Search Results (709)

Leaf area index (LAI) serves as a crucial indicator for characterizing the growth and development process of maize. However, the LAI inversion of maize based on unmanned aerial vehicles (UAVs) is highly susceptible to various factors such as weather conditions, light intensity, and sensor performance. In contrast to satellites, the spectral stability of UAV-based data is relatively inferior, and the phenomenon of “spectral fragmentation” is prone to occur during large-scale monitoring. This study was designed to solve the problem that maize LAI inversion based on UAVs is difficult to achieve both high spatial resolution and spectral consistency. A two-stage remote sensing data fusion method integrating coarse and fine fusion was proposed. The SHapley Additive exPlanations (SHAP) model was introduced to investigate the contributions of 20 features in 7 categories to LAI inversion of maize, and canopy temperature extracted from thermal infrared images was one of them. Additionally, the most suitable feature sampling window was determined through multi-scale sampling experiments. The grid search method was used to optimize the hyperparameters of models such as Gradient Boosting, XGBoost, and Random Forest, and their accuracy was compared. The results showed that, by utilizing a 3 × 3 feature sampling window and 9 features with the highest contributions, the LAI inversion accuracy of the whole growth stage based on Random Forest could reach R² = 0.90 and RMSE = 0.38 m²/m². Compared with the single UAV data source mode, the inversion accuracy was enhanced by nearly 25%. The R² in the jointing, tasseling, and filling stages were 0.87, 0.86, and 0.62, respectively. Moreover, this study verified the significant role of thermal infrared data in LAI inversion, providing a new method for fine LAI inversion of maize. Full article

Landslide susceptibility evaluation is an indispensable part of disaster prevention and mitigation work. Selecting effective evaluation methods and models for landslide susceptibility assessment is of significant importance. This study focuses on selected areas in Yunyang County, Chongqing City. By interpreting high-resolution satellite remote sensing images from before and after heavy rainfall on 31 August 2014, the distribution of rainfall-induced accumulation landslides was obtained. To evaluate the susceptibility of accumulation landslides, we have equated evaluation factors to accumulation distribution prediction factors. Eight evaluation factors were extracted using multi-source data, including lithology, elevation, slope, remote sensing image texture features, and the normalized difference vegetation index (NDVI). Various machine learning models, such as Random Forest (RF), Support Vector Machine (SVM), and BP Neural Network models, were employed to assess the susceptibility of rainfall-induced accumulation landslides in the study area. Subsequently, the accuracy of the evaluation models was compared and verified using the Receiver Operating Characteristic (ROC) curve, and the evaluation results were analyzed. Finally, the developed Random Forest model was applied to Gongping Town in Fengjie County to verify its applicability in other regions. The findings indicate that the complex geological conditions and the unique tectonic erosion landform patterns in the northeastern region of Chongqing not only make this area a center of heavy rainfall but also lead to frequent and recurrent rainfall-induced landslides. The Random Forest model effectively reflects the development characteristics of accumulation landslides in the study area. High and very high susceptibility zones are concentrated in the northern and central regions of the study area, while low and moderate susceptibility zones predominantly occupy the mountainous and riverside areas. Landslide susceptibility mapping in the study area shows that the Random Forest model yields reasonably graded results. Elevation, remote sensing image texture features, and lithology are highly significant factors in the evaluation system, indicating that the development factors of slope geological disasters in the study area are mainly related to topography, geomorphology, and lithology. The landslide susceptibility evaluation results in Gongping Town, Fengjie County, validate the applicability of the Random Forest model developed in this study to other regions. Full article

The European Ground Motion Service (EGMS) and geospatial data are integrated in this paper to evaluate ground deformation and its effects on critical infrastructures in the Preveza Regional Unit. The EGMS, a new service of the Copernicus Land Monitoring Service, employs information from the C-band Synthetic Aperture Radar (SAR)-equipped Sentinel-1A and Sentinel-1B satellites. This allows for the millimeter-scale measurement of ground motion, which is essential for assessing anthropogenic and natural hazards. The study examines ground displacement from 2018 to 2022 using multi-temporal Synthetic Aperture Radar Interferometry (MTInSAR). The Regional Unit of Preveza was selected for study area. According to the investigation, the area’s East–West Mean Velocity Displacement varies between 22.5 mm/y and −37.7 mm/y, while the Vertical Mean Velocity Displacement ranges from 16 mm/y to −39.3 mm/y. Persistent Scatterers (PSs) and Distributed Scatterers are the sources of these measurements. This research focuses on assessing the impact of ground deformation on 21 school units, 2 health centers, 1 hospital, 4 bridges and 1 dam. The findings provide valuable insights for local authorities and other stakeholders, who will greatly benefit from the information gathered from this study, which will lay the groundwork for wise decision-making and the creation of practical plans to strengthen the resistance of critical infrastructures to ground motion. Full article

