Search Results (2,550)

Accurate land cover mapping is essential for environmental monitoring and agricultural management. Sentinel-2 imagery, with high spatial resolution and open access, provides valuable opportunities for operational classification. Convolutional neural networks (CNNs) have demonstrated state-of-the-art results, yet their adoption is limited by high computational demands and limited methodological transparency. This study proposes a lightweight CNN for soil–vegetation classification, in Dolj County, Romania. The architecture integrates three convolutional blocks, global average pooling, and dropout, with fewer than 150,000 trainable parameters. A fully documented workflow was implemented, covering preprocessing, patch extraction, training, and evaluation, addressing reproducibility challenges common in deep leaning studies. Experiments on Sentinel-2 imagery achieved 91.2% overall accuracy and a Cohen’s kappa of 0.82. These results are competitive with larger CNNs while reducing computational requirements by over 90%. Comparative analyses showed improvements over an NDVI baseline and a favorable efficiency–accuracy balance relative to heavier CNNs reported in the literature. A complementary ablation analysis confirmed that the adopted three-block architecture provides the optimal trade-off between accuracy and efficiency, empirically validating the robustness of the proposed design. These findings highlight the potential of lightweight, transparent deep learning for scalable and reproducible land cover monitoring, with prospects for extension to multi-class mapping, multi-temporal analysis, and fusion with complementary data such as SAR. This work provides a methodological basis for operational applications in resource-constrained environments. Full article

This study presents a multi-resolution and multi-temporal remote sensing approach to assess human-induced changes in cultural landscapes, with a focus on the archaeological site of Amrit (Syria) within the MapDam project. By integrating satellite archives (KH, Landsat series, NASADEM) with ancillary geospatial data (OpenStreetMap) and advanced analytical methods, four decades (1984–2024) of land-use/land-cover (LULC) change and shoreline dynamics were reconstructed. Machine learning classification (Random Forest) achieved high accuracy (Test Accuracy = 0.94; Kappa = 0.89), enabling robust LULC mapping, while predictive modelling of urban expansion, calibrated through a Gradient Boosting Machine, attained a Figure of Merit of 0.157, confirming strong predictive reliability. The results reveal path-dependent urban growth concentrated on low-slope terrains (≤5°) and consistent with proximity to infrastructure, alongside significant shoreline regression after 1974. A Business-as-Usual projection for 2024–2034 estimates 8.676 ha of new anthropisation, predominantly along accessible plains and peri-urban fringes. Beyond quantitative outcomes, this study demonstrates the replicability and scalability of open-source, data-driven workflows using Google Earth Engine and Python 3.14, making them applicable to other high-risk heritage contexts. This transparent methodology is particularly critical in conflict zones or in regions where cultural assets are neglected due to economic constraints, political agendas, or governance limitations, offering a powerful tool to document and safeguard endangered archaeological landscapes. Full article

Kinmen Island, historically known as Quemoy, holds significant historical and geopolitical importance due to its strategic location in the Taiwan Strait, just a few kilometers from the Chinese mainland. This study presents the first comprehensive assessment of soil erosion and deposition on Kinmen, providing a scientific foundation for future land conservation and sustainable development initiatives. It also addresses the underrepresentation of small-island environments in soil erosion modeling by adapting the Revised Universal Soil Loss Equation (RUSLE) and Unit-Stream-Power-based Erosion Deposition (USPED) models for coarse-textured soils under limited rainfall conditions, offering insights into the reliability and limitations of these models in such contexts. The rainfall–runoff erosivity factor (${\mathrm{R}}_{\mathrm{m}}$) was derived from precipitation data at four stations, while soil samples from ten locations were analyzed for the Soil Erodibility Factor (${\mathrm{K}}_{\mathrm{m}}$). Topographic factors, including the Slope Length and Steepness ($\mathrm{LS}$) and the Topographic Sediment Transport (${\mathrm{LS}}_{\mathrm{T}}$) factors, were computed from a 20 m DEM (Digital Elevation Model), and the Cover-Management Factor ($\mathrm{C}$) was obtained from land use classification. The RUSLE estimated a mean soil erosion rate of 2.17 Mg ha⁻¹ year⁻¹, while the USPED results varied with parameterization, ranging from 0.87 to 3.79 Mg ha⁻¹ year⁻¹ for erosion and 1.39 to 6.51 Mg ha⁻¹ year⁻¹ for deposition. The results were compared with studies from the neighboring Fujian Province and contextualized through two field expeditions. This pioneering research advances the understanding of erosion and deposition processes in a strategically located island environment and supports evidence-based policies for land conservation, contributing to SDG 15 (Life on Land) and SDG 13 (Climate Action). Full article

