Search

Accurate and efficient classification of wetlands, as one of the most valuable ecological resources, using satellite remote sensing data is essential for effective environmental monitoring and sustainable land management. Deep learning models have recently shown significant promise for identifying wetland land cover; however, they are mostly constrained in practical issues regarding efficiency while gaining high accuracy with limited training ground truth samples. To address these limitations, in this study, a novel deep learning model, namely Wet-ConViT, is designed for the precise mapping of wetlands using multi-source satellite data, combining the strengths of multispectral Sentinel-2 and SAR Sentinel-1 datasets. Both capturing local information of convolution and the long-range feature extraction capabilities of transformers are considered within the proposed architecture. Specifically, the key to Wet-ConViT's foundation is the multi-head convolutional attention (MHCA) module that integrates convolutional operations into a transformer attention mechanism. By leveraging convolutions, MHCA optimizes the efficiency of the original transformer self-attention mechanism. This resulted in high-precision land cover classification accuracy with a minimal computational complexity compared with other state-of-the-art models, including two convolutional neural networks (CNNs), two transformers, and two hybrid CNN–transformer models. In particular, Wet-ConViT demonstrated superior performance for classifying land cover with approximately 95% overall accuracy metrics, excelling the next best model, hybrid CoAtNet, by about 2%. The results highlighted the proposed architecture's high precision and efficiency in terms of parameters, memory usage, and processing time. Wet-ConViT could be useful for practical wetland mapping tasks, where precision and computational efficiency are paramount. [ABSTRACT FROM AUTHOR]

Wetland mapping is a critical component of environmental monitoring, requiring advanced techniques to accurately represent the complex land cover patterns and subtle class differences innate in these ecosystems. This study aims to address these challenges by proposing CVTNet, a novel deep learning (DL) model that integrates convolutional neural networks (CNNs) and vision transformer (ViT) architectures. CVTNet uses channel attention (CA) and spatial attention (SA) mechanisms to enhance feature extraction from Sentinel-1 (S1) and Sentinel-2 (S2) satellite data. The primary goal of this model is to achieve a balanced trade-off between Precision and Recall, which is essential for accurate wetland mapping. The class-specific analysis demonstrated CVTNet's proficiency across diverse classes, including pasture, shrubland, urban, bog, fen, and water. Comparative analysis showed that CVTNet outperforms contemporary algorithms such as Random Forest (RF), ViT, multi-layer perceptron mixer (MLP-mixer), and hybrid spectral net (HybridSN) classifiers. Additionally, the attention mechanism (AM) analysis and sensitivity analysis highlighted the crucial role of CA, SA, and ViT in focusing the model's attention on critical regions, thereby improving the mapping of wetland regions. Despite challenges at class boundaries, particularly between bog and fen, and misclassifications of swamp pixels, CVTNet presents a solution for wetland mapping. [ABSTRACT FROM AUTHOR]

Mangrove forests are considered to be the most productive ecosystems on the planet due to the multiple ecosystem services they offer, both environmental economic, and social; however, their area in recent years has been decreasing due to anthropogenic activities such as urbanization and deforestation. These activities alter the normal cycle of carbon stored in sediments, which is considered their main function to counteract climate change. Therefore, the objective of this research was to compare the carbon storage capacity and coverage in forested and non-forested sites of two tropical wetlands located in Colombia (the Caimanera) and Mexico (the Llano). Methodologically, we began by identifying the coverages and determining the area in the wetlands with Sentinel-2A satellite images and a supervised classification; subsequently, soil cores were extracted in all the coverages to a depth of 70 cm and the apparent density (AD), the percentage of organic carbon (OC), and the density of carbon in the soil were determined. For analysis of the variables, a trend graph was constructed between carbon density and depth with descriptive statistics, using one-way ANOVA to establish which coverage and wetland were the most significant concerning carbon storage. The results of the supervised classification showed that Rhizophora mangle and Avicennia germinans are the dominant species, also finding deforested areas in both wetlands. The one-way ANOVA statistical test indicated that the Caimanera, with the percentage of organic carbon (18.4 ± 1.19%), is 1.57 times greater than of the Llano mangrove swamp with (11.7 ± 0.748 MgC/ha). Through the trend graph, it was observed that the carbon density of the forested area of the Caimanera ranged from 120 to 140 MgC/ha, which is higher than in the deforested areas of the same wetland between 40 and 60 MgC/ha, and the homologous areas of the Llano wetland. The results suggest that deforested areas are sources of greenhouse gas emissions because they contain less carbon than forested areas. Therefore, it is concluded that the Caimanera and the Llano wetlands have the same mangrove species and that the average organic carbon stored in their soil is below the average of other mangrove forest soils in the American continent; it is recommended that the findings of this work be considered for the carbon balances by continent and the characterization of mangrove species according to their carbon storage capacity. [ABSTRACT FROM AUTHOR]

Expansion and intensification of agriculture are among the main factors of degradation and systematic loss of wetlands throughout the twentieth century. We analyze the potential occurrence of wetlands in the core area of the temperate Pampas region of South America, recognized for the quality of its pastures and the suitability of its soils for grain production. We mapped the spatial distribution of wetlands in the Province of Buenos Aires based on the analysis and classification of the local soil database at a scale of 1:50,000. Thus, 399 soil series were classified as hydric/non-hydric according to the scope of methods and criteria reviewed. Then we used this information to classify 2211 map units into five categories based on the percentage of hydric and non-hydric soil series: 1—hydric (100% hydric series); 2—predominantly hydric (66–99% hydric series); 3—partially hydric (33–65% hydric series); 4—predominantly non-hydric (1–32% hydric series); and 5—non-hydric (0% hydric series). We estimated wetlands cover about 35% of the province. Wetlands distribution is not uniform, we identified three main landscapes: terrestrial matrix with wetlands, mosaic of wetlands and non-wetlands, and mosaic dominated by wetland patches. Our results provide tools for land management in terms of strategies for a wise use of wetlands and their conservation. Our map shows high values of consistency with the occurrence of wetlands visually identified in high-resolution imagery (Google Earth platform). In such a highly agriculturized landscape, our results indicate a much larger wetland area compared to estimates made with optical remote sensing data classifications. [ABSTRACT FROM AUTHOR]

Accurate and efficient classification of wetlands, as one of the most valuable ecological resources, using satellite remote sensing data is essential for effective environmental monitoring and sustainable land management. Deep learning models have recently shown significant promise for identifying wetland land cover; however, they are mostly constrained in practical issues regarding efficiency while gaining high accuracy with limited training ground truth samples. To address these limitations, in this study, a novel deep learning model, namely Wet-ConViT, is designed for the precise mapping of wetlands using multi-source satellite data, combining the strengths of multispectral Sentinel-2 and SAR Sentinel-1 datasets. Both capturing local information of convolution and the long-range feature extraction capabilities of transformers are considered within the proposed architecture. Specifically, the key to Wet-ConViT’s foundation is the multi-head convolutional attention (MHCA) module that integrates convolutional operations into a transformer attention mechanism. By leveraging convolutions, MHCA optimizes the efficiency of the original transformer self-attention mechanism. This resulted in high-precision land cover classification accuracy with a minimal computational complexity compared with other state-of-the-art models, including two convolutional neural networks (CNNs), two transformers, and two hybrid CNN–transformer models. In particular, Wet-ConViT demonstrated superior performance for classifying land cover with approximately 95% overall accuracy metrics, excelling the next best model, hybrid CoAtNet, by about 2%. The results highlighted the proposed architecture’s high precision and efficiency in terms of parameters, memory usage, and processing time. Wet-ConViT could be useful for practical wetland mapping tasks, where precision and computational efficiency are paramount.