Addressing global warming and adapting to the impacts of climate change is a primary focus of climate change adaptation strategies at both European and national levels. Land surface temperature (LST) is a widely used proxy for investigating climate-change-induced phenomena, providing insights into the surface radiative properties of different land cover types and the impact of urbanization on local climate characteristics. Accurate and continuous estimation across large spatial regions is crucial for the implementation of LST as an essential parameter in climate change mitigation strategies. Here, we propose a deep-learning-based methodology for LST estimation using multi-source data including Sentinel-2 imagery, land cover, and meteorological data. Our approach addresses common challenges in satellite-derived LST data, such as gaps caused by cloud cover, image border limitations, grid-pattern sensor artifacts, and temporal discontinuities due to infrequent sensor overpasses. We develop a regression-based convolutional neural network model, trained on ECOSTRESS (ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station) mission data, which performs pixelwise LST predictions using 5 × 5 image patches, capturing contextual information around each pixel. This method not only preserves ECOSTRESS’s native resolution but also fills data gaps and enhances spatial and temporal coverage. In non-gap areas validated against ground truth ECOSTRESS data, the model achieves LST predictions with at least 80% of all pixel errors falling within a ±3 °C range. Unlike traditional satellite-based techniques, our model leverages high-temporal-resolution meteorological data to capture diurnal variations, allowing for more robust LST predictions across different regions and time periods. The model’s performance demonstrates the potential for integrating LST into urban planning, climate resilience strategies, and near-real-time heat stress monitoring, providing a valuable resource to assess and visualize the impact of urban development and land use and land cover changes. Full article

The geostationary meteorological satellite Fengyun-4A (FY-4A) has rapidly advanced, generating abundant high spatiotemporal resolution atmospheric precipitable water vapor (PWV) products. However, remote sensing satellites are vulnerable to weather conditions, and these latest operational PWV products still require systematic validation. This study presents a comprehensive evaluation of FY-4A PWV products by separately using PWV data retrieved from radiosondes (RS) and the Global Navigation Satellite System (GNSS) from 2019 to 2022 in China and the surrounding regions. The overall results indicate a significant consistency between FY-4A PWV and RS PWV as well as GNSS PWV, with mean biases of 7.21 mm and −8.85 mm, and root mean square errors (RMSEs) of 7.03 mm and 3.76 mm, respectively. In terms of spatial variability, the significant differences in mean bias and RMSE were 6.50 mm and 2.60 mm between FY-4A PWV and RS PWV in the northern and southern subregions, respectively, and 5.36 mm and 1.73 mm between FY-4A PWV and GNSS PWV in the northwestern and southern subregions, respectively. The RMSE of FY-4A PWV generally increases with decreasing latitude, and the bias is predominantly negative, indicating an underestimation of water vapor. Regarding temporal differences, both the monthly and daily biases and RMSEs of FY-4A PWV are significantly higher in summer than in winter, with daily precision metrics in summer displaying pronounced peaks and irregular fluctuations. The classic seasonal, regional adjustment model effectively reduced FY-4A PWV deviations across all regions, especially in the NWC subregion with low water vapor distribution. In summary, the accuracy metrics of FY-4A PWV show distinct spatiotemporal variations compared to RS PWV and GNSS PWV, and these variations should be considered to fully realize the potential of multi-source water vapor applications. Full article

Sulfur dioxide (SO₂) can be of natural and anthropogenic origin and is one of the sulfur compounds present in the atmosphere. Among natural sources, volcanoes contribute with relevant annual outputs, and major eruptions lead to spikes in these outputs. In the case of anthropogenic pollution, SO₂ emissions are mostly correlated with the sulfur content of fuels, which has been the focus of specific emission mitigation policies for decades. Following other examples of cyclic and multi-year evaluations, an analysis of SO₂ at the Lamezia Terme (code: LMT) WMO/GAW (World Meteorological Organization—Global Atmosphere Watch) station in Calabria, Southern Italy, was performed. The coastal site is characterized by wind circulation patterns that result in the detection of air masses with low or enhanced anthropic influences. The presence of the Aeolian Arc of active, quiescent, and extinct volcanoes, as well as Mount Etna in Sicily, may influence LMT observations with diffused SO₂ emissions. For the first time in the history of the LMT, a multi-year analysis of a parameter has been integrated with TROPOMI data gathered by Sentinel-5P and used to test total tropospheric column densities at the LMT itself and select coordinates in the Tyrrhenian and Ionian seas. Surface and satellite data indicate that SO₂ peaks at the LMT are generally linked to winds from the western–seaside wind corridor, a pattern that is compatible with active volcanism in the Tyrrhenian Sea and maritime shipping to and from the Gioia Tauro port located in the same region. The findings of this research provide the basis for enhanced source apportionment, which could further differentiate anthropogenic sources in the area from natural outputs. Full article

