (BOF) algorithm. Fourth, benthic cover categories are detected automatically using Weighted Majority Voting (WMV) ensembles for Support Vector Machines (SVM), K-Nearest Neighbor (K-NN), and Bagging (BAG) classifiers. Fifth, WMV-trained ensembles can be used for categorizing more benthic cover images automatically. Finally, correctly categorized geo-located images can provide ground truth samples for benthic cover mapping using high-resolution satellite imagery. The proposed methodology was tested over Shiraho, Ishigaki Island, Japan, a heterogeneous coastal area. The WMV ensemble exhibited 89% overall accuracy for categorizing corals, sediments, seagrass, and algae species. Furthermore, the same WMV ensemble produced a benthic cover map using a Quickbird satellite image with 92.7% overall accuracy.

Land cover mapping (LCM) in complex surface-mined and agricultural landscapes could contribute greatly to regulating mine exploitation and protecting mine geo-environments. However, there are some special and spectrally similar land covers in these landscapes which increase the difficulty in LCM when employing high spatial resolution images. There is currently no research on these mixed complex landscapes. The present study focused on LCM in such a mixed complex landscape located in Wuhan City, China. A procedure combining ZiYuan-3 (ZY-3) stereo satellite imagery, the feature selection (FS) method, and machine learning algorithms (MLAs) (random forest, RF; support vector machine, SVM; artificial neural network, ANN) was proposed and first examined for both LCM of surface-mined and agricultural landscapes (MSMAL) and classification of surface-mined land (CSML), respectively. The mean and standard deviation filters of spectral bands and topographic features derived from ZY-3 stereo images were newly introduced. Comparisons of three MLAs, including their sensitivities to FS and whether FS resulted in significant influences, were conducted for the first time in the present study. The following conclusions are drawn. Textures were of little use, and the novel features contributed to improve classification accuracy. Regarding the influence of FS: FS substantially reduced feature set (by 68% for MSMAL and 87% for CSML), and often improved classification accuracies (with an average value of 4.48% for MSMAL using three MLAs, and 11.39% for CSML using RF and SVM); FS showed statistically significant improvements except for ANN-based MSMAL; SVM was most sensitive to FS, followed by ANN and RF. Regarding comparisons of MLAs: for MSMAL based on feature subset, RF achieved the greatest overall accuracy of 77.57%, followed by SVM and ANN; for CSML, SVM had the highest accuracies (87.34%), followed by RF and ANN; based on the feature subsets, significant differences were observed for MSMAL and CSML using any pair of MLAs. In general, the proposed approach can contribute to LCM in complex surface-mined and agricultural landscapes. [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]