Figure - available from: Remote Sensing
This content is subject to copyright.
Map of study area in the upper Choptank River watershed located in the Delmarva Peninsula, USA. (a) The 2-m WorldView3 (WV3) imagery (acquisition date: April 6, 2015) in a natural color composite. (b) The 2-m light detection and ranging (lidar) digital elevation model (DEM) generated from three separate lidar collections. (c) Topographic wetness index (TWI) derived from the 2-m lidar DEM, which was generated from the System for Automated Geoscientific Analysis (SAGA) v. 7.3.0.
Source publication
The Delmarva Peninsula in the eastern United States is partially characterized by thousands of small, forested, depressional wetlands that are highly sensitive to weather variability and climate change, but provide critical ecosystem services. Due to the relatively small size of these depressional wetlands and their occurrence under forest canopy c...
Similar publications
This article describes methodological approaches and results for digital mapping of water-migrational and erosional-accumulative soil cover structures for the forest-steppe of Tambov Plain. Such maps form the basis for applied maps such as for agroecological studies, forestry, landscape planning, etc. In this study, soil-landscape relationships wer...
Citations
... Consequently, the research design and methodologies in LULCC studies must be meticulously customized. Notably, DL techniques, especially CNNs, have enhanced capabilities for object detection, segmentation, and traditional classification, empowering detailed image analyses (Barbierto et al., 2020;Du et al., 2020;Guo et al., 2021;Pešek et al., 2022). Furthermore, DL autonomously learns data features, a marked advancement over traditional ML, eliminating the need for manual, domain-specific feature engineering Shih et al., 2019;Magalhães et al., 2022). ...
... In contrast, hyperspectral imagery offers a higher spectral resolution, enhancing the identification precision for specific cover types-essential for detailed applications like mineralogy, vegetation studies, and pollution monitoring (Ghamisi et al., 2016;Yu et al., 2017;Li et al., 2019;Lei et al., 2021). Additionally, panchromatic imagery, with its higher spatial resolution, finds its niche in analyzing feature textures and shapes, critical for detailed object recognition tasks (Zhang X. et al., 2020;Sertel et al., 2022;Zhang et al., 2022). Similar to ML, DL models in LSS commonly utilize multi-spectral, hyperspectral, and panchromatic imagery, benefiting from their capacity to learn directly from data. ...
... Similar to ML, DL models in LSS commonly utilize multi-spectral, hyperspectral, and panchromatic imagery, benefiting from their capacity to learn directly from data. These models, particularly adept with CNNs, have proven instrumental for a plethora of tasks, including land cover mapping, crop identification, and change detection, capitalizing on the rich information provided by these advanced imaging methods (Barbierato et al., 2020;Du et al., 2020;Guo et al., 2021;Wang J. et al., 2022;Wang L. et al., 2022;Pešek et al., 2022). ...
This review explores the comparative utility of machine learning (ML) and deep learning (DL) in land system science (LSS) classification tasks. Through a comprehensive assessment, the study reveals that while DL techniques have emerged with transformative potential, their application in LSS often faces challenges related to data availability, computational demands, model interpretability, and overfitting. In many instances, traditional ML models currently present more effective solutions, as illustrated in our decision-making framework. Integrative opportunities for enhancing classification accuracy include data integration from diverse sources, the development of advanced DL architectures, leveraging unsupervised learning, and infusing domain-specific knowledge. The research also emphasizes the need for regular model evaluation, the creation of diversified training datasets, and fostering interdisciplinary collaborations. Furthermore, while the promise of DL for future advancements in LSS is undeniable, present considerations often tip the balance in favor of ML models for many classification schemes. This review serves as a guide for researchers, emphasizing the importance of choosing the right computational tools in the evolving landscape of LSS, to achieve reliable and nuanced land-use change data.
... In addition, in the face of thousands of slight forest undulations, wetlands often occur when the forest canopy is submerged. Du et al. (2020) used the most advanced U-NET semantic segmentation deep neural network to map the submerged area of forest wetlands. They used LiDAR intensity images to infer the inundation of wetlands. ...
The breathtaking economic development put a heavy toll on ecology, especially on water pollution. Efficient water resource management has a long-term influence on the sustainable development of the economy and society. Economic development and ecology preservation are tangled together, and the growth of one is not possible without the other. Deep learning (DL) is ubiquitous in autonomous driving, medical imaging, speech recognition, etc. The spectacular success of deep learning comes from its power of richer representation of data. In view of the bright prospects of DL, this review comprehensively focuses on the development of DL applications in water resources management, water environment protection, and water ecology. First, the concept and modeling steps of DL are briefly introduced, including data preparation, algorithm selection, and model evaluation. Finally, the advantages and disadvantages of commonly used algorithms are analyzed according to their structures and mechanisms, and recommendations on the selection of DL algorithms for different studies, as well as prospects for the application and development of DL in water science are proposed. This review provides references for solving a wider range of water-related problems and brings further insights into the intelligent development of water science.