High-speed railways are critical infrastructure in many countries, but their construction generates substantial spoil, particularly in mountainous regions dominated by tunnels and slopes, necessitating the establishment and monitoring of spoil disposal areas. Inadequate monitoring of spoil disposal areas can lead to significant environmental issues, including soil erosion and geological hazards such as landslides and debris flows, while also hindering the recycling and reuse of construction spoil, thereby impeding the achievement of circular economy and sustainable development goals for high-speed railways. Although the potential of geographic information systems, remote sensing, and global positioning systems in waste monitoring is increasingly recognized, there remains a critical research gap in their application to spoil disposal areas monitoring within high-speed railway projects. This study proposes an innovative framework integrating geographic information systems, remote sensing, and global positioning systems for monitoring spoil disposal areas during high-speed railway construction across three key scenarios: identification of disturbance boundaries (scenario 1), extraction of soil and water conservation measures (scenario 2), and estimation of spoil volume changes (scenario 3). In scenario 1, disturbance boundaries were identified using Gaofen-1 satellite data through processes such as imagery fusion, unsupervised classification, and spatial analysis. In scenario 2, unmanned aerial vehicle data were employed to extract soil and water conservation measures via visual interpretation and overlay analysis. In scenario 3, Sentinel-1 data were used to analyze elevation changes through the differential interferometric synthetic aperture radar method, followed by the estimation of spoil volume changes. The effectiveness of this integrated framework was validated through a case study. The results demonstrate that the framework can accurately delineate disturbance boundaries, efficiently extract soil and water conservation measures, and estimate dynamic changes in spoil volume with an acceptable error margin (15.5%). These findings highlight the framework’s capability to enhance monitoring accuracy and efficiency. By integrating multi-source data, this framework provides robust support for sustainable resource management, reduces the environmental impact, and advances circular economy practices. This study contributes to the efficient utilization of construction spoil and the sustainable development of high-speed railway projects. Full article

Soil salinization affects agricultural productivity and ecosystem health in Xinjiang, especially in arid areas. The region’s complex topography and limited agricultural data emphasize the pressing need for effective, large-scale monitoring technologies. Therefore, 1044 soil samples were collected from arid farmland in northern Xinjiang, and the potential effectiveness of soil salinity monitoring was explored by combining environmental variables with Landsat 8 and Sentinel-2. The study applied four types of feature selection algorithms: Random Forest (RF), Competitive Adaptive Reweighted Sampling (CARS), Uninformative Variable Elimination (UVE), and Successive Projections Algorithm (SPA). These variables are then integrated into various machine learning models—such as Ensemble Tree (ETree), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and LightBoost—as well as deep learning models, including Convolutional Neural Networks (CNN), Residual Networks (ResNet), Multilayer Perceptrons (MLP), and Kolmogorov–Arnold Networks (KAN), for modeling. The results suggest that fertilizer use plays a critical role in soil salinization processes. Notably, the interpretable model KAN achieved an accuracy of 0.75 in correctly classifying the degree of soil salinity. This study highlights the potential of integrating multi-source remote sensing data with deep learning technologies, offering a pathway to large-scale soil salinity monitoring, and thereby providing valuable support for soil management. Full article

The intertidal ecosystem serves as a critical transitional zone between terrestrial and marine environments, supporting diverse biodiversity and essential ecological functions. However, these systems are increasingly threatened by climate change, rising sea levels, and anthropogenic impacts. Accurately mapping intertidal ecosystems and differentiating mangroves, salt marshes, and tidal flats remains a challenge due to inconsistencies in classification frameworks. Here, we present a high-precision mapping approach for intertidal ecosystems using multi-source satellite data, including Sentinel-1, Sentinel-2, and Landsat 8/9, integrated with the Google Earth Engine (GEE) platform, to enable the detailed mapping of intertidal zones across China–ASEAN. Our findings indicate a total intertidal area of 73,461 km² in China–ASEAN, with an average width of 1.16 km. Analyses of patch area, abundance, and perimeter relationships reveal a power-law distribution with a scaling exponent of 1.52, suggesting self-organizing characteristics shaped by both natural and human pressures. Our findings offer foundational data to guide conservation and management strategies in the region’s intertidal zones and present a novel perspective to propel research on global coastal ecosystems. Full article