Wetland mapping is a critical component of environmental monitoring, requiring advanced techniques to accurately represent the complex land cover patterns and subtle class differences innate in these ecosystems. This study aims to address these challenges by proposing CVTNet, a novel deep learning (DL) model that integrates convolutional neural networks (CNNs) and vision transformer (ViT) architectures. CVTNet uses channel attention (CA) and spatial attention (SA) mechanisms to enhance feature extraction from Sentinel-1 (S1) and Sentinel-2 (S2) satellite data. The primary goal of this model is to achieve a balanced trade-off between Precision and Recall, which is essential for accurate wetland mapping. The class-specific analysis demonstrated CVTNet’s proficiency across diverse classes, including pasture, shrubland, urban, bog, fen, and water. Comparative analysis showed that CVTNet outperforms contemporary algorithms such as Random Forest (RF), ViT, multi-layer perceptron mixer (MLP-mixer), and hybrid spectral net (HybridSN) classifiers. Additionally, the attention mechanism (AM) analysis and sensitivity analysis highlighted the crucial role of CA, SA, and ViT in focusing the model’s attention on critical regions, thereby improving the mapping of wetland regions. Despite challenges at class boundaries, particularly between bog and fen, and misclassifications of swamp pixels, CVTNet presents a solution for wetland mapping.

Deep learning and remote sensing techniques have significantly advanced water surface monitoring; however, the need for annotated data remains a challenge. This is particularly problematic in wetland detection, where water extent varies over time and space, demanding multiple annotations for the same area. In this paper, we present DeepAqua, a deep learning model inspired by knowledge distillation (a.k.a. teacher–student model) to generate labeled data automatically and eliminate the need for manual annotations during the training phase. We utilize the Normalized Difference Water Index (NDWI) as a teacher model to train a Convolutional Neural Network (CNN) for segmenting water from Synthetic Aperture Radar (SAR) images. To train the student model, we exploit cases where optical- and radar-based water masks coincide, enabling the detection of both open and vegetated water surfaces. DeepAqua represents a significant advancement in computer vision techniques for water detection by effectively training semantic segmentation models without any manually annotated data. Experimental results show that DeepAqua outperforms other unsupervised methods by improving accuracy by 3%, Intersection Over Union by 11%, and F1-score by 6%. This approach offers a practical solution for monitoring wetland water extent changes without the need of ground truth data, making it highly adaptable and scalable for wetland monitoring.

ABSTRACTTimely and accurate wetland information is necessary for wetland resource management. Recent advances in machine learning and remote sensing have facilitated cost-effective monitoring of wetlands. However, reliable methods for fine-grained and rapid wetland mapping are still lacking. To address the issue, a wetland sample set with 20 categories for China was collected based on a sampling strategy that combines automatic sample generation and visual interpretation. Simultaneously, a novel multi-stage method for fine-grained wetland classification was proposed, which integrates pixel-based and object-based strategies using ensemble learning algorithms and multi-source remote sensing data. First, a pixel-based ensemble learning algorithm was implemented to classify five rough wetland categories and six non-wetland categories. Second, an object-based ensemble learning approach was designed to separate the water cover in the pixel-based classification results into eight detailed categories. Third, the merged pixel-based and object-based classification results were refined with knowledge-based post-processing procedures to identify 14 fine-grained wetland categories. Results using the Pixel Information Expert Engine (PIE-Engine) cloud platform proved the effectiveness of the proposed wetland classification method. The overall accuracy, kappa, and weighted F1 reached 87.39%, 82.80%, and 86.02%, respectively. The adopted ensemble learning algorithm yielded better performance than classifiers such as CatBoost, random forest, and XGBoost. The incorporation of spectral, texture, shape, topographic, and geographic features from multi-source data contributed to differentiating wetland categories. According to the relative contribution, spectral indexes (NDVI and NDWI), texture features (sum average and contrast), and topographic features (slope and elevation) were identified as important leading predictors for the first-stage pixel-based classification. Shape features (shape index and compactness) and auxiliary features (geographic location) were crucial predictors for the second-stage object-based classification. Compared with other products, our 10-m wetland mapping results for national wetland reserves were rich in detail and fine in categories. Overall, the constructed sample set and developed classification method show promise in laying a foundation for large-scale wetland mapping. The derived wetland maps can provide support for wetland protection and restoration.

Wetlands are one of the most important ecosystems on the Earth, and using hyperspectral remote sensing (RS) technology for fine wetland mapping is important for restoring and protecting the natural resources of coastal wetlands. However, the high cost in collecting labeled samples and inconsistent acquisition conditions across different geographic regions or scenes lead to difficulties in wetland mapping and classification. To mitigate these difficulties, a spatial–spectral weighted adversarial domain adaptation (SSWADA) network is proposed for the cross-scene wetland mapping using hyperspectral image (HSI). The proposed SSWADA employs an idea of weighted adversarial discrimination to align the feature distribution of source and target scenes, where a generator or feature extractor with joint 2D–3D convolution is used to extract spatial–spectral features of HSI, a weighted discriminator is constructed to perform source instance weighting and a multi-classifier structure is designed to improve the classification performance on target samples. Experimental results on four different tasks show that our SSWADA outperforms existing domain adaptation methods for cross-scene wetland mapping. [ABSTRACT FROM AUTHOR]