... Our findings agreed with the results of prior research studies that have underscored the limitations of the NWI in effectively delineating small wetlands. Du et al. [41] conducted an assessment of the NWI program and revealed the challenges faced in achieving precision in wetland mapping, particularly when dealing with the smaller wetland patches -attributable to the NWI adoption of a relatively larger mapping unit, approximately 0.20 hectares. Similarly, Chignell et al. [42] expressed the limitations of the NWI, especially when applied in remote and forested terrains and advocated for the integration of supplementary methodologies to improve the mapping of wetlands. ...
Wetlands are invaluable ecosystems, offering essential services such as carbon sequestration, water purification, flood control and habitat for countless aquatic species. However, these critical environments are under increasing threat from factors like industrialization and agricultural expansion. In this research, we focused on small-sized wetlands, typically less than 10 acres in size, due to their unique ecological roles and groundwater recharge contributions. To effectively protect and manage these wetlands, precise mapping and monitoring are essential. To achieve this, we exploited the capabilities of Sentinel-2 imagery and employ a range of machine learning algorithms, including Random Forest (RF), Classification and Regression Tree (CART), Gradient Tree Boost (GTB), Naive Bayes (NB), k-nearest neighbors (KNN) and Support Vector Machine (SVM). Our evaluation used variables, such as spectral bands, indices and image texture. We also utilized Google Earth Engine (GEE) for streamlined data processing and visualization. We found that Random Forest (RF) and Gradient Tree Boost (GTB) outperformed other classifiers according to the performance evaluation. The Normalized Difference Water Index (NDWI) came out to be one of the important predictors in mapping wetlands. By exploring the synergistic potential of these algorithms, we aim to address existing gaps and develop an optimized approach for accurate small-sized wetland mapping. Our findings will be useful in understanding the value of small wetlands and their conservation in the face of environmental challenges. They will also lay the framework for future wetland research and practical uses.
... La arquitectura más utilizada para tareas de segmentación de imágenes son las arquitecturas codificantes -descodificantes, y en particular el modelo U-Net o derivados de esta (Diakogiannis et al., 2020;Ronneberger et al., 2015). Este modelo fue desarrollado para aplicaciones médicas, sin embargo, ya ha probado su utilidad para obtener clasificaciones o detectar cambios en la superficie terrestre (Bragagnolo et al., 2021b;Clark and McKechnie, 2020;Du et al., 2020;Flood et ...
... Adicionalmente, nueve de las diez clases de interés obtuvieron un F1score más alto en la U-Net que en su contraparte RF, gracias a la inclusión de patrones en la dimensión espacial. Estudios previos, enfocados en comparar RF con alguna técnica de aprendizaje profundo muestran resultados similares (de Bem et al., 2020;Du et al., 2020;Giang et al., 2020;Ienco et al., 2019;Kussul et al., 2017;Robinson et al., 2019;Stoian et al., 2019). ...
... Al comparar el F1-score y OA de la clasificación obtenida en este trabajo con otras clasificaciones realizadas utilizando la U-Net, se observó que este trabajo se encontró entre valores de brillo, saturación y matiz (Clark and McKechnie, 2020;Du et al., 2020;Wagner et al., 2020b). A pesar de que estas técnicas ayudan a que el algoritmo encuentra patrones más generales, suelen ser computacionalmente demandantes por lo que frecuentemente uno se tiene que ajustar a los recursos disponibles. ...
La deforestación y la degradación forestal son dos procesos que contribuyen al cambio global mediante la emisión de gases de efecto invernadero, la pérdida de biodiversidad y la reducción en la calidad de algunos servicios ecosistémicos. Gracias a su capacidad de estudiar grandes superficies y contar con un registro histórico, la percepción remota ha demostrado ser una herramienta esencial para cuantificar estos procesos. Además, el desarrollo de nuevos métodos de análisis como los algoritmos de aprendizaje profundo e imágenes de mayor resolución espectral, espacial y temporal gratuitas abren la posibilidad de desarrollar métodos que permitan mejorar las capacidades actuales de monitoreo. En este contexto, el presente trabajo evaluó el desempeño de los algoritmos de aprendizaje profundo con imágenes multiespectrales y de radar de apertura sintética para clasificar
distintos tipos de coberturas del suelo, detectar la deforestación y la degradación forestal. Los resultados muestran que los algoritmos de aprendizaje profundo, en general, permiten obtener mejores resultados que su contraparte de aprendizaje automatizado, debido a la incorporación de patrones en las dimensiones espaciales y temporales. Sin embargo, dicho desempeño está condicionado al tamaño de muestra y la fuerza de la relación entre la señal remota y la clase o característica a evaluar. Por otro lado, la combinación de la información multiespectral y radar de apertura sintética en general fue beneficiosa, aunque en algunos casos el agregar la información radar brinda resultados similares que solo con la multiespectral. Este último resultado se debe a la falta de contribución de nueva información útil por parte de las imágenes de radar, en comparación con la que ya brindan las imágenes multiespectrales. Los resultados apuntan a que este tipo de técnicas permiten
obtener resultados más precisos para identificar estos procesos, por lo cual, representan una herramienta atractiva para el desarrollo de futuras herramientas encaminadas al monitoreo de estos procesos.