Remote sensing technologies continue to expand their role in environmental monitoring, providing invaluable advances in soil assessing and mapping. This study aimed to prove the need to apply spatial statistical models for processing data in remote sensing (RS), which appears to be an important source of spatial data at multiple scales. A crucial problem facing us is the fusion of multi-source spatial data of different natures and characteristics, among which there is the support size of measurement that unfortunately is little considered in RS. A data fusion approach of both sample (point) and grid (areal) data is proposed that explicitly takes into account spatial correlation and change of support in both increasing support (upscaling) and decreasing support (downscaling). The techniques of block cokriging and kriging downscaling were employed for the implementation of such an approach, respectively. The method is applied to soil sample data, jointly analysed with hyperspectral data measured in the laboratory, UAV, and satellite data (Planet and Sentinel 2) of an olive grove after filtering soil pixels. Each data type had its own support that was transformed to the same support as the soil sample data so that the data fusion approach could be applied. To demonstrate the statistical, as well as practical, effectiveness of such a method, it was compared by a cross-validation test with a univariate approach for predicting each soil property. The positive results obtained should stimulate advanced statistical techniques to be applied more and more widely to RS data. Full article

Quantifying forest carbon storage to better manage climate change and its effects requires accurate estimation of forest structural parameters such as canopy height. Variables from remote sensing data and machine learning models are tools that are being increasingly used for this purpose. This study modeled the canopy height of forest–savanna mosaics in the Sudano–Guinean zone of Togo. Relative heights were extracted from GEDI and ICESat-2 products, which were combined with optical, radar, and topographic variables for canopy height modeling. We tested four methods: Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN). The RF algorithm obtained the best predictions using 98% relative height (RH98). The best-performing result was obtained from variables extracted from GEDI data (r = 0.84; RMSE = 4.15 m; MAE = 2.36 m) and compared to ICESat-2 (r = 0.65; RMSE = 5.10 m; MAE = 3.80 m). Models that were developed during this study can be applied over large areas in forest–savanna mosaics, enhancing forest dynamics monitoring in line with REDD+ objectives. This study provides valuable insights for future spaceborne LiDAR and other remote sensing data applications in similar complex ecosystems and offers local decision-makers a robust tool for forest management. Full article

Soybean yield prediction is one of the most critical activities for increasing agricultural productivity and ensuring food security. Traditional models often underestimate yields because of limitations associated with single data sources and simplistic model architectures. These prevent complex, multifaceted factors influencing crop growth and yield from being captured. In this line, this work fuses multi-source data—satellite imagery, weather data, and soil properties—through the approach of multi-modal fusion using Convolutional Neural Networks and Recurrent Neural Networks. While satellite imagery provides information on spatial data regarding crop health, weather data provides temporal insights, and the soil properties provide important fertility information. Fusing these heterogeneous data sources embeds an overall understanding of yield-determining factors in the model, decreasing the RMSE by 15% and improving R² by 20% over single-source models. We further push the frontier of feature engineering by using Temporal Convolutional Networks (TCNs) and Graph Convolutional Networks (GCNs) to capture time series trends, geographic and topological information, and pest/disease incidence. TCNs can capture long-range temporal dependencies well, while the GCN model has complex spatial relationships and enhanced the features for making yield predictions. This increases the prediction accuracy by 10% and boosts the F1 score for low-yield area identification by 5%. Additionally, we introduce other improved model architectures: a custom UNet with attention mechanisms, Heterogeneous Graph Neural Networks (HGNNs), and Variational Auto-encoders. The attention mechanism enables more effective spatial feature encoding by focusing on critical image regions, while the HGNN captures interaction patterns that are complex between diverse data types. Finally, VAEs can generate robust feature representation. Such state-of-the-art architectures could then achieve an MAE improvement of 12%, while R² for yield prediction improves by 25%. In this paper, the state of the art in yield prediction has been advanced due to the employment of multi-source data fusion, sophisticated feature engineering, and advanced neural network architectures. This provides a more accurate and reliable soybean yield forecast. Thus, the fusion of Convolutional Neural Networks with Recurrent Neural Networks and Graph Networks enhances the efficiency of the detection process. Full article

Soil salinization is a serious land degradation phenomenon, posing a severe threat to regional agricultural resource utilization and sustainable development. It has been a mainstream trend to use machine-learning methods to achieve monitoring of large-scale salinized soil quickly. However, machine learning model training requires many samples and hyper-parameter optimization and lacks solvability. To compare the performance of different machine-learning models, this study conducted a soil sampling experiment on saline soils along the south bank of the Yellow River in Dalate Banner. The experiment lasted two years (2022 and 2023) during the spring bare soil period, collecting 304 soil samples. The soil salinity was estimated with the multi-source remote sensing satellite data by combining the extreme gradient boosting model (XGBoost), Optuna hyper-parameter optimization, and Shapley addition (SHAP) interpretable model. Correlation analysