Search Results (2,063)

Timely and accurate monitoring of lakes’ water quality is crucial for assessing regional ecological health and implementing targeted conservation activities. Compared with traditional in situ water quality measurement methods, satellite remote sensing technology is more cost-effective and convenient, and also enables long-term time-series monitoring. This study utilizes Sentinel-2 multispectral imagery, selects East Juyan Lake as the study area, and employs measured water quality data from 30 in situ sampling points as training and testing samples. Using the correlation coefficient, root mean square error, and mean absolute error as evaluation metrics, a Grid Search-based XGBoost machine-learning method is applied to invert the concentration of total phosphorus (TP), a key parameter for water quality assessment. The experiments demonstrate that: (1) The XGBoost model, after parameter tuning via Grid Search, achieved the highest inversion accuracy, with R², RMSE, and MRE values of 0.856, 0.017, and 7.20%, respectively; The average TP concentration retrieved for the lake was 0.231 mg/L. This method requires minimal manual setting of numerous training parameters, reducing human intervention. (2) The spatial distribution shows that TP is primarily enriched in the deeper central and eastern parts of the lake, while concentrations are relatively lower in the near-shore vegetation zones and the western shallow water areas. The findings provide a significant reference for remote sensing monitoring of lake water quality and can be used to predict and regulate salinity, eutrophication, and similar conditions in comparable lakes. Full article

Arundo donax L. (common reed), a highly invasive species in Mediterranean wetlands such as the Albufera Natural Park, poses significant ecological and management challenges. Using Landsat-5 and Sentinel-2 NDVI data, this study quantified changes in its coverage between 1996 and 2024. The results reveal a significant expansion, showing a decreasing trend (91.4 ha in 1996 to 62.5 ha in 2011; −31.6%) followed by a clear rebound (83.5 ha in 2024; +33.6%), especially in the southern shrublands of the lagoon. A Mann–Kendall analysis confirmed a significant decreasing trend during 1996–2011 and an increasing trend during 2011–2024 (p < 0.05). The results indicate that previous control efforts reduced A. donax cover but that the species has recolonised after 2011, likely due to discontinuous management. These dynamics emphasise that long-term monitoring is required. Management strategies must focus on targeting the rhizome and implementing long-term monitoring programmes spanning three to five years. The utilisation of remote sensing methodologies proved effective in the monitoring of coverage, thereby facilitating the development of remediation strategies. It is imperative that actions accord primacy to critical areas such as the south and canals, complemented by native restoration and enhanced inter-administrative coordination, with the communication of benefits such as flood risk reduction. A balanced approach is required that considers ecological objectives, risks, and socio-political aspects. Full article

Traffic safety is a critical issue in highway operation management, where accurate identification of accident hotspots enables proactive risk prevention and facility optimization. Traditional methods relying on historical statistics often fail to capture macro-level environmental patterns and micro-level dynamic variations. To address this challenge, we propose a Dual-Branch Feature Adaptive Gated Fusion Network (DFAGF-Net) that integrates satellite remote sensing imagery with traffic flow time-series data. The framework consists of three components: the Global Contextual Aggregation Network (GCA-Net) for capturing macro spatial layouts from remote sensing imagery, a Sequential Gated Recurrent Unit Attention Network (Seq-GRUAttNet) for modeling dynamic traffic flow with temporal attention, and a Hybrid Feature Adaptive Module (HFA-Module) for adaptive cross-modal feature fusion. Experimental results demonstrate that the DFAGF-Net achieves superior performance in accident hotspot recognition. Specifically, GCA-Net achieves an accuracy of 84.59% on satellite imagery, while Seq-GRUAttNet achieves an accuracy of 82.51% on traffic flow data. With the incorporation of the HFA-Module, the overall performance is further improved, reaching an accuracy of 90.21% and an F1-score of 0.92, which is significantly better than traditional concatenation or additive fusion methods. Ablation studies confirm the effectiveness of each component, while comparisons with state-of-the-art models demonstrate superior classification accuracy and generalization. Furthermore, model interpretability analysis reveals that curved highway alignments, roadside greenery, and varying traffic conditions across time are major contributors to accident hotspot formation. By accurately locating high-risk segments, DFAGF-Net provides valuable decision support for proactive traffic safety management and targeted infrastructure optimization. Full article