... In [55] introduced an integrated framework that combines enhanced versions of the U-Net and SegNet models to enhance the accuracy and performance of high-resolution image segmentation. Enhanced versions of U-Net have been utilized to analyze the spatial distribution of palm canopy and its relationship with human disturbance and soil conditions [56]; they have also been employed for the assessment of mining activities, a primary cause of deforestation, land use change, and pollution [57], as well as for mapping the inundation status of forested wetlands by integrating spectral bands, topographic data, and lidar information [58]. ...
Land cover classification, generated from satellite imagery through semantic segmentation, has become fundamental for monitoring land use and land cover change (LULCC). The tropical Andes territory provides opportunities due to its significance in the provision of ecosystem services. However, the lack of reliable data for this region, coupled with challenges arising from its mountainous topography and diverse ecosystems, hinders the description of its coverage. Therefore, this research proposes the Tropical Andes Land Cover Dataset (TALANDCOVER). It is constructed from three sample strategies: aleatory, minimum 50%, and 70% of representation per class, which address imbalanced geographic data. Additionally, the U-Net deep learning model is applied for enhanced and tailored classification of land covers. Using high-resolution data from the NICFI program, our analysis focuses on the Department of Antioquia in Colombia. The TALANDCOVER dataset, presented in TIF format, comprises multiband R-G-B-NIR images paired with six labels (dense forest, grasslands, heterogeneous agricultural areas, bodies of water, built-up areas, and bare-degraded lands) with an estimated 0.76 F1 score compared to ground truth data by expert knowledge and surpassing the precision of existing global cover maps for the study area. To the best of our knowledge, this work is a pioneer in its release of open-source data for segmenting coverages with pixel-wise labeled NICFI imagery at a 4.77 m resolution. The experiments carried out with the application of the sample strategies and models show F1 score values of 0.70, 0.72, and 0.74 for aleatory, balanced 50%, and balanced 70%, respectively, over the expert segmented sample (ground truth), which suggests that the personalized application of our deep learning model, together with the TALANDCOVER dataset offers different possibilities that facilitate the training of deep architectures for the classification of large-scale covers in complex areas, such as the tropical Andes. This advance has significant potential for decision making, emphasizing sustainable land use and the conservation of natural resources.
... Digital Elevation Models (DEMs) are digital models used to describe the height and shape of a terrain surface and have been widely used in various fields such as surveying, hydrology, meteorology, geological hazards [1,2], soil, engineering construction, and communication [3][4][5]. Airborne LiDAR [6], as one of the main methods for obtaining DEMs [7][8][9], has become irreplaceable in obtaining large-scale and high-precision geographical scene data due to its high efficiency, strong penetration, and other characteristics. ...
... δ is employed to normalizeÃ. Within δ,Ã is scaled using 1 ...
Due to the irregularity and complexity of ground and non-ground objects, filtering non-ground data from airborne LiDAR point clouds to create Digital Elevation Models (DEMs) remains a longstanding and unresolved challenge. Recent advancements in deep learning have offered effective solutions for understanding three-dimensional semantic scenes. However, existing studies lack the capability to model global semantic relationships and fail to integrate global and local semantic information effectively, which are crucial for the ground filtering of point cloud data, especially for larger objects. This study focuses on ground filtering challenges in large scenes and introduces an elevation offset-attention (E-OA) module, which considers global semantic features and integrates them into existing network frameworks. The performance of this module has been validated on three classic benchmark models (RandLA-Net, point transformer, and PointMeta-L). It was compared with two traditional filtering methods and the advanced CDFormer model. Additionally, the E-OA module was compared with three state-of-the-art attention frameworks. Experiments were conducted on two distinct data sources. The results show that our proposed E-OA module improves the filtering performance of all three benchmark models across both data sources, with a maximum improvement of 6.15%. The performance of models was enhanced with the E-OA module, consistently exceeding that of traditional methods and all competing attention frameworks. The proposed E-OA module can serve as a plug-and-play component, compatible with existing networks featuring local feature extraction capabilities.
... In contrast, our approaches utilize 1 m C-CAP data to extract water polygons, enabling seamless support for NWI maintenance with minimal adjustments. Recent wetland studies using high-resolution data and advanced algorithms have shown great potential in their experimental study regions [20,22,23]. However, due to differing objectives, wetland classification systems, and operational procedures, the resultant wetland maps may exhibit substantial discrepancies with NWI [11], rendering them inadequate for direct NWI maintenance support. ...