Recent advancements in remote sensing and geospatial processing tools have ushered in a new era of mapping and monitoring landscape changes across various scales. This progress is critical for understanding and anticipating the underlying drivers of environmental change. In particular, large-scale Land Use and Land Cover (LULC) mapping has become an indispensable tool for territorial planning and monitoring. This study aims to map and evaluate LULC changes in the El Jadida region of Morocco between 1985 and 2020. Utilizing multispectral Landsat imagery, we applied and compared three supervised machine learning classification algorithms: Random Forest (RF), Support Vector Machine (SVM), and Neural Network (NNET). Model performance was assessed using statistical metrics, including overall accuracy, the Kappa coefficient, and the F1 score. The results indicate that the RF algorithm was the most effective, achieving an overall accuracy of 90.3% and a Kappa coefficient of 0.859, outperforming both NNET (81.3%; Kappa = 0.722) and SVM (80.2%; Kappa = 0.703). Analysis of explanatory variables underscored the decisive contribution of the NDWI, NDBI, and SWIR and thermal bands in discriminating land cover classes. The spatio-temporal analysis reveals significant urban expansion, primarily at the expense of agricultural land, while forested areas and water bodies remained relatively stable. This trend highlights the growing influence of anthropogenic pressure on landscape structure and underscores its implications for sustainable resource management and land use planning. The findings demonstrate the high efficacy of machine learning, particularly the RF algorithm, for accurate LULC mapping and change detection in the El Jadida region. This study provides a critical evidence base for regional planners to address the ongoing loss of agricultural land to urban expansion. Full article

Rice, as one of the world’s three major staple crops, provides a food source for nearly half of the global population. Timely and accurate acquisition of rice cultivation information is crucial for optimizing spatial distribution, guiding production practices, and safeguarding food security. Taking Bishan District of Chongqing as the study area, NDVI values were derived from Sentinel-2 satellite imagery to construct standard NDVI time-series curves for typical land-cover types, including paddy fields, dryland, water bodies, construction land, and forest and grassland. These curves were then used in the NDVI time-series characteristics method to identify paddy fields. First, the Euclidean distance between the standard NDVI time series of paddy fields and those of other land-cover types was calculated. The sum of these element-wise differences was used to determine the upper threshold for paddy field extraction. Second, the mean absolute deviation between elements of the rice sample dataset and the standard NDVI time series was calculated for each time step. The sum of these average deviations was used as the lower threshold to extract the initial paddy field data. On this basis, an extreme-value constraint was introduced to reduce the interference of mixed pixels from forest and grassland and construction land, effectively eliminating anomalous pixels and improving the accuracy of paddy field identification. Finally, the results were validated and compared with those from other extraction methods. The results indicate that: (1) Paddy fields exhibit distinct NDVI time-series characteristics throughout the entire growing season, which can serve as a reference standard. By calculating the Euclidean distance between the NDVI curves of other land-cover types and those of paddy fields, similarity can be quantified, enabling rice identification. (2) The extraction method based on NDVI time-series characteristics successfully identified paddy fields through the appropriate setting of thresholds. The overall accuracy and Kappa coefficient remained high, while the F1-score consistently exceeded 0.8, indicating a good balance between precision and recall. Furthermore, the bootstrap uncertainty analysis revealed narrow 95% confidence intervals across all metrics, confirming the robustness and statistical reliability of the results. Overall, the proposed method demonstrated excellent performance in paddy field classification and significantly outperformed traditional machine learning methods implemented on the GEE platform. (3) Mixed pixels considerably affected the accuracy of rice classification; however, the introduction of the extreme-value constraint effectively mitigated this influence and further improved classification results. Full article

Bangladesh is highly susceptible to land use land cover (LULC) changes due to its geographical location and dense population. These changes have significant effects on food security, urban development, and natural resource management. Policy planning and resource management largely depend on accurate and detailed LULC maps. However, Bangladesh does not have its own national scale detailed high-resolution LULC maps. This study aims to develop high-resolution land use land cover (HRLULC) maps for Bangladesh for the years 2020 and 2023 using a deep learning method based on convolutional neural network (CNN), and to analyze LULC changes between these years. We used an advanced LULC classification algorithm, namely SACLASS2, that was developed by JAXA to work on multi-temporal satellite data from different sensors. Our HRLULC maps with 14 categories achieved an overall accuracy of 94.55 ± 0.41% with Kappa coefficient 0.93 for 2020 and 94.32 ± 0.42% with Kappa coefficient 0.93 for 2023, which is higher than the commonly accepted standard of around 87 overall accuracy for 14 category LULC map. Between 2020 and 2023, the most notable LULC increase were observed in single cropland (17 ± 4%), aquaculture (20 ± 5%), and brickfield (56 ± 25%). Conversely, decrease occurred for salt pans (47 ± 16%), bare land (24 ± 3%), and built-up (13 ± 3%). These findings offer valuable insights into the spatio-temporal patterns of LULC in Bangladesh, which can support policymakers in making informed decisions and developing effective conservation strategies aimed at promoting sustainable land management and urban planning. Full article