Accurate forest type classification in subtropical regions is essential for ecological monitoring and sustainable management. Multimodal remote sensing data provide rich information support, yet the synergy between network architectures and fusion strategies in deep learning models remains insufficiently explored. This study established a multimodal deep learning framework with integrated interpretability analysis by combining high-resolution Beijing-2 RGB imagery, Sentinel-1 data, and time-series Sentinel-2 NDVI data. Two representative architectures (U-Net and Swin-UNet) were systematically combined with three fusion strategies, including feature concatenation (Concat), gated multimodal fusion (GMU), and Squeeze-and-Excitation (SE). To quantify feature contributions and decision patterns, three complementary interpretability methods were also employed: Shapley Additive Explanations (SHAP), Grad-CAM++, and occlusion sensitivity. Results show that Swin-UNet consistently outperformed U-Net. The SwinUNet-SE model achieved the highest overall accuracy (OA) of 82.76%, exceeding the best U-Net model by 3.34%, with the largest improvement of 5.8% for mixed forest classification. The effectiveness of fusion strategies depended strongly on architecture. In U-Net, SE and Concat improved OA by 0.91% and 0.23% compared with the RGB baseline, while GMU slightly declined. In Swin-UNet, all strategies achieved higher gains between 1.03% and 2.17%, and SE effectively reduced NDVI sensitivity. SHAP analysis showed that RGB features contributed most (values > 0.0015), NDVI features from winter and spring ranked among the top 50%, and Sentinel-1 features contributed less. These findings reveal how architecture and fusion design interact to enhance multimodal forest classification. Full article

Mangrove ecosystems play a critical role in global carbon cycling, serving as significant carbon sinks by storing carbon in both aboveground biomass (ACG) and soil carbon stock (SOC). However, the temporal dynamics of ACG and SOC, as well as their spatial variations across different mangrove age stages, remain poorly understood, particularly under the influence of introduced species such as Sonneratia apetala Buch.-Ham. To address these gaps, our study used a long-term series of NDVI from Landsat (from 1990 to 2024) and the mangrove product of China (1990, 2000, 2010, and 2018) to estimate the mangrove age stage ($\mathrm{Stage}\mathrm{I}$ 10–24 years, $\mathrm{Stage}\mathrm{II}$ 24–34 years, and $\mathrm{Stage}\mathrm{III}$ > 34 years). UAV-LiDAR and in-situ surveys were applied to measure mangrove canopy height to calculate ACG and measure the belowground soil carbon stock, respectively. Combined with the mangrove age stage, ACG, and SOC, our results reveal that ACG accumulates rapidly in younger mangroves dominated by Sonneratia apetala, peaking early (<20 years) and then stabilizing as mangroves, indicating that the introduction of Sonneratia apetala changed the increase in ACG with age. In contrast, SOC increases more gradually over time, with only older mangroves (over 30 years) storing significantly higher SOC. Root structure, TN, and TP were sensitive to the SOC. The different root structures (pneumatophore, plank, pop, and knee root) had different SOC results, and the pneumatophore had the lowest SOC. Remote sensing data revealed that the introduction of Sonneratia apetala altered the species composition of younger mangroves, leading to its predominance within these ecosystems. This shift in species composition not only altered the temporal dynamics of aboveground carbon (ACG) but also favored pneumatophore-dominated root structures, which were associated with the lowest soil organic carbon (SOC). Consequently, younger stands may require more time to accumulate SOC to levels comparable to older mangrove forests. These results suggest that restoration targets for vegetation carbon and soil carbon should be set on different timelines, explicitly accounting for stand age, species composition, and root functional types. Full article

