Search Results (285)

In recent years, large-scale linear infrastructure developments have been developed across hundreds of kilometers of permafrost regions on the Qinghai–Tibet Plateau. The implementation of major engineering projects, including the Qinghai–Tibet Highway, oil pipelines, communication cables, and the Qinghai–Tibet Railway, has spurred intensified research into permafrost dynamics. Climate warming has accelerated permafrost degradation, leading to a range of geological hazards, most notably widespread thermokarst landslides. This study investigates the spatiotemporal distribution patterns and influencing factors of thermokarst landslides in Qinghai Province through an integrated approach combining field surveys, remote sensing interpretation, and statistical analysis. The study utilized multi-source datasets, including Landsat-8 imagery, Google Earth, GF-1, and ZY-3 satellite data, supplemented by meteorological records and geospatial information. The remote sensing interpretation identified 1208 cryogenic hazards in Qinghai’s permafrost regions, comprising 273 coarse-grained soil landslides, 346 fine-grained soil landslides, 146 thermokarst slope failures, 440 gelifluction flows, and 3 frost mounds. Spatial analysis revealed clusters of hazards in Zhiduo, Qilian, and Qumalai counties, with the Yangtze River Basin and Qilian Mountains showing the highest hazard density. Most hazards occur in seasonally frozen ground areas (3500–3900 m and 4300–4900 m elevation ranges), predominantly on north and northwest-facing slopes with gradients of 10–20°. Notably, hazard frequency decreases with increasing permafrost stability. These findings provide critical insights for the sustainable development of cold-region infrastructure, environmental protection, and hazard mitigation strategies in alpine engineering projects. Full article

Artificial intelligence (AI) has become the mainstream of analysis tools in remote sensing. Various semantic segmentation models have been introduced to segment land cover from aerial or satellite images, and remarkable results have been achieved. However, they often lack universal performance on unseen images, making them challenging to provide as a service. One of the primary reasons for the lack of robustness is overfitting, resulting from errors and inconsistencies in the ground truth (GT). In this study, we propose a method to mitigate these inconsistencies by utilizing redundant models and verify the improvement using a public dataset based on Google Earth images. Redundant models share the same network architecture and hyperparameters but are trained with different combinations of training and validation data on the same dataset. Because of the variations in sample exposure during training, these models yield slightly different inference results. This variability allows for the estimation of pixel-level confidence levels for the GT. The confidence level is incorporated into the GT to influence the loss calculation during the training of the enhanced model. Furthermore, we implemented a consensus model that employs modified masks, where classes with low confidence are substituted by the dominant classes identified through a majority vote from the redundant models. To further improve robustness, we extended the same approach to fuse the dataset with different class compositions based on imagery from the Korea Multipurpose Satellite 3A (KOMPSAT-3A). Performance evaluations were conducted on three network architectures: a simple network, U-Net, and DeepLabV3. In the single-dataset case, the performance of the enhanced and consensus models improved by an average of 2.49% and 2.59% across the network architectures. In the multi-dataset scenario, the enhanced models and consensus models showed an average performance improvement of 3.37% and 3.02% across the network architectures, respectively, compared to an average increase of 1.55% without the proposed method. Full article