As the second batch of international wetland cities, Wuhan and Nanchang, both provincial capital cities in China, have abundant wetland resources. An important sign of achievement of protecting the urban wetland areas is the international wetland city designation. Understanding the growth and changes of wetlands in international wetland cities is necessary for wetland protection and management. Thus, it is crucial to conduct proper wetland mapping in these international wetland cities. By studying wetland cities, sustainable planning can be provided to promote the coordinated development of wetlands and cities. In this research, Google Earth Engine and random forest machine learning were used. According to the “Data-Information-Knowledge-Wisdom” research framework, we carried out mapping of diverse wetlands in Wuhan and Nanchang with a resolution of 10 m in 2015 and 2020. Then, using the findings of wetland mapping, we examined changes in the wetland landscapes of the two cities. Finally, this study examined changes in international wetland city indicators over this time frame. The research results are as follows. 1) Our wetland mapping results in 2015 and 2020 achieved good accuracy, with an overall accuracy of over 0.90 and a kappa coefficient of over 0.85. 2) The total wetland area in both cities increased. Nanchang grew by 91.11 km2, whereas Wuhan grew by 290.68 km2. Most restored wetland areas were far from urban construction areas. In the two cities, the fragmentation of wetlands decreased, the diversity of wetlands increased, and the growth rate of wetlands was high. 3) Wetland rates rose from 17.79% to 19.07% in Nanchang and from 19.74% to 23.12% in Wuhan, according to mapping results between 2015 and 2020. The wetland protection rate in Nanchang remained unchanged, but the wetland protection rate in Wuhan decreased. Wuhan needs to strengthen the protection of increased wetlands. In addition, the study found that most of the increased areas of wetlands were previously cultivated land. The international wetland mapping framework of this study can be easily implemented in other regions of the world.

Detailed wetland inventories and information about the spatial arrangement and the extent of wetland types across the Earth's surface are crucially important for resource assessment and sustainable management. In addition, it is crucial to update these inventories due to the highly dynamic characteristics of the wetlands. Remote sensing technologies capturing high-resolution and multi-temporal views of landscapes are incredibly beneficial in wetland mapping compared to traditional methods. Taking advantage of the Google Earth Engine's computational power and multi-source earth observation data from Sentinel-1 multi-spectral sensor and Sentinel-2 radar, we generated a 10 m nationwide wetlands inventory map for Iran. The whole country is mapped using an object-based image processing framework, containing SNIC superpixel segmentation and a Random Forest classifier that was performed for four different ecological zones of Iran separately. Reference data was provided by different sources and through both field and office-based methods. Almost 70% of this data was used for the training stage and the other 30% for evaluation. The whole map overall accuracy was 96.39% and the producer's accuracy for wetland classes ranged from nearly 65 to 99%. It is estimated that 22,384 km2 of Iran are covered with water bodies and wetland classes, and emergent and shrub-dominated are the most common wetland classes in Iran. Considering the water crisis that has been started in Iran, the resulting ever-demanding map of Iranian wetland sites offers remarkable information about wetland boundaries and spatial distribution of wetland species, and therefore it is helpful for both governmental and commercial sectors. [ABSTRACT FROM AUTHOR]

Context: There a large information gap on the spatial distribution and diversity of wetland types in South America. Aims: We focus on mapping the spatial distribution of broad wetland types in Argentina, based on the integration of open spatial data sources developed by national government agencies. Methods: We designed a two-tier process, as follows: we filtered broad wetland types described in the attributes of the spatial datasets and created a separate vector layer for each wetland class; we then ensembled the layers by populating a 25-m cell raster template. Key results: Our WetCarto_AR layer indicates that wetlands cover 13.5% of mainland Argentina, being distributed throughout the country with a greater concentration towards the north-east, but patchy in the rest of the country. Palustrine is the dominant wetlands class followed by Riparian and Lacustrine. Global datasets underestimated wetland coverage, although the same large wetlands are recognised in all. Conclusions: Our results make visible the known spatial extent of wetlands in Argentina and provide information to feed or validate global models. Implications: Results stress the importance of existing local databases, which, even when generated for other purposes, can be a starting point for country or region wetland mapping. We produced a distribution map of wetlands in Argentina (WetCarto_AR) by integrating open data sources developed by national agencies for other purposes. Wetlands are concentrated towards the north-east but patchy mostly elsewhere. Wetlands cover 13.5% of mainland Argentina, a figure greatly underestimated by global wetland datasets. Our results stress the importance of local databases to map the known extent of wetlands, to feed or validate global models, all contributing to reduce the information gap on wetland distribution in South America. [ABSTRACT FROM AUTHOR]

The Ramsar Convention of 1971 encourages wetland preservation, but it is unclear how climate change will affect wetland extent and related biodiversity. Due to the use of the self-attention mechanism, vision transformers (ViTs) gain better modeling of global contextual information and become a powerful alternative to Convolutional Neural Networks (CNNs). However, ViTs require enormous training datasets to activate their image classification power, and gathering training samples for remote sensing applications is typically costly. As such, in this study, we develop a deep learning algorithm called (WetMapFormer), which effectively utilizes both CNNs and vision transformer architectures for precise mapping of wetlands in three pilot sites around the Albert county, York county, and Grand Bay-Westfield located in New Brunswick, Canada. The WetMapFormer utilizes local window attention (LWA) rather than the conventional self-attention mechanism for improving the capability of feature generalization in a local area by substantially reducing the computational cost of vanilla ViTs. We extensively evaluated the robustness of the proposed WetMapFormer with Sentinel-1 and Sentinel-2 satellite data and compared it with the various CNNs and vision transformer models which include ViT, Swin Transformer, HybridSN, CoAtNet, a multimodel network, and ResNet, respectively. The proposed WetMapFormer achieves F-1 scores of 0.94, 0.94, 0.96, 0.97, 0.97, 0.97, and 1 for the recognition of aquatic bed, freshwater marsh, shrub wetland, bog, fen, forested wetland, and water, respectively. As compared to other vision transformers, the WetMapFormer limits receptive fields while adjusting translational invariance and equivariance characteristics. The codes will be made available publicly at https://github.com/aj1365/WetMapFormer.

Wetlands have suffered from considerable degradation due to anthropogenic and natural disturbances in recent decades. Although some advancements have been made, effective methods that can produce large-scale wetland maps with detailed categories are still lacking due to the diversity and complexity of wetland ecosystems. To address this issue, we developed a novel algorithm for detailed wetland types classification integrating k-fold random forest and hierarchical decision tree, and so named two-step classification algorithm. Firstly, the phenology-based features were composited based on time series Sentinel-1/2 images, and the k-fold random forest was used to extract five rough wetland types in Google Earth Engine platform. Secondly, the hierarchical decision tree designed based on geometric features was used to separate the rough wetland types into fourteen detailed types. Application of the two-step classification method in Northern, Central and Southern Asia (NCSA) resulted in a continental-scale wetland map with an overall accuracy of 90.0 ± 0.5%. Wetland types, including inland marsh, lake, river, coastal swamp, estuarine water, lagoon, shallow marine water, reservoir, canal/channel and agricultural pond, had good accuracy with both UA and PA over 77%. The remaining wetland types had moderate accuracy, with both UA and PA over 58%. As we calculated, total wetland areas of NCSA were 1,375,489.27 km2. Among the fourteen wetland categories, the inland marsh had the largest area (544,584.38 km2) and was primarily distributed in subarctic and humid continental climates, while the canal/channel had the smallest area (1,651.57 km2) and was primarily scattered in desert, semiarid and humid subtropical climates. The lake and floodplain shared generally large areas with value of 392,413.55 km2 and 173,255.71 km2 respectively, which were typically distributed across desert and semiarid climates. This study successfully mapped continental-scale wetlands with detailed categories at a 10-m spatial resolution, which can provide valuable information for the management of wetland ecosystems and facilitate the implementation of wetland-related sustainable development goals.