Remote sensing of tidal flats and their dynamic changes is essential for understanding and conserving intertidal ecosystems. As a highly dynamic land cover type influenced by tidal variations, tidal flats present challenges for consistent long-term monitoring. The tidal flat area may be inflated in long-term remote sensing datasets due to the increasing observation frequency in recent decades. Although significant progress has been made in time-series mapping of tidal flats using Landsat imagery, the relationship between tidal flat dynamics and satellite observation frequency remains poorly understood. In this study, we aimed to quantify the impact of increased Landsat observations on long-term time series of tidal flat area changes using two widely used global tidal flat products (GTF30 and Murray’s product). Specifically, we first used a regression analysis to investigate the relationship between observation frequency, tide level, and tidal flat area; the result revealed that higher observation frequency is more likely to capture lower tides and thus detect larger tidal flat areas. Next, we developed a weighted statistical regression method to quantify the influence of observation frequency on the mapped tidal flat area at the selected 45 tidal stations. Our analysis indicates that both products exhibit significant inflated increases due to the increased observation frequency during 2000–2022. Specifically, the GTF30 product shows a spurious increase of 12.83 ± 6.51 km² attributable to the increased observation frequency, accounting for 17.57% of the total observed change. Similarly, the Murray product also exhibits a spurious increase of 13.92 ± 7.45 km², which is approximately 1.95 times the mapped change in tidal flat area. Therefore, this study emphasizes the presence of substantial inflation effects in long-term tidal flat remote sensing datasets caused by the increasing observation frequency. Quantifying this bias is essential for accurate interpretation of the long-term tidal flat dynamics and ecological assessments. 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

The process of reservoir impoundment poses a significant threat to the stability of reservoir bank slopes, potentially triggering new landslides or reactivating ancient ones. Consequently, long-term and stable monitoring of surface deformation in reservoir areas is essential for ensuring safe reservoir operation. SBAS-InSAR technology—characterized by its high precision, multi-temporal capability, and wide spatial coverage—offers an effective means of comprehensively characterizing landslide deformation in such environments. In this study, SBAS-InSAR is applied to monitor landslides in the Xiluodu Reservoir area using Sentinel-1A imagery. Ascending and descending orbit data are jointly inverted to reconstruct the two-dimensional (2D) surface deformation time series. The deformation patterns and their spatiotemporal evolution are analyzed in conjunction with remote sensing imagery, topographic and geological data, and reservoir water level fluctuations. The integrated analysis identifies 10 and 12 significant deformation zones in the vertical and east–west directions, respectively—demonstrating improved detection accuracy compared to single-orbit approaches. Two representative landslides, the Mixiluo and Huanghua landslides, are selected for detailed investigation. Their toe deformation exhibits a pronounced response to both rainfall and reservoir water level variations. These findings provide valuable reference data and technical support for the early identification of reservoir bank landslides and the safe operation of reservoirs in this and similar engineering contexts. Full article

This study employs an integrated framework that combines field-based measurements, remote sensing, and Geographic Information Systems (GISs) to monitor vegetation dynamics and assess the suitability of a steppe range reserve for livestock grazing. Forty-three surface and subsurface soil samples were collected in April and November 2021 to capture seasonal variations. Above-ground biomass (AGB) measurements were recorded at five sampling locations across the reserve. Six Sentinel-2 satellite imageries, acquired around mid-March 2016–2021, were processed to derive time-series Normalized Difference Vegetation Index (NDVI) data, capturing temporal shifts in vegetation cover and density. The GIS-based Multi-Criteria Decision Analysis (MCDA) was employed to model the suitability of the reserve for livestock grazing. The results showed higher salinity, total dissolved solids (TDSs), and nitrate (NO₃) values in April. However, the percentage of organic matter increased from approximately 7% in April to over 15% in November. The dry forage productivity ranged from 111 to 964 kg/ha/year. On average, the reserve’s dry yield was 395 kg/ha/year, suggesting moderate productivity typical of steppe rangelands in this region. The time-series NDVI analyses showed significant fluctuations in vegetation cover, with lower NDVI values prevailing in 2016 and 2018, and higher values estimated in 2019 and 2020. The grazing suitability analysis showed that 13.8% of the range reserve was highly suitable, while 24.4% was moderately suitable. These findings underscore the importance of tailoring grazing practices to enhance forage availability and ecological resilience in steppe rangelands. By integrating satellite-derived metrics with in situ vegetation and soil measurements, this study provides a replicable methodological framework for assessing and monitoring rangelands in semi-arid regions. Full article