Aquatic vegetation plays a crucial role in freshwater ecosystems by providing habitats, regulating water quality, and supporting biodiversity. This study aims to monitor and analyze the dynamics of aquatic vegetation in Chimaditida Shallow Lake, Greece, using Sentinel-2 satellite imagery, with validation from field measurements. Data processing was performed using Google Earth Engine and QGIS. The study focuses on discriminating and mapping two classes of aquatic surface conditions: areas covered with Floating and Emergent Aquatic Vegetation and open water, covering all seasons from 1 March 2024, to 28 February 2025. Spectral bands such as B04 (red), B08 (near infrared), B03 (green), and B11 (shortwave infrared) were used, along with indices like the Modified Normalized Difference Water Index and Normalized Difference Vegetation Index. The classification was enhanced using Otsu’s thresholding technique to distinguish accurately between Floating and Emergent Aquatic Vegetation and open water. Seasonal fluctuations were observed, with significant peaks in vegetation growth during the summer and autumn months, including a peak coverage of 2.08 km² on 9 September 2024 and a low of 0.00068 km² on 28 December 2024. These variations correspond to the seasonal growth patterns of Floating and Emergent Aquatic Vegetation, driven by temperature and nutrient availability. The study achieved a high overall classification accuracy of 89.31%, with producer accuracy for Floating and Emergent Aquatic Vegetation at 97.42% and user accuracy at 95.38%. Validation with Unmanned Aerial Vehicle-based aerial surveys showed a strong correlation (R² = 0.88) between satellite-derived and field data, underscoring the reliability of Sentinel-2 for aquatic vegetation monitoring. Findings highlight the potential of satellite-based remote sensing to monitor vegetation health and dynamics, offering valuable insights for the management and conservation of freshwater ecosystems. The results are particularly useful for governmental authorities and natural park administrations, enabling near-real-time monitoring to mitigate the impacts of overgrowth on water quality, biodiversity, and ecosystem services. This methodology provides a cost-effective alternative for long-term environmental monitoring, especially in regions where traditional methods are impractical or costly. Full article

The Mediterranean region, identified by scientists as a ‘climate hot spot’, is experiencing warmer and drier conditions, along with an increase in the intensity and frequency of extreme weather events. One such extreme phenomena is droughts. The recent wildfires in this region are a concerning consequence of this phenomenon, causing severe environmental damage and transforming natural landscapes. However, droughts involve a two-way interaction: On the one hand, climate change and various human activities, such as urbanization and deforestation, influence the development and severity of droughts. On the other hand, droughts have a significant impact on various sectors, including ecology, agriculture, and the local economy. This study investigates drought dynamics in four Mediterranean countries, Greece, France, Italy, and Spain, each of which has experienced severe wildfire events in recent years. Using satellite-based Earth observation data, we monitored drought conditions across these regions over a five-year period that includes the dates of major wildfires. To support this analysis, we derived and assessed key indices: the Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Normalized Difference Drought Index (NDDI). High-resolution satellite imagery processed within the Google Earth Engine (GEE) platform enabled the spatial and temporal analysis of these indicators. Our findings reveal that, in all four study areas, peak drought conditions, as reflected in elevated NDDI values, were observed in the months leading up to wildfire outbreaks. This pattern underscores the potential of satellite-derived indices for identifying regional drought patterns and providing early signals of heightened fire risk. The application of GEE offered significant advantages, as it allows efficient handling of long-term and large-scale datasets and facilitates comprehensive spatial analysis. Our methodological framework contributes to a deeper understanding of regional drought variability and its links to extreme events; thus, it could be a valuable tool for supporting the development of adaptive management strategies. Ultimately, such approaches are vital for enhancing resilience, guiding water resource planning, and implementing early warning systems in fire-prone Mediterranean landscapes. Full article

Mangroves, as a key component of the blue-carbon ecosystem, have exceptional carbon sequestration capacity and are mainly distributed in tropical coastal regions. In the Solomon Islands, ongoing degradation of mangrove forests, primarily due to land conversion and timber exploitation, highlights an urgent need for high-resolution spatial data to inform effective conservation strategies. The present study introduces an efficient and accurate methodology for mapping mangrove habitats and prioritizing protection areas utilizing open-source satellite imagery and datasets available through the Google Earth Engine platform in conjunction with a U-Net deep learning algorithm. The model demonstrates high performance, achieving an F1-score of 0.834 and an overall accuracy of 0.96, in identifying mangrove distributions. The total mangrove area in the Solomon Islands is estimated to be approximately 71,348.27 hectares, accounting for about 2.47% of the national territory. Furthermore, based on the mapped mangrove habitats, an optimized hotspot analysis is performed to identify regions characterized by high-density mangrove distribution. By incorporating spatial variables such as distance from roads and urban centers, along with mangrove area, this study proposes priority mangrove protection areas. These results underscore the potential for using openly accessible satellite data to enhance the precision of mangrove conservation strategies in data-limited settings. This approach can effectively support coastal resource management and contribute to broader climate change mitigation strategies. Full article