Agricultural landscapes often exhibit low tree cover and homogeneity, leading to various environmental challenges. Traditional farmsteads, as scattered built environments in agricultural landscapes with diverse woody vegetation, enhance ecological heterogeneity and provide significant ecosystem services (ES), yet their dendroflora remains understudied. This study assesses woody vegetation on ten traditional farmsteads in Vojvodina, Serbia as case studies, through field surveys of woody species, biodiversity indices, GIS-based spatial analyses, and classification of species according to functional and ecosystem-related traits, offering insights into ecological patterns within these landscapes. The analysis examines species composition, abundance, origin, structural traits (tree cover, density, age, height, and crown width), and functional roles in ES provision. The vegetation shows potential to contribute to ES, especially through melliferous species (about 80%), food sources (about 82% for humans; 91% for birds, 91% for small mammals, 87% for domestic animals), and windbreak functions (about 76%). Phytoncide-producing species (about 62%) suggest a potential provision of air quality benefits, while entomophilous species (about 83%) indicate a potential provision of pollination support. Traditional farmsteads support biodiversity conservation, habitat provision, and preservation of genetic resources, particularly through old and rare species. Integrating these systems into agroforestry and biodiversity-friendly practices may increase ecological resilience and balance in intensive farming areas. Recognising traditional farmsteads as biodiversity reservoirs is vital for sustainable land use, and for conserving cultural and natural heritage within agricultural landscapes. Full article

Accurate and detailed mapping of coastal wetlands is essential for effective wetland resource management. However, due to periodic tidal inundation, frequent cloud cover, and spectral similarity of land cover types, reliable coastal wetland classification methods remain limited. To address these issues, we developed an integrated pixel- and object-based hierarchical classification strategy based on multi-source remote sensing data to achieve fine-grained coastal wetland classification on Google Earth Engine. With the random forest classifier, pixel-level classification was performed to classify rough wetland and non-wetland types, followed by object-based classification to differentiate artificial and natural attributes of water bodies. In this process, multi-dimensional features including water level, phenology, variation, topography, geography, and geometry were extracted from Sentinel-1/2 time-series images, topographic data and shoreline data, which can fully capture the variability and dynamics of coastal wetlands. Feature combinations were then optimized through Recursive Feature Elimination and Jeffries–Matusita analysis to ensure the model’s ability to distinguish complex wetland types while improving efficiency. The classification strategy was applied to typical coastal wetlands in central Jiangsu in 2020 and finally generated a 10 m wetland map including 7 wetland types and 3 non-wetland types, with an overall accuracy of 92.50% and a Kappa coefficient of 0.915. Comparative analysis with existing datasets confirmed the reliability of this strategy, particularly in extracting intertidal mudflats, salt marshes, and artificial wetlands. This study can provide a robust framework for fine-grained wetland mapping and support the inventory and conservation of coastal wetland resources. Full article

Over the past decade, recurring influxes of pelagic Sargassum have posed significant environmental and economic challenges in the Caribbean Sea. Effective monitoring is crucial for understanding bloom dynamics and mitigating their impacts. This study presents a comprehensive machine learning (ML) and deep learning (DL) framework for detecting Sargassum and estimating its fractional cover using imagery from key satellite sensors: the Operational Land Imager (OLI) on Landsat-8 and the Multispectral Instrument (MSI) on Sentinel-2. A spectral library was constructed from five core spectral bands (Blue, Green, Red, Near-Infrared, and Short-Wave Infrared). It was used to train an ensemble of five diverse classifiers: Random Forest (RF), K-Nearest Neighbors (KNN), XGBoost (XGB), a Multi-Layer Perceptron (MLP), and a 1D Convolutional Neural Network (1D-CNN). All models achieved high classification performance on a held-out test set, with weighted F1-scores exceeding 0.976. The probabilistic outputs from these classifiers were then leveraged as a direct proxy for the sub-pixel fractional cover of Sargassum. Critically, an inter-algorithm agreement analysis revealed that detections on real-world imagery are typically either of very high (unanimous) or very low (contentious) confidence, highlighting the diagnostic power of the ensemble approach. The resulting framework provides a robust and quantitative pathway for generating confidence-aware estimates of Sargassum distribution. This work supports efforts to manage these harmful algal blooms by providing vital information on detection certainty, while underscoring the critical need to empirically validate fractional cover proxies against in situ or UAV measurements. Full article