The goal of this study was to check the climatological, hydrological, hydrogeological, topographical, and also vegetation cover situation of the wetland by using the google earth engine cloud system and calculation of current and future hydrological water balance of the wetland. For this purpose, data from TRMM, MODIS, Terra, LANDSAT, GRACE, and ALOS satellites were used. The results showed that GEE has a lot of potential and application for preparing time series and monitoring areas where little information is available about its past situation. According to the rainfall of 1.1333 mm3, surface runoff of 12.20 mm3, and evapotranspiration of 13.875 mm3 in the wetland area, the water balance of the wetland is -0.452 mm3. This amount indicates the volume of water that the wetland has based on climatic and hydrological relations. This amount will be equal to 1.4 mm3 in 2040, which shows that the wetland condition will improve in the future.

Wetlands are some of the most diverse ecosystems in the world. The accurate mapping of wetland types and monitoring their dynamic changes provide the scientific foundation for wetland conservation and restoration. Aligarh district, located in Uttar Pradesh, had many wetlands but due to encroachment, they are shrinking. No wetland mapping has been done before to compare the past and present situation of wetlands. Therefore under this study, an attempt has been made to understand the status of wetlands in the Aligarh district in terms of their number and extent and also assess the temporal changes during 2002-2017 using the multi-temporal Landsat imageries. Supervised Classification with the Maximum Likelihood algorithm was used to classify the wetlands. We found that about 3988 ha area was covered by wetlands, which is one per cent of the total geographic area of the district. The maximum number of wetlands were point wetlands currently (having less than 1 ha area). In the last 15 years, the area of wetlands decreased by 49%. The overall accuracy of the supervised image produced was 87.50% with a kappa value of 0.75. [ABSTRACT FROM AUTHOR]

The present study attempts to delineate wetlands in the lower Tangon river basin in the Barind flood plain region using spectral water body extraction indices. The main objectives of this present study are simulating and predicting wetland areas using the advanced artificial neural network-based cellular automata (ANN-CA) model and water depth using statistical (adaptive exponential smoothing) as well as advanced machine learning algorithms such as Bagging, Random Subspace, Random Forest, Support vector machine, etc. The result shows that RmNDWI and NDWI are the representative wetland delineating indices. NDWI map was used for water depth prediction. Regarding the prediction of wetland areas, a remarkable decline is likely to be identified in the upcoming two decades. The small wetland patches away from the master stream are expected to dry out during the predicted period, where the major wetland patches nearer to the master stream with greater water depth are rather sustainable, but their depth of water is predicted to be reduced in the next decades. All models show satisfactory performance for wetland depth mapping, but the random subspace model was identified as the best-suited water depth predicting method with an acceptable prediction accuracy (root mean square error <0.34 in all the years) and the machine learning models explored better result than adaptive exponential smoothing. This recent study will be very helpful for the policymakers for managing wetland landscape as well as the natural environment. [ABSTRACT FROM AUTHOR]

Recently, deep learning algorithms, specifically convolutional neural networks (CNNs), have played an important role in remote sensing image classification, including wetland mapping. However, one limitation of deep CNN for classification is its requirement for a great number of training samples. This limitation is particularly enhanced when the classes of interest are spectrally similar, such as that of wetland types, and the training samples are limited. This article presents a novel approach named 3-D hybrid generative adversarial network (3-D hybrid GAN) that addresses the limited training sample issue in the classification of remote sensing imagery with a focus on complex wetland classification. We used a conditional map unit that generates synthetic training samples for only classes with a lower number of training samples to improve the per-class accuracy of wetlands. This procedure overcomes the issue of imbalanced data in conventional wetland mapping. Based on the achieved results, better classification accuracy is obtained by integrating a 3-D generative adversarial network (3-D GAN) and the CNN network of a 3-D hybrid CNN using both 3-D and 2-D convolutional filters. Experimental results on the avalon pilot site located in eastern Newfoundland, Canada, and covering five wetland types of bog, fen, marsh, swamp, and shallow water demonstrate that our model significantly outperforms other CNN models, including the HybridSN, SpectralNet, MLP-mixer, as well as a conventional algorithm of random forest for complex wetland classification by approximately 1% to 51% in terms of F-1 score.

Wetlands are among the most important, yet in danger ecosystems and play a vital role for the well-being of humans as well as flora and fauna. Over the past few years, state-of-the-art deep learning (DL) tools have gained attention for wetland classification within the remote sensing community. However, the DL methods could have complex structure and their efficiency greatly depends on the availability of a large number of training data. Inspired by DL methods, yet with less complexity, the Deep Forest (DF) classifier is an advanced tree-based deep learning tool with a great capability for several remote sensing applications. Despite the effectiveness of DF classifiers, few research studies have investigated the potential of such a powerful technique for classification of remote sensing, with no documented research for wetland classification. Accordingly, the potential of the DF algorithm for the classification of wetland complexes has been investigated in this study. In particular, three well-known classifiers, namely Extreme Gradient Boosting (XGB), Random Forest (RF), and Extra Tree (ET), were used as the tree-based classifier to build DF, for which the hyper parameter tuning is carried out to ensure the optimum classification accuracy. Three well-known tree-based classification algorithms, namely Decision Tree (DT), Conventional Random Forest (CRF), and Conventional Extreme Gradient Boosting (CXGB), as well as a Convolutional Neural Network (CNN) are used as benchmark tools to compare the results obtained from the DF classifiers for wetland mapping. The results demonstrated that the DF-XGB classifier outperforms both DF-RF and DF-ET in terms of classification accuracy albeit with a longer training time. The results also confirmed the superiority of all three DF-based classifiers compared to the CRF and DT classifiers. For example, the DF-XGB improved the F1-score by 14%, 13%, 7%, 3%, and 1% for fen, swamp, marsh, bog, and shallow water, respectively, compared to the optimized CRF. The results indicated that the DF algorithm has great capability to be applied over large areas to support regional and national wetland mapping and monitoring.