Mangroves form the dominant coastal plant community of low-energy tropical intertidal habitats and provide critical ecosystem services to humans and the environment. However, more frequent and increasingly powerful hurricanes and storm surges are creating additional pressure on the natural resilience of these threatened coastal ecosystems. Advances in remote sensing techniques and approaches are critical to providing robust quantitative monitoring of post-storm mangrove forest recovery to better prioritize the often-limited resources available for the restoration of these storm-damaged habitats. Here, we build on previously utilized spatial and temporal ranges of European Space Agency (ESA) Sentinel satellite imagery to monitor and map the recovery of the mangrove forests of the British Virgin Islands (BVI) since the occurrence of back-to-back category 5 hurricanes, Irma and Maria, on September 6 and 19 of 2017, respectively. Pre- to post-storm changes in coastal mangrove forest health were assessed annually using the normalized difference vegetation index (NDVI) and moisture stress index (MSI) from 2016 to 2023 using Google Earth Engine. Results reveal a steady trajectory towards forest health recovery on many of the Territory’s islands since the storms’ impacts in 2017. However, some mangrove patches are slower to recover, such as those on the islands of Virgin Gorda and Jost Van Dyke, and, in some cases, have shown a continued decline (e.g., Prickly Pear Island). Our work also uses a linear ANCOVA model to assess a variety of geospatial, environmental, and anthropogenic drivers for mangrove recovery as a function of NDVI pre-storm and post-storm conditions. The model suggests that roughly 58% of the variability in the 7-year difference (2016 to 2023) in NDVI may be related by a positive linear relationship with the variable of population within 0.5 km and a negative linear relationship with the variables of northwest aspect vs. southwest aspect, island size, temperature, and slope. Full article

Remote sensing has emerged as a promising technology for large-scale detection and updating of global wind turbine databases. High-resolution imagery (e.g., Google Earth) facilitates the identification of offshore wind turbines (OWTs) but offers limited offshore coverage due to the high cost of capturing vast ocean areas. In contrast, medium-resolution imagery, such as 10-m Sentinel-2, provides broad ocean coverage but depicts turbines only as small bright spots and shadows, making accurate detection challenging. To address these limitations, We propose a novel deep learning approach to capture the variability in OWT appearance and shadows caused by changes in solar illumination and satellite viewing geometry. Our method learns intrinsic, imaging geometry-invariant features of OWTs, enabling robust detection across multi-seasonal Sentinel-2 imagery. This approach is implemented using Faster R-CNN as the baseline, with three enhanced extensions: (1) direct integration of imaging parameters, where Geowise-Net incorporates solar and view angular information of satellite metadata to improve geometric awareness; (2) implicit geometry learning, where Contrast-Net employs contrastive learning on seasonal image pairs to capture variability in turbine appearance and shadows caused by changes in solar and viewing geometry; and (3) a Composite model that integrates the above two geometry-aware models to utilize their complementary strengths. All four models were evaluated using Sentinel-2 imagery from offshore regions in China. The ablation experiments showed a progressive improvement in detection performance in the following order: Faster R-CNN < Geowise-Net < Contrast-Net < Composite. Seasonal tests demonstrated that the proposed models maintained high performance on summer images against the baseline, where turbine shadows are significantly shorter than in winter scenes. The Composite model, in particular, showed only a 0.8% difference in the F1 score between the two seasons, compared to up to 3.7% for the baseline, indicating strong robustness to seasonal variation. By applying our approach to 887 Sentinel-2 scenes from China’s offshore regions (2023.1–2025.3), we built the China OWT Dataset, mapping 7369 turbines as of March 2025. Full article