This study investigates post-fire vegetation transitions and spectral responses in the Snowstorm Fire (2017) and South Sugarloaf Fire (2018) in Nevada using Landsat 8 Operational Land Imager (OLI) surface reflectance imagery and unsupervised ISODATA classification. By comparing pre-fire and post-fire conditions, we have assessed changes in vegetation composition, spectral signatures, and the emergence of novel land cover types. The results revealed widespread conversion of shrubland and conifer-dominated systems to herbaceous cover with significant reductions in near-infrared reflectance and elevated shortwave infrared responses, indicative of vegetation loss and surface alteration. In the South Sugarloaf Fire, three new spectral classes emerged post-fire, representing ash-dominated, charred, and sparsely vegetated conditions. A similar new class emerged in Snowstorm, highlighting the spatial heterogeneity of fire effects. Class stability analysis confirmed low persistence of shrub and conifer types, with grassland and herbaceous classes showing dominant post-fire expansion. The findings highlight the ecological consequences of high-severity fire in sagebrush ecosystems, including reduced resilience, increased invasion risk, and type conversion. Unsupervised classification and spectral signature analysis proved effective for capturing post-fire landscape change and can support more accurate, site-specific post-fire assessment and restoration planning. Full article

Landscape character assessment (LCA) is a systematic approach used to classify, describe, and analyze the physical and cultural attributes that define the landscape. The traditional approaches to LCA are fundamentally subjective and descriptive, relying on human evaluations of aesthetic value, and they often show inconsistencies in results when assessed by different observers for the same landscape. This research aims to establish a spatial and quantitative methodology through GIS for evaluating the landscape character of King Khalid University (KKU)’s campus in the Southern Province of Saudi Arabia, which is considered crucial for designing a sustainable and context-sensitive landscape. To identify the feasible developed areas and their sustainable characteristics, three key landscape variables were measured and spatially expressed, subsequently averaged to categorize landscape character. The variables include land use and land cover, which were obtained from Sentinel 2 remote sensing data through supervised classification, as well as landforms and hydrological settings derived from a digital elevation model (DEM) utilizing GIS functionalities. The findings revealed three distinct landscape characters, each characterized by quantifiable landscape attributes. The landscapes exhibiting the most significant character encompass approximately 20% (1074 ha) of the study area, whereas those with the least significance account for 6.5% (342 ha). The remaining 73.5% (3884 ha) is classified as landscapes with an average significance character. The results provide a solid scientific basis for choosing locations in the campus’s study area that promote environmentally friendly and sustainable landscape development. This method improves objectivity in LCA and offers a reproducible framework for implementation in arid and semi-arid areas. Full article

Wetlands, among the most productive ecosystems on Earth, shelter a diversity of species and help maintain ecological balance. However, they are witnessing growing anthropogenic and climatic threats, which underscores the need for regular and long-term monitoring. This study presents a systematic review of 121 peer-reviewed articles published between January 2015 and 30 April 2025 that applied machine learning (ML) and deep learning (DL) for wetland mapping and bird-habitat monitoring. Despite rising interest, applications remain fragmented, especially for avian habitats; only 39 studies considered birds, and fewer explicitly framed wetlands as bird habitats. Following PRISMA 2020 and the SPIDER framework, we compare data sources, classification methods, validation practices, geographic focus, and wetland types. ML is predominant overall, with random forest the most common baseline, while DL (e.g., U-Net and Transformer variants) is underused relative to its broader land cover adoption. Where reported, DL shows a modest but consistent accuracy over ML for complex wetland mapping; this accuracy improves when fusing synthetic aperture radar (SAR) and optical data. Validation still relies mainly on overall accuracy (OA) and Kappa coefficient ($\kappa$), with limited class-wise metrics. Salt marshes and mangroves dominate thematically, and China geographically, whereas peatlands, urban marshes, tundra, and many regions (e.g., Africa and South America) remain underrepresented. Multi-source fusion is beneficial yet not routine; The combination of unmanned aerial vehicles (UAVs) and DL is promising for fine-scale avian micro-habitats but constrained by disturbance and labeling costs. We then conclude with actionable recommendations to enable more robust and scalable monitoring. This review can be considered as the first comparative synthesis of ML/DL methods applied to wetland mapping and bird-habitat monitoring, and highlights the need for more diverse, transferable, and ecologically/socially integrated AI applications in wetland and bird-habitat monitoring. Full article