Tropical wetland resources have high ecological value to flood storage, greenhouse gas emissions, and biodiversity, with diverse types and widespread distribution. However, cloud pollution, inundation fluctuations, and spectral similarity pose unique challenges in the monitoring of tropical wetland using remote sensing. In this study, we proposed a comprehensive method for mapping the various types of tropical wetland using time series Sentinel-2 images based on the Google Earth Engine (GEE) platform integrated inundation dynamic, phenological, and geography features for multi-class topical wetland mapping (IPG-MTWM). Obtained a precise Vietnam wetland cover map (VWeC), which covers ten types of wetlands within a spatial resolution of 10 m. The overall accuracy (OA) of the VWeC was 82.07 %. compared the VWeC results with other wetland products showing the advantages of the IPG-MTWM in mapping complete wetland cover types with high spatial resolution and accuracy at large scales. The VWeC is the first thematic mapping on wetland cover types of Vietnam, it indicates that Vietnam has approximately 1,367,502.16 ha wetlands, of which coastal wetland accounts for approximately 44.27 % (605,318.3 ha). Vietnam’s wetlands are mainly distributed in South Vietnam (SV). The integrated inundation dynamic, phenological, and geography features method, highlights the potential of precise and fast multi-class topical wetland mapping at a large-scale using hydro-periods Sentinel-2 images and GEE platform. This study provides an important technique and dataset for tropical wetland monitoring, protection, and management.

Nebraska's eastern saline wetlands are globally unique and highly vulnerable inland salt marsh ecosystems. This research aims to evaluate the status of the saline wetlands in eastern Nebraska to discover the conditions of saline wetland hydrology, hydrophytes, and hydraulic soil. The research adopts machine learning and Google Earth Engine to classify Sentinel-2 imagery for water and vegetation classification and the National Agriculture Imagery Program imagery for salinity conditions. Six machine learning models are applied in water, soil, and vegetation detection in the study area. The optimal model (linear kernel SVM) generates an overall accuracy of 99.95% for water classification. For saline vegetation classification, the optimal model is the gradient tree boost with an overall accuracy of 94.07%. The overall accuracy values of saline soil classification using the optimal model (linear kernel SVM) varied among different years. The results of this study show the possibility of an observation approach for continuously monitoring Nebraska's eastern saline wetlands. The water classification results show that the saline wetlands in this area all have a similar temporal water cover pattern within each year. For saline vegetation, the peak season in this area is between June and July. The years 2019 (19.00%) and 2018 (17.69%) had higher saline vegetation cover rates than 2017 (10.54%). The saline soil classification shows that the saline soil area is highly variable in response to changes in the water and vegetation conditions. The research findings provide solid scientific evidence for conservation decision-making in these saline wetland areas. [ABSTRACT FROM AUTHOR]

The goal of this study was to check the climatological, hydrological, hydrogeological, topographical, and also vegetation cover situation of the wetland by using the google earth engine cloud system and calculation of current and future hydrological water balance of the wetland. For this purpose, data from TRMM, MODIS, Terra, LANDSAT, GRACE, and ALOS satellites were used. The results showed that GEE has a lot of potential and application for preparing time series and monitoring areas where little information is available about its past situation. According to the rainfall of 1.1333 mm³, surface runoff of 12.20 mm³, and evapotranspiration of 13.875 mm³ in the wetland area, the water balance of the wetland is -0.452 mm³. This amount indicates the volume of water that the wetland has based on climatic and hydrological relations. This amount will be equal to 1.4 mm3 in 2040, which shows that the wetland condition will improve in the future. [ABSTRACT FROM AUTHOR]

Given the key role wetlands play in climate regulation and shoreline stabilization, identifying their spatial distribution is essential for the management, restoration, and protection of these invaluable ecosystems. The increasing availability of high spatial and temporal resolution optical and synthetic aperture radar (SAR) remote sensing data coupled with advanced machine learning techniques have provided an unprecedented opportunity for mapping complex wetlands' ecosystems. A recent partnership between the National Aeronautics and Space Administration (NASA) and the Indian Space Research Organization (ISRO) resulted in the design of the NASA‐ISRO SAR (NISAR) mission. In this study, the capability of L‐band simulated NISAR data for wetland mapping in Yucatan Lake, Louisiana, is investigated using two object‐based machine learning approaches: Support vector machine (SVM) and random forest (RF). L‐band Unmanned Aerial Vehicle SAR (UAVSAR) data are exploited as a proxy for NISAR data. Specifically, we evaluated the synergistic use of different polarimetric features for efficient delineation of wetland types, extracting 84 polarimetric features from more than 10 polarimetric decompositions. High spatial resolution National Agriculture Imagery Program imagery is applied for image segmentation using the mean‐shift algorithm. Overall accuracies of 74.33% and 81.93% obtained by SVM and RF, respectively, demonstrate the great possibility of L‐band prototype NISAR data for wetland mapping and monitoring. In addition, variable importance analysis using the Gini index for RF classifier suggests that H/A/ALPHA, Freeman‐Durden, and Aghababaee features have the highest contribution to the overall accuracy. Plain Language Summary: By illuminating the surface, SAR signals can provide meaningful information on the shape, geometry, and roughness of the surface. In particular, polarimetric decompositions bring a measure of the relative contribution of backscatter from different scattering mechanisms that can be used for wetland delineations, classification, and monitoring. Given the availability of various polarimetric decompositions, the selection of appropriate decomposition based on the application and SAR sensor configuration is crucial. In this study, we investigated the performance of various polarimetric decompositions for delineating wetlands classes over Yucatan Lake in Louisiana. The adopted machine learning classification workflow was applied to the L‐band simulated NISAR data that are acquired by the UAVSAR platform to evaluate the performance of planned L‐band NISAR data. Our investigation showed that H/A/ALPHA, Freeman‐Durden, and Aghababaee features have the highest contribution to the overall accuracy. Key Points: High spatial resolution Earth Observation (EO) data and machine learning techniques have provided opportunities for preservation of wetlandsL‐band simulated NISAR was captured with UAVSAR as a proxy for evaluating the planned NISAR for application of wetland monitoringUsing 84 polarimetric features and support vector machine and random forest classifiers, overall accuracies of 74.33% and 83.93% were obtained [ABSTRACT FROM AUTHOR]

Wetlands not only affect the local hydrology and ecosystems, but also regulate the conditions of human-environment. However, the availability of accurate wetland data remains a key challenge in wetland research. This study attempts to address this problem through a novel mapping framework that is based on the Google Earth Engine (GEE), feature optimization, and the random forest (RF) model (GFORF). This framework was built to map high-accuracy wetland data on the headwaters of the Brahmaputra, Ganges, and Indus rivers (HBGIR) in the western Tibetan Plateau (TP). Four time periods were examined: 1990, 2000, 2010, and 2017. Our results showed that the overall accuracy for the acquired wetland data was 82.73%, 83.16%, 82.47%, and 88.14% in 1990, 2000, 2010, and 2017, respectively. Furthermore, the feature optimization results showed that the spectral indices feature was the main contributor to the accuracy of wetland mapping, with the highest value being 26.9%. The seasonal factors, surface reflectance, auxiliary data, and texture contributed 21.8%, 21.6%, 21.5%, and 8.1%, respectively. Combining the seasonal features and auxiliary data of distances to rivers significantly improved the mapping accuracy of the wetlands by approximately 14%, 24%, 11%, and 10% in 1990, 2000, 2010, and 2017, respectively. In addition, our analysis showed that the wetland areas in the HBGIR amounted to 5177.39 km2, accounting for 5.82% of the total area. Over the 30-year observation period, the overall consolidation of the wetlands was characterized by a slight expansionary phase, with an average increase of 0.16% per year from 1990 to 2017. As a result of the improvement in the accuracy of wetland mapping in alpine areas, the change dynamics of wetlands was revealed, which provides justification for implementing ongoing wetland ecological services and protection measures.