In January 2025, a magnitude 6.8 earthquake struck Dingri County, Shigatse, Tibet, causing severe damage. Rapid and precise extraction of damaged buildings is essential for emergency relief and rebuilding efforts. This study proposes an approach integrating YOLO-E (Real-Time Seeing Anything) and the Segment Anything Model 2 (SAM2) to extract damaged buildings with multi-source remote sensing images, including post-earthquake Gaofen-7 imagery (0.80 m), Beijing-3 imagery (0.30 m), and pre-earthquake Google satellite imagery (0.15 m), over the affected region. In this hybrid approach, YOLO-E functions as the preliminary segmentation module for initial segmentation. It leverages its real-time detection and segmentation capability to locate potential damaged building regions and generate coarse segmentation masks rapidly. Subsequently, SAM2 follows as a refinement step, incorporating shapefile information from pre-disaster sources to apply precise, pixel-level segmentation. The dataset used for training contained labeled examples of damaged buildings, and the model optimization was carried out using stochastic gradient descent (SGD), with cross-entropy and mean squared error as the selected loss functions. Upon evaluation, the model reached a precision of 0.840, a recall of 0.855, an F1-score of 0.847, and an IoU of 0.735. It successfully extracted 492 suspected damaged building patches within a radius of 20 km from the earthquake epicenter, clearly showing the distribution characteristics of damaged buildings concentrated in the earthquake fault zone. In summary, this hybrid YOLO-E and SAM2 approach, leveraging multi-source remote sensing imagery, delivers precise and rapid extraction of damaged buildings with a precision of 0.840, recall of 0.855, and IoU of 0.735, effectively supporting targeted earthquake rescue and post-disaster reconstruction efforts in the Dingri County fault zone. Full article

The Xixia Imperial Tombs (XITs) represent a crucial, yet still largely mysterious, component of the Tangut civilization’s legacy. Located in northwestern China, this extensive necropolis offers invaluable insights into the Tangut state, culture, and burial practices. This study employs an integrated approach utilizing multi-resolution and multi-temporal satellite remote sensing data, including Gaofen-2 (GF-2), Landsat-8 OLI, declassified GAMBIT imagery, and Google Earth, combined with deep learning techniques, to conduct a comprehensive archaeological investigation of the XITs’ burial landscape. We performed geomorphological analysis of the surrounding environment and automated identification and mapping of burial mounds and mausoleum features using YOLOv5, complemented by manual interpretation of very-high-resolution (VHR) satellite imagery. Spectral indices and image fusion techniques were applied to enhance the detection of archaeological features. Our findings demonstrated the efficacy of this combined methodology for archaeology prospect, providing valuable insights into the spatial layout, geomantic considerations, and preservation status of the XITs. Notably, the analysis of declassified GAMBIT imagery facilitated the identification of a suspected true location for the ninth imperial tomb (M9), a significant contribution to understanding Xixia history through remote sensing archaeology. This research provides a replicable framework for the detection and preservation of archaeological sites using readily available satellite data, underscoring the power of advanced remote sensing and machine learning in heritage studies. Full article

Urban forests play a crucial role in enhancing vegetation cover and bolstering the ecological functions of cities by expanding green space, improving ecological connectivity, and reducing landscape fragmentation. This study examines these dynamics in Jinhua City, China, utilizing Landsat 8 satellite imagery for all four seasons of 2023, accessed through the Google Earth Engine (GEE) platform. Fractional vegetation cover (FVC) was calculated using the pixel binary model, followed by the classification of FVC levels. To understand the influence of landscape structure, nine representative landscape metrics were selected to construct a landscape index system. Pearson correlation analysis was employed to explore the relationships between these indices and seasonal FVC variations. Furthermore, the contribution of each index to seasonal FVC was quantified using a random forest (RF) regression model. The results indicate that (1) Jinhua exhibits the highest average FVC during the summer, reaching 0.67, while the lowest value is observed in winter, at 0.49. The proportion of areas with very high coverage peaks in summer, accounting for 50.6% of the total area; (2) all landscape metrics exhibited significant correlations with seasonal FVC. Among them, the class area (CA), percentage of landscape (PLAND), largest patch index (LPI), and patch cohesion index (COHESION) showed strong positive correlations with FVC, whereas the total edge length (TE), landscape shape index (LSI), patch density (PD), edge density (ED), and area-weighted mean shape index (AWMSI) were negatively correlated with FVC; (3) RF regression analysis revealed that CA and PLAND contributed most substantially to FVC, followed by COHESION and LPI, while PD, AWMSI, LSI, TE, and ED demonstrated relatively lower contributions. These findings provide valuable insights for optimizing urban forest landscape design and enhancing urban vegetation cover, underscoring that increasing large, interconnected forest patches represents an effective strategy for improving FVC in urban environments. Full article