This study investigates landslide occurrence in Taiwan, a region highly susceptible to landslides due to steep mountains and frequent typhoons (TYPs). The primary objective is to understand how both geomorphological factors and TYP characteristics contribute to landslide occurrence, which is essential for improving hazard prediction and risk management. The research analyzed landslide events that occurred during the TYP seasons of 2019 and 2023. The methodology involved using satellite-derived landslide inventories from SPOT imagery for events larger than 0.1 hectares, tropical cyclone track and intensity data from IBTrACS v4 (classified by Saffir–Simpson Hurricane Scale), and detailed topographic variables (elevation, slope, aspect, Stream Power Index) extracted from a 30 m Shuttle Radar Topography Mission Digital Elevation Model (SRTM-DEM). Land use and land cover classifications were based on Landsat imagery. To establish a timeline, landslides were matched with TYPs within a ±3-day window, and proximity was analyzed using buffer zones ranging from 50 to 500 km around storm centers. Key findings revealed that landslide susceptibility results from a complex interplay of meteorological, topographic, and land cover factors. The critical controls identified include elevations above 2000 m, slope angles between 30 and 45 degrees, southeast- and south-facing aspects, and low Stream Power Index values typical of headwater and upper slope locations. Landslides were most frequent during Category 3 TYPs and were concentrated 300 to 350 km from storm centers, where optimal rainfall conditions for slope failures exist. Interestingly, despite the stronger storms in 2023, the number of landslides was higher in 2019. This emphasizes the importance of interannual variability and terrain preparedness. These findings support sustainable disaster risk reduction and climate-resilient development, aligning with Sustainable Development Goals 11 (Sustainable Cities and Communities) and 13 (Climate Action). Furthermore, they provide a foundation for improving hazard assessment and risk mitigation in Taiwan and similar mountainous, TYP-prone regions. Full article

Accurate mapping of forest canopy height is essential for monitoring forest structure, assessing biodiversity, and informing sustainable management practices. However, obtaining high-resolution canopy height data across large tropical landscapes remains challenging and prohibitively expensive. While machine learning approaches like Random Forest have become standard for predicting forest attributes from remote sensing data, deep learning methods remain underexplored for canopy height mapping despite their potential advantages. To address this limitation, we developed a rapid, automatic, scalable, and cost-efficient deep learning framework that predicts tree canopy height at fine-grained resolution (30 × 30 m) across Indonesian Borneo’s tropical forests. Our approach integrates diverse remote sensing data, including Landsat-8, Sentinel-1, land cover classifications, digital elevation models, and NASA Carbon Monitoring System airborne LiDAR, along with derived vegetation indices, texture metrics, and climatic variables. This comprehensive data pipeline produced over 300 features from approximately 2 million observations across Bornean forests. Using LiDAR-derived canopy height measurements from ~100,000 ha as training data, we systematically compared multiple machine learning approaches and found that our neural network model achieved canopy height predictions with R2 of 0.82 and RMSE of 4.98 m, substantially outperforming traditional machine learning approaches such as Random Forest (R2 of 0.57–0.59). The model performed particularly well for forests with canopy heights between 10–40 m, though systematic biases were observed at the extremes of the height distribution. This framework demonstrates how freely available satellite data can be leveraged to extend the utility of limited LiDAR coverage, enabling cost-effective forest structure monitoring across vast tropical landscapes. The approach can be adapted to other forest regions worldwide, supporting applications in ecological research, conservation planning, and forest loss mitigation. Full article

Protected areas play a fundamental role in the implementation of international environmental strategies in order to ensure effective management systems that support the conservation of biodiversity and the provision of ecosystem services. However, the actual capacity of national parks to generate a specific “park effect” remains an open question. This study aims to assess whether the transformations observed in Italian national parks between 1960 and 2018 can be attributed to a specific park effect or are instead the result of other territorial dynamics. We analyzed long-term changes in land use and land cover (LUMCs) and variations in ecosystem services (ES), both inside and outside park boundaries, taking into account the SNAI classification. The results show a significant expansion of forest areas (+52%) and sparse vegetation (+56%), alongside a marked decline in arable land (−60%) and permanent crops (−26%). At the same time, the overall value of ES remains stable at around EUR 4 billion per year, with regulating services—accounting for 80% of the total—increasing by 20% between 1960 and 2018 and provisioning services declining by 41%. Italy’s national parks represent strategic socioecological laboratories capable of generating benefits both locally and globally. To fully realize this potential, more integrated management is needed, enabling their transformation from mere conservation areas to drivers of territorial resilience and social cohesion. Full article