Abstract Given the key role wetlands play in climate regulation and shoreline stabilization, identifying their spatial distribution is essential for the management, restoration, and protection of these invaluable ecosystems. The increasing availability of high spatial and temporal resolution optical and synthetic aperture radar (SAR) remote sensing data coupled with advanced machine learning techniques have provided an unprecedented opportunity for mapping complex wetlands’ ecosystems. A recent partnership between the National Aeronautics and Space Administration (NASA) and the Indian Space Research Organization (ISRO) resulted in the design of the NASA‐ISRO SAR (NISAR) mission. In this study, the capability of L‐band simulated NISAR data for wetland mapping in Yucatan Lake, Louisiana, is investigated using two object‐based machine learning approaches: Support vector machine (SVM) and random forest (RF). L‐band Unmanned Aerial Vehicle SAR (UAVSAR) data are exploited as a proxy for NISAR data. Specifically, we evaluated the synergistic use of different polarimetric features for efficient delineation of wetland types, extracting 84 polarimetric features from more than 10 polarimetric decompositions. High spatial resolution National Agriculture Imagery Program imagery is applied for image segmentation using the mean‐shift algorithm. Overall accuracies of 74.33% and 81.93% obtained by SVM and RF, respectively, demonstrate the great possibility of L‐band prototype NISAR data for wetland mapping and monitoring. In addition, variable importance analysis using the Gini index for RF classifier suggests that H/A/ALPHA, Freeman‐Durden, and Aghababaee features have the highest contribution to the overall accuracy.

Monitoring wetlands is necessary in order to understand and protect their ecohydrological balance. In Ireland, traditionally wetland-monitoring is carried out by manual field visits which can be very time-consuming. To automate the process, this study extends the ability of remote sensing-based monitoring of wetlands by combining RGB image processing, machine learning algorithms, and satellite data analysis to create seasonal maps of vegetation communities within the wetlands. The methodology matches multispectral and broad coverage of open-source Sentinel-2 (S2) imagery with the high spatial granularity of Unmanned Aerial Vehicles (UAV) or drone images. Single sensor drone imagery was captured, colour corrected and classified using random forest (RF) classifier for a subset of the wetland. The classified imagery was upsampled to satellite imagery scale to create training data for vegetation-segmentation in the entire wetland. The process was repeated for multiple seasons, and an annual map was created utilising the majority voting. The proposed framework has been evaluated on various wetlands across Ireland, with results presented herein for an ombrotrophic peatland complex, Clara Bog. The accuracy of the maps was checked utilising a set of area-based performance metric. The application of this method thereby reduces the number of field surveys typically required to assess the long-term ecological change of such wetland habitats. The performance of the proposed method demonstrates that the technique is a robust, quick, and cost-effective way to map wetland habitats seasonally and to explore their ecohydrological synergies. [ABSTRACT FROM AUTHOR]

Wetlands are mapped across the USA for compliance with §404 of the Clean Water Act using field-collected data and protocols in the 1987 Federal Wetlands Delineation Manual (3-factor method). The National Wetlands Inventory (NWI) maps wetlands and deepwater habitats for management and policy-making using aerial image analysis with limited field verification. There have been few comparisons of maps other than for limited geographic areas or wetland types. We compared 3-factor wetland delineations to NWI maps for 1751 assessment areas (AA) in different regions. We did not assess the accuracy of either product, but instead compared mapped area and polygon count for existing data at sites, then aggregated results to broader scales and compared with ancillary data to identify factors correlated with map differences. In a subset of NWI polygons eliminating non-wetland Cowardin types, 74% of NWI polygons were mapped in common with 3-factor polygons. NWI identified greater area in 33% of AA and greater total area across all sites. Approximately 27% of AA had 3-factor but no NWI polygons, while 6.7% of AA had features mapped only by NWI. Multiple factors likely contributed to differences including polygon size and temporal mismatches between maps, suggesting caution be used when comparing products. [ABSTRACT FROM AUTHOR]

Spatially and thematically explicit information of wetlands is important to understanding ecosystem functions and services, as well as for establishment of management policy and implementation. However, accurate wetland mapping is limited due to lacking an operational classification system and an effective classification approach at a large scale. This study was aimed to map wetlands in China by developing a hybrid object-based and hierarchical classification approach (HOHC) and a new wetland classification system for remote sensing. Application of the hybrid approach and the wetland classification system to Landsat 8 Operational Land Imager data resulted in a wetland map of China with an overall classification accuracy of 95.1%. This national scale wetland map, so named CAS_Wetlands, reveals that China's wetland area is estimated to be 451,084 ± 2014 km2, of which 70.5% is accounted by inland wetlands. Of the 14 sub-categories, inland marsh has the largest area (152,429 ± 373 km2), while coastal swamp has the smallest coverage (259 ± 15 km2). Geospatial variations in wetland areas at multiple scales indicate that China's wetlands mostly present in Tibet, Qinghai, Inner Mongolia, Heilongjiang, and Xinjiang Provinces. This new map provides a new baseline data to establish multi-temporal and continuous datasets for China's wetlands and biodiversity conservation. [ABSTRACT FROM AUTHOR]

Stubbs, Q.; Yeo, I.-Y.; Lang, M.; Townshend, J.; Sun, L.; Prestegaard, K., and Jantz, C., 2020. Assessment of wetland change on the Delmarva Peninsula from 1984 to 2010. Journal of Coastal Research, 36(3), 575–589. Coconut Creek (Florida), ISSN 0749-0208. The decline in wetland extent and condition emphasizes the need for sound wetland restoration and conservation policies, which require baseline information on wetland status, change, and change drivers. Multiple wetland maps are available, but they can be quite inconsistent bcause of different input and generation techniques, dates, and objectives. Moderate-resolution (30 m2) regional land-cover data sets (LCDs) were analyzed to (1) quantify historical wetland changes on the Delmarva Peninsula at multiple spatial scales between 1984 and 2010, (2) identify differences in the spatial area of wetland change and discuss the source of and implications for these differences, and (3) investigate the extent to which drivers of wetland change can be identified using existing LCDs. The following regional LCDs were considered: the National Oceanic and Atmospheric Administration Coastal Change Analysis Program (C-CAP), the U.S. Geological Survey (USGS) Chesapeake Bay Land Cover Data Series (CBLCD), and the USGS National Land Cover Database. The C-CAP and CBLCD had the highest spatial agreement at 97%, and an average of 76% spatial agreement with the U.S. Fish and Wildlife Service National Wetland Inventory. The highest percentages of net wetland loss occurred between 1992 and 2001, whereas net wetland gain occurred between 2001 and 2010. Wetlands were predominantly converted (e.g., lost) to croplands/grass/shrubs (67%) and water (11%), which could be linked to drivers such as agriculture and sea-level rise. [ABSTRACT FROM AUTHOR]