Indonesia faces significant challenges in meeting food security targets due to rapid agricultural land loss, with approximately 1.22 million hectares of rice fields converted between 1990 and 2022. Therefore, this study developed a prediction model for the loss of rice fields by 2030, incorporating land productivity attributes, specifically rice cropping intensity/RCI, using geospatial technology—a novel method with a resolution of approximately 10 m for quantifying ecosystem service (ES) impacts. Land use/land cover data from Landsat images (2013, 2020, 2024) were classified using the Random Forest algorithm on Google Earth Engine. The prediction model was developed using a Multi-Layer Perceptron Neural Network and Markov Cellular Automata (MLP-NN Markov-CA) algorithms. Additionally, time series Sentinel-1A satellite imagery was processed using K-means and a hierarchical clustering analysis to map rice fields and their RCI. The validation process confirmed high model robustness, with an MLP-NN Markov-CA accuracy and Kappa coefficient of 83.90% and 0.91, respectively. The present study, which was conducted in Indramayu Regency (West Java), predicted that 1602.73 hectares of paddy fields would be lost within 2020–2030, specifically 980.54 hectares (61.18%) and 622.19 hectares (38.82%) with 2 RCI and 1 RCI, respectively. This land conversion directly threatens ES, resulting in a projected loss of 83,697.95 tons of rice production, which indicates a critical degradation of service provisioning. The findings provide actionable insights for land use planning to reduce agricultural land conversion while outlining the urgency of safeguarding ES values. The adopted method is applicable to regions with similar characteristics. Full article

The use of Google Earth Engine (GEE), a cloud-based computing platform, in spatio-temporal evaluation studies has increased rapidly in natural sciences such as forestry. In this study, Sentinel-2 satellite imagery and Shuttle Radar Topography Mission (SRTM) elevation data and image classification algorithms based on two machine learning techniques were examined. Random Forest (RF) and Classification and Regression Trees (CART) were used to classify land use and land cover (LULC) in western Oregon (USA). To classify the LULC from the spectral bands of satellite images, a composition consisting of vegetation difference indices NDVI, NDWI, EVI, and BSI, and a digital elevation model (DEM) were used. The study area was selected due to a diversity of land cover types including research forest, botanical gardens, recreation area, and agricultural lands covered with diverse plant species. Five land classes (forest, agriculture, soil, water, and settlement) were delineated for LULC classification testing. Different spatial points (totaling 75, 150, 300, and 2500) were used as training and test data. The most successful model performance was RF, with an accuracy of 98% and a kappa value of 0.97, while the accuracy and kappa values for CART were 95% and 0.94, respectively. The accuracy of the generated LULC maps was evaluated using 500 independent reference points, in addition to the training and testing datasets. Based on this assessment, the RF classifier that included elevation data achieved an overall accuracy of 92% and a kappa coefficient of 0.90. The combination of vegetation difference indices with elevation data was successful in determining the areas where clear-cutting occurred in the forest. Our results present a promising technique for the detection of forests and forest openings, which was helpful in identifying clear-cut sites. In addition, the GEE and RF classifier can help identify and map storm damage, wind damage, insect defoliation, fire, and management activities in forest areas. Full article