Pasture systems, typically composed of grasses, legumes, and forage crops, are vital livestock nutrition sources. The quality of these pastures depends on various factors, including species composition and growth stage, which directly impact livestock productivity. Remote sensing (RS) technologies offer powerful, non-invasive means for large-scale pasture monitoring and classification, enabling efficient assessment of pasture health across extensive areas. However, traditional supervised classification methods require labelled datasets that are often expensive and labour-intensive to produce, especially over large grasslands. This study explores unsupervised clustering as a cost-effective alternative for identifying pasture types without the need for labelled data. Leveraging spatiotemporal data from the Sentinel-2 mission, we propose a clustering framework that classifies pastures based on their temporal growth dynamics. For this, the pasture segments are first created with quick-shift segmentation, and spectral time series for each segment are grouped into clusters using time-series distance-based clustering techniques. Empirical analysis shows that the dynamic time warping (DTW) distance measure, combined with K-Medoids and hierarchical clustering, delivers promising pasture mapping with normalised mutual information (NMI) of 86.28% and 88.02% for site-1 and site-2 (total area of approx. 2510 ha), respectively, in New South Wales, Australia. This approach offers practical insights for improving pasture management and presents a viable solution for categorising pasture and grazing systems across landscapes. Full article

As an important part of the urban ecological environment, urban green space plays a crucial and irreplaceable role in improving air quality, promoting sustainable development, and enhancing residents’ quality of life. This study takes Beijing’s urban green space as the research object. Based on Landsat series satellite remote sensing images, the land use distribution of Beijing is obtained through supervised classification. Combined with data such as PM_2.5 concentration and wind speed, the dry deposition efficiency of PM_2.5 is quantitatively analyzed. The results show that: (1) Beijing’s urban green space has significant advantages in PM_2.5 dry deposition. In terms of dry deposition flux, the order of annual average deposition of different land types is: forest land > farm land > grassland > impervious surface > water body = unutilized land. Among them, forest land has the best dry deposition effect, with an annual average dry deposition of 1.13 g/m², which is 188.41 times that of impervious surface; cultivated land and grassland are 0.22 g/m² and 0.19 g/m² respectively, which are 37.13 times and 32.34 times that of impervious surface. (2) From 2000 to 2020, the PM_2.5 removal rate of green space continued to rise, but the reduction amount showed a trend of first increasing and then decreasing. There are significant seasonal differences. The reduction amount is the highest in autumn (reaching 449.90 tons in October), followed by summer, spring, and winter (the lowest in August, at 190.27 tons). (3) In terms of spatial distribution, the high-value areas of dry deposition are concentrated in the suburbs, showing a “southwest-northeast” axial distribution, while the low-value areas are mainly located in the outer suburbs, reflecting the imbalance of green space layout and the regional differences in PM_2.5 reduction. Combined with the current situation of green space in Beijing, the study puts forward targeted optimization suggestions, providing theoretical support and scientific basis for the construction of Beijing as a “garden city”. Full article

As carbon cycling and global environmental protection gain increasing attention, forest disturbance research has intensified worldwide. Constrained by limited data availability, existing frameworks often rely on extracting individual spectral bands for simple binary disturbance detection, lacking systematic approaches to visualize and classify causes of disturbance over large areas. Accurately identifying disturbance types is critical because different disturbances (e.g., fires, logging, pests) exhibit vastly different impacts on forest structure, successional pathways and, consequently, forest carbon sequestration and storage capacities. This study proposes an integrated remote sensing and deep learning (DL) method for forest disturbance type identification, enabling high-precision monitoring in Northeast China from 1992 to 2023. Leveraging the Google Earth Engine platform, we integrated Landsat time-series data (30 m resolution), Global Forest Change data, and other multi-source datasets. We extracted four key vegetation indices (NDVI, EVI, NBR, NDMI) to construct long-term forest disturbance feature series. A comparative analysis showed that the proposed convolutional neural network (CNN) model with six feature bands achieved 5.16% higher overall accuracy and a 6.92% higher Kappa coefficient than a random forest (RF) algorithm. Remarkably, even with only six features, the CNN model outperformed the RF model trained on fifteen features, achieving a 0.4% higher overall accuracy and a 0.58% higher Kappa coefficient, while utilizing 60% fewer parameters. The CNN model accurately classified forest disturbances—including fires, pests, logging, and geological disasters—achieving a 92.26% overall accuracy and an 89.04% Kappa coefficient. This surpasses the 81.4% accuracy of the Global Forest Change product. The method significantly improves the spatiotemporal accuracy of regional-scale forest monitoring, offering a robust framework for tracking ecosystem dynamics. Full article