Wetland inventories especially on their spatial extent are a prerequisite for management and conservation of any wetland. The advancement in geospatial techniques has offered a wide range of methodological applications to prepare the inventories and to understand the dynamics of wetlands. The freely available Landsat imagery has been widely used in extracting spatial and temporal information about wetlands. The literature suggests that wetland has declined all over the globe over the past few decades. This study aims to prepare land use/land cover information of three wetlands of Punjab (Harike, Ropar, and Nangal) through direct on screen digitization and through digital processing using automatic digital indices as well. Evaluation of the performance of two band indices, normalized difference water index (NDWI) and modified normalized difference water index (MNDWI) is also taken up in the present study. Landsat data of two periods-1990/91 and of 2018 are used for the study to perform two band indices. The result indicates that the NDWI and MNDWI are less time consuming and serve the purpose of mapping and monitoring wetlands with higher accuracy. [ABSTRACT FROM AUTHOR]

Satellite imagery has been widely used to delineate, map and monitor different wetland types. However, the influence of clouds and spectral confusion between wetlands and other land cover types has a negative effect on classification accuracies across nearly all methods. Most wetlands are topographic lowlands surrounded by uplands, and this study explores the possibilities of delineating wetlands from Digital Elevation Models (DEMs) using the cut-and-fill method. The objectives were: (1) to examine the possible use of the cut-and-fill method, which is commonly used in construction, to delineate different types of large floodplain wetlands, and (2) to compare the accuracy of the cut-and-fill method with wetness indices commonly used for delineating wetlands from satellite images. Comparison between the cut-and-fill method, the Normalised Difference Water Index (NDWI) and the Modified Normalised Water Difference Index (MNDWI) showed that the cut-and-fill method was superior in terms of overall accuracy and kappa statistics while the NDWI was the poorest of the three methods. The study concluded that the cut-and-fill method can be useful in delineating wetland areas, especially for wetlands in confined valley settings and where cloud-free images are not available. [ABSTRACT FROM AUTHOR]

Wetlands are important ecosystems that are linked to climate change mitigation. As 25% of global wetlands are located in Canada, accurate and up-to-date wetland classification is of high importance, nationally and internationally. The advent of deep learning techniques has revolutionized the current use of machine learning algorithms to classify complex environments, specifically in remote sensing. In this paper, we explore the potential and possible limitations to be overcome regarding the use of ensemble deep learning techniques for complex wetland classification and discusses the potential and limitation of various solo convolutional neural networks (CNNs), including DenseNet, GoogLeNet, ShuffleNet, MobileNet, Xception, Inception-ResNet, ResNet18, and ResNet101 in three different study areas located in Newfoundland and Labrador, Canada (i.e., Avalon, Gros Morne, and Grand Falls). Moreover, to improve the classification accuracies of wetland classes of bog, fen, marsh, swamp, and shallow water, the results of the three best CNNs in each study area is fused using three supervised classifiers of random forest (RF), bagged tree (BTree), Bayesian optimized tree (BOT), and one unsupervised majority voting classifier. The results suggest that the ensemble models, in particular BTree, have a valuable role to play in the classification of wetland classes of bog, fen, marsh, swamp, and shallow water. The ensemble CNNs show an improvement of 9.63–19.04% in terms of mean producer’s accuracy compared to the solo CNNs, to recognize wetland classes in three different study areas. This research indicates a promising potential for integrating ensemble-based learning and deep learning for operational large area land cover, particularly complex wetland type classification.

In this study, we proposed an adaptive sparse constrained least squares linear spectral mixture model (SCLS-LSMM) to map wetlands in a sophisticated scene. It includes three procedures: (1) estimating the abundance based on sparse constrained least squares method with all endmembers in the spectral library, (2) selecting “active” endmember combinations for each pixel based on the estimated abundances and (3) estimating abundances based on the linear spectral unmixing algorithm only with the adaptively selected endmember combinations. The performances of the proposed SCLS-LSMM on wetland vegetation communities mapping were compared with the traditional full constrained least squares linear spectral mixture model (FCLS-LSMM) using HJ-1A/B hyperspectral images. The accuracy assessment results showed that the proposed SCLS-LSMM obtained a significantly better performance with a systematic error (SE) of –0.014 and a root-mean-square error (RMSE) of 0.087 for Reed marsh, and a SE of 0.004 and a RMSE of 0.059 for Weedy meadow, compared with the traditional FCLS-LSMM. The proposed methods improved the unmixing accuracies of wetlands’ vegetation communities and have the potential to understand the process of wetlands’ degradation under the impacts of climate changes and permafrost degradation.

• Damming over river has attenuated 32–54% flow in different seasons in the river. • Flow reduction causes drying of wetland accelerating eco-hydrological failure rate. • Degree of hydro-ecological impact is 100% in the outskirt wetland area. • Half of the wetland area has observed eco-hydrological deficit in post-dam period. • Ecological flow is essential for wetland habitat and survival of the ecosystem. In 1992, damming was performed in Punarbhaba river (India and Bangladesh), disturbing water flow and riparian wetland ecology. We measured the eco-hydrological failure rate, degree of flooding alteration and degree of eco-hydro deficit in relation to indicators of hydrological alteration in riparian wetlands. Normalized Differences Water Index (NDWI) and Modified Normalized Differences Water Index (MNDWI) images derived from Landsat satellite images were studied. A greater intensity of NDWI and MNDWI score were associated with the higher amount of water availability and therefore, monthly NDWI and MNDWI values were used. We showed that due to the attenuation of water availability (52% in pre-monsoon season, 34% in monsoon, and 32% in post-monsoon seasons), most months had a considerable decrease of NDWI/MNDWI scores, often below acceptable ecological thresholds. The registered failure rates for attaining the eco-hydrological threshold exceeded 100%. The estimated degree of flooding alteration in the larger parts of wetlands reached 100%, indicating a high degree of impact. Up to 54% of wetlands were eco-hydrologically deficit and 36% of wetlands were critically affected. Sustenance of ecological flow is necessary to reduce the growing hydrological crisis of the wetland habitat and ecosystem. [ABSTRACT FROM AUTHOR]