Mangrove ecosystems are crucial coastal habitats that support life and regulate the Earth’s atmosphere. However, these ecosystems face prominent threats due to anthropogenic activities and environmental constraints. For instance, the Saudi Arabian coast is particularly vulnerable to species extinction and biodiversity loss due to the fragility of the ecosystem; this highlights the need to understand the spatial and temporal dynamics of mangrove forests in desert environments. Hence, this is the first national study to quantify mangrove forests and analyze at-risk zone-based land use along Saudi Arabian coasts over 40 years. Thus, the primary contents of this research were (1) to produce a new long-term dataset covering the entire Saudi coastline, (2) to identify the patterns, analyze the trends, and quantify the change of mangrove areas, and (3) to determine vulnerability zoning of mangrove area-based land use and transportation networks. This study used Landsat satellite imagery via Google Earth Engine for national-scale mangrove mapping of Saudi Arabia between 1985 and 2024. Visible and infrared bands and seven spectral indices were employed as input features for the random forest classifier. The two classes used were mangrove and non-mangrove; the latter class included non-mangrove land-use and land-cover areas. Then, the study employed the output mangrove mapping to delineate vulnerable mangrove forest-based land use. The overall results showed a substantial increase in mangrove areas, ranging from 27.74 to 59.31 km² in the Red Sea and from 1.05 to 8.65 km² in the Arabian Gulf between 1985 and 2024, respectively. However, within this decadal trend, there were noticeable periods of decline. The spatial coverage of mangroves was larger on Saudi Arabia’s western coasts, especially the southwestern coasts, than on its eastern coasts. The overall accuracy, conducted annually, ranged between 91.00% and 98.50%. The results also show that expanding land uses and transportation networks within at-risk zones of mangrove forests may have a high potential effect. This study aimed to benefit the government, conservation agencies, coastal planners, and policymakers concerned with the preservation of mangrove habitats. Full article

Accurate localization of buried water pipelines in rural areas is crucial for maintenance and leak management but is often hindered by outdated maps and the limitations of traditional geophysical methods. This study aimed to develop and validate a multi-source remote-sensing workflow, integrating UAV (unmanned aerial vehicle)-borne near-infrared (NIR) surveys, multi-temporal Sentinel-2 imagery, and historical Google Earth orthophotos to precisely map pipeline locations and establish a surface baseline for future monitoring. Each dataset was processed within a unified least-squares framework to delineate pipeline axes from surface anomalies (vegetation stress, soil discoloration, and proxies) and rigorously quantify positional uncertainty, with findings validated against RTK-GNSS (Real-Time Kinematic—Global Navigation Satellite System) surveys of an excavated trench. The combined approach yielded sub-meter accuracy (±0.3 m) with UAV data, meter-scale precision (≈±1 m) with Google Earth, and precision up to several meters (±13.0 m) with Sentinel-2, significantly improving upon inaccurate legacy maps (up to a 300 m divergence) and successfully guiding excavation to locate a pipeline segment. The methodology demonstrated seasonal variability in detection capabilities, with optimal UAV-based identification occurring during early-vegetation growth phases (NDVI, Normalized Difference Vegetation Index ≈ 0.30–0.45) and post-harvest periods. A Sentinel-2 analysis of 221 cloud-free scenes revealed persistent soil discoloration patterns spanning 15–30 m in width, while Google Earth historical imagery provided crucial bridging data with intermediate spatial and temporal resolution. Ground-truth validation confirmed the pipeline location within 0.4 m of the Google Earth-derived position. This integrated, cost-effective workflow provides a transferable methodology for enhanced pipeline mapping and establishes a vital baseline of surface signatures, enabling more effective future monitoring and proactive maintenance to detect leaks or structural failures. This methodology is particularly valuable for water utility companies, municipal infrastructure managers, consulting engineers specializing in buried utilities, and remote-sensing practitioners working in pipeline detection and monitoring applications. Full article

The accurate prediction of water quality parameters is essential for effective pollution control and resource management. This study presents a hybrid AI-remote sensing framework for forecasting water quality in the Gulf of Thailand, which combines Sentinel-2 imagery with Support Vector Machine (SVM) and Autoregressive Integrated Moving Average (ARIMA) models. Our approach achieves a 5.4× increase in data coverage over traditional methods, demonstrating the effectiveness of machine learning in environmental monitoring. Predictive accuracy was evaluated across Support Vector Machine (SVM), ARIMA, and Amazon Forecast models. Results indicate that SVM, optimised through RBF kernel and grid search, outperforms other models for Chlorophyll-a (RMSE: 1.8), while ARIMA exhibits superior performance for Secchi Depth (RMSE: 0.2) and Trophic State Index (RMSE: 0.8). The study also introduces Aqua Sight, a web-based visualisation tool built on Google Earth Engine, enabling stakeholders to access real-time water quality forecasts. These findings highlight the potential of integrating satellite-derived data with machine learning to enhance early warning systems and support environmental decision making in coastal ecosystems. Full article