The motivation behind this research is the fact that agricultural production in Bulgaria is a key contributor to the national economy. The current study presents a robust methodology for predicting crop yields using multitemporal Sentinel-2 satellite imagery, public agricultural statistics, and climate data in Bulgaria. Focusing on the municipalities of Medkovets, Yakimovo, and Knezha—regions with over 90% arable land—we conducted time-series analyses of the NDVI, EVI, and GCI for the 2023 and 2024 growing seasons. These indices were used to derive statistical features, which were then combined with ERA5-based climate variables and public yield records from the State Agricultural Fund. A Random Forest regression model was trained on 2023 and 2024 data and used to simulate predictions for 2025. The model achieved an R² of 0.78 and an RMSE of 1.24 t/ha, indicating good agreement between predicted and observed yields despite the relatively small dataset. The preliminary results reveal the importance of the EVI and NDVI as indicators of crop productivity and demonstrate variations in vegetation development between years. The findings highlight the potential of remote sensing and open data integration for regional yield forecasting while also identifying areas for future improvement, including dataset expansion and the use of ground-truth yields. Full article

Accurate precipitation forecasting plays a crucial role in sustainable water resource management, especially in arid regions like Konya, one of Turkey’s driest areas. Reliable forecasts support effective water budgeting, agricultural planning, and climate adaptation efforts in the region. This study investigates the performance of different deep learning training algorithms in forecasting monthly precipitation using Long Short-Term Memory (LSTM) networks, a method tailored for time-series prediction. A comprehensive dataset comprising 39 years (1984–2022) of precipitation records was utilized, obtained from the Turkish State Meteorological Service (MGM) as ground-based observations and from NASA’s POWER database as remote sensing data, and was split into 80% for training and 20% for testing. A comparative analysis of three widely used optimization algorithms, Adaptive Moment Estimation (ADAM), Root Mean Square Propagation (RMSProp), and Stochastic Gradient Descent with Momentum (SGDM), revealed that ADAM consistently outperformed the others in forecasting accuracy. Model performance was evaluated with statistical metrics, and the LSTM-ADAM combination achieved the best results. In the final phase, cross-validation was applied using MGM and NASA data sources in a crosswise manner to test model generalizability and data source independence. The best performance was observed when the model was trained with MGM data and tested with NASA data, achieving a remarkably low RMSE of 3.62 mm, MAE of 2.93 mm, R² of 0.9966, and NSE of 0.9686. When trained with NASA data and tested with MGM data, the model still demonstrated strong performance, with an RMSE of 4.48 mm, MAE of 3.22 mm, R² of 0.9921, and NSE of 0.9678. These results demonstrate that satellite and ground-based data can be used interchangeably under suitable conditions, while also confirming the superiority of the ADAM optimizer in LSTM-based precipitation forecasting. Full article

This study presents an analysis of regional sea level variability on various seafloor structures. The main aim of this paper was to determine the regional trends of sea level changes (time span of 29 years) in the area of the ocean trench and submarine canyon, in the area of seamounts and corrugations, and then to compare the models of the seafloor with the models of the sea surface. We used hybrid datasets, including satellite altimetric time series, multibeam bathymetric soundings, GEBCO products, free-air gravity anomaly models, and mean dynamic ocean topography models. Radar remote sensing and spaceborne radar technologies are essential in capturing the long-term dynamics of sea surface variability regarding seafloor topography. The values of regional sea level change trends in the seamounts and corrugation region are two times higher (from 2.56 ± 0.10 mm/year to 7.66 ± 0.18 mm/year) than in the trench and canyon region (1.75 ± 0.01 mm/year to 3.65 ± 0.07 mm/year). In the region of trench and canyon, i.e., on narrow and deep forms of the seafloor, the values of regional trends are stable and regular. In the region of seamounts and corrugations, where the depth is more diverse, regional trend values are higher and irregular. Study results show that regional sea level fluctuations can be the consequence of the diversified structure of the seafloor. The region of the trench and canyon, although characterized by high susceptibility to climatic phenomena, presents lower amplitudes of sea level changes than the subregion of seamounts and corrugations, where the bathymetry of the seafloor is more complex. Full article