Remote sensing has been proven promising in wetland mapping. However, conventional methods in a complex and heterogeneous urban landscape usually use mono temporal Landsat TM/ETM + images, which have great uncertainty due to the spectral similarity of different land covers, and pixel-based classifications may not meet the accuracy requirement. This paper proposes an approach that combines spatiotemporal fusion and object-based image analysis, using the spatial and temporal adaptive reflectance fusion model to generate a time series of Landsat 8 OLI images on critical dates of sedge swamp and paddy rice, and the time series of MODIS NDVI to calculate phenological parameters for identifying wetlands with an object-based method. The results of a case study indicate that different types of wetlands can be successfully identified, with 92.38%. The overall accuracy and 0.85 Kappa coefficient, and 85% and 90% for the user's accuracies of sedge swamp and paddy respectively. [ABSTRACT FROM AUTHOR]

Alarming wetland loss and modification of wetland landscape in the Atreyee floodplain is an ensuing concern in post-dam condition (after the construction of a dam over Atreyee river in 2012). The nature of the conflict between the changing wetland and agriculture landscape in the altered hydrological state in post-dam period is investigated and illustrated. Agriculture and wetland maps are prepared from multi-temporal satellite images using frequency approach. The result clearly exhibited that agriculture land is increased substantially (4316.95–8047.53 km2) and wetland is declined (1098.25–592.88 km2) in the post-dam state. Out of the lost, 268.33 km2 of wetland area is transformed into agricultural land and the transformation rate is high from low-frequency water presence (wetland with irregular water appearance) wetland to agricultural land. The consistency and stability of agriculture land are gradually increased over time when it is decreased in case of wetland. Extension and perforation of agricultural practices toward wetland areas are caused for wetland loss and fragmentation of wetland. It causes physical and ecological vulnerability of the same. Increasing number of wetland patches (25,839–31,769), decreasing frequency of agriculture patches (94,280–16,296), dwindling of large core wetland area (656.10–212.04 km2), doubling of large core agriculture land (2270.87–3822.88 km2), etc., are some of the evidences signifying growing conflict between wetland and agriculture land. Aggressive growth in agriculture land has been emerging as a strong reason for wetland loss and transformation. [ABSTRACT FROM AUTHOR]

Highlights • Identifying the improved discrimination by the synergistic use of different SAR features. • Optimizing both the type and number of input features. • Comparing the performance of SVM and RF algorithms for complex wetland classification. Abstract Wetlands are home to a great variety of flora and fauna species and provide several unique environmental services. Knowledge of wetland species distribution is critical for sustainable management and resource assessment. In this study, multi-temporal single- and full-polarized RADARSAT-2 and single-polarized TerraSAR-X data were applied to characterize the wetland extent of a test site located in the north east of Newfoundland and Labrador, Canada. The accuracy and information content of wetland maps using remote sensing data depend on several factors, such as the type of data, input features, classification algorithms, and ecological characteristics of wetland classes. Most previous wetland studies examined the efficiency of one or two feature types, including intensity and polarimetry. Fewer investigations have examined the potential of interferometric coherence for wetland mapping. Thus, we evaluated the efficiency of using multiple feature types, including intensity, interferometric coherence, and polarimetric scattering for wetland mapping in multiple classification scenarios. An ensemble classifier, namely Random Forest (RF), and a kernel-based Support Vector Machine (SVM) were also used to determine the effect of the classifier. In all classification scenarios, SVM outperformed RF by 1.5–5%. The classification results demonstrated that the intensity features had a higher accuracy relative to coherence and polarimetric features. However, an inclusion of all feature types improved the classification accuracy for both RF and SVM classifiers. We also optimized the type and number of input features using an integration of RF variable importance and Spearman’s rank-order correlation. The results of this analysis found that, of 81 input features, 22 were the most important uncorrelated features for classification. An overall classification accuracy of 85.4% was achieved by incorporating these 22 important uncorrelated features based on the proposed classification framework. [ABSTRACT FROM AUTHOR]

The effects of dams on hydrological conditions and ecological functioning of wetlands downstream are less well studied. Rivers and wetlands are vital environmental elements linked to natural and human ecosystems, so it is extremely important to study ecohydrological planning and human well-being. This study investigates the impact of the dam on the hydrological abundance and eco-hydrological alterations of Loktak Lake, which is located upstream of the Ithai barrage. For this purpose, the Indicator of Hydrological Alteration (IHA) was used to examine the ecohydrological threshold, failure rate, impact magnitude and ecohydrological deficit/surplus in a river section and the adjacent wetland in three temporal phases (I, 1996–2001; II, 2006–2011; and III, 2016–2021). The results show that the hydrological surplus has recently increased to 27.22% (phase III), while in phase I it was only 1.1%. Due to the decreasing failure rate of ecological optima, eco-hydrological surplus was recorded in both Loktak lakes, which is an obvious indication of a reduction in ecological distress that may lead to negative impacts on natural and human well-being. However, due to the constant high-water level in the lake, Phumdi is no longer able to reach the bottom of the lake during the dry season. Since it cannot absorb nutrients, the lake's vegetation declines and rotting sediments settle. Since the Ithai Dam closed the outlet that once connected the lake to the sea, fishermen can no longer dispose of the decomposing biomass. This study is important for dam management and planning to consider the impacts on wetlands downstream and to take measures to mitigate these impacts. • Water level rise in Loktak leads to high hydrological abundance throughout the year. • Eco-hydro-surplus was recorded due to the reducing failure rate of ecological optima. • Due to the high-water level, Phumdis unable to reach the lake bed in dry season. • Ithai barrage made impossible for migratory fish to enter the Loktak from Myanmar. [ABSTRACT FROM AUTHOR]

To best conserve wetlands and manage associated ecosystem services in the face of climate and land-use change, wetlands must be routinely monitored to assess their extent and function. Wetland extent and function are largely driven by spatial and temporal patterns in inundation and soil moisture, which to date have been challenging to map, especially within forested wetlands. The objective of this paper is to investigate the different, but often interacting effects, of evergreen vegetation and inundation on leaf-off bare earth return lidar intensity within mixed deciduous-evergreen forests in the Coastal Plain of Maryland, and to develop an inundation mapping approach that is robust in areas of varying levels of evergreen influence. This was achieved through statistical comparison of field derived metrics, and development of a simple yet robust normalization process, based on first of many, and bare earth lidar intensity returns. Results demonstrate the confounding influence of forest canopy gap fraction and inundation, and the effectiveness of the normalization process. After normalization, inundated deciduous forest could be distinguished from non-inundated evergreen forest. Inundation was mapped with an overall accuracy between 99.4% and 100%. Inundation maps created using this approach provide insights into physical processes in support of environmental decision-making, and a vital link between fine-scale physical conditions and moderate resolution satellite imagery through enhanced calibration and validation.