The National Wetlands Inventory (NWI) is the most comprehensive wetland geospatial dataset in the United States. However, it can be time-consuming and costly to maintain. This study introduces automated algorithms and methods to support NWI maintenance. Through a wall-to-wall comparison between NWI and Coastal Change Analysis Program (C-CAP) datasets, a pixel-level difference product was generated at 1 m resolution. Building upon this, supplementary attributes describing wetland changes were incorporated into each NWI polygon. Additionally, new water polygons were extracted from C-CAP data, and regional statistics regarding wetland changes were computed for HUC12 watersheds. The 1 m difference product can indicate specific wetland change locations, such as wetland loss to impervious surfaces, the gain of open water bodies from uplands, and the conversion of drier vegetated wetlands to open water. The supplementary attributes can indicate the amount and percentage of wetland loss or water regime change for NWI polygons. Extracted new water polygons can serve as preliminary materials for generating NWI standard-compliant products, expediating NWI maintenance processes while reducing costs. Regional statistics of wetland change can help target watersheds with the most significant changes for maintenance, thereby reducing work areas. The approaches we present hold significant value in supporting NWI maintenance.
... Este estudio mostró que el uso de imágenes multiespectrales y radar con el algoritmo U-net permite obtener una clasificación detallada de la cobertura y uso de suelo con una precisión intermedia (0.78). Este método cuenta con dos ventajas que le permiten obtener mejores resultados que algoritmos previamente disponibles para discriminar entre las clases de interés (Du et al., 2020;Giang et al., 2020): contar con información de la composición de la superficie, características geométricas y de humedad (Mercier et al., 2019;Poortinga et al., 2019), así como resumir patrones espectrales y espaciales de las imágenes. En particular, los resultados de este estudio indican que el método permite clasificar las áreas de bosque y plantaciones maduras con una precisión de usuario de 0.89 y 0.76 y precisión del productor de 0.9 y 0.73, respectivamente. ...
... La comparación entre estos métodos reveló que, aunque la precisión obtenida con la U-net no es tan impresionante, sí implica un aumento de 0.23 en la precisión total de la clasificación y de 0.15 en el F1-score respecto al uso del algoritmo random forests (Solórzano et al., 2021). Estudios previos han reportado resultados similares (Du et al., 2020;Giang et al., 2020). ...
... Este estudio mostró que el uso de imágenes multiespectrales y radar con el algoritmo U-net permite obtener una clasificación detallada de la cobertura y uso de suelo con una precisión intermedia (0.78). Este método cuenta con dos ventajas que le permiten obtener mejores resultados que algoritmos previamente disponibles para discriminar entre las clases de interés (Du et al., 2020;Giang et al., 2020): contar con información de la composición de la superficie, características geométricas y de humedad (Mercier et al., 2019;Poortinga et al., 2019), así como resumir patrones espectrales y espaciales de las imágenes. En particular, los resultados de este estudio indican que el método permite clasificar las áreas de bosque y plantaciones maduras con una precisión de usuario de 0.89 y 0.76 y precisión del productor de 0.9 y 0.73, respectivamente. ...
... La comparación entre estos métodos reveló que, aunque la precisión obtenida con la U-net no es tan impresionante, sí implica un aumento de 0.23 en la precisión total de la clasificación y de 0.15 en el F1-score respecto al uso del algoritmo random forests (Solórzano et al., 2021). Estudios previos han reportado resultados similares (Du et al., 2020;Giang et al., 2020). ...
... Este estudio mostró que el uso de imágenes multiespectrales y radar con el algoritmo U-net permite obtener una clasificación detallada de la cobertura y uso de suelo con una precisión intermedia (0.78). Este método cuenta con dos ventajas que le permiten obtener mejores resultados que algoritmos previamente disponibles para discriminar entre las clases de interés (Du et al., 2020;Giang et al., 2020): contar con información de la composición de la superficie, características geométricas y de humedad (Mercier et al., 2019;Poortinga et al., 2019), así como resumir patrones espectrales y espaciales de las imágenes. En particular, los resultados de este estudio indican que el método permite clasificar las áreas de bosque y plantaciones maduras con una precisión de usuario de 0.89 y 0.76 y precisión del productor de 0.9 y 0.73, respectivamente. ...
... La comparación entre estos métodos reveló que, aunque la precisión obtenida con la U-net no es tan impresionante, sí implica un aumento de 0.23 en la precisión total de la clasificación y de 0.15 en el F1-score respecto al uso del algoritmo random forests (Solórzano et al., 2021). Estudios previos han reportado resultados similares (Du et al., 2020;Giang et al., 2020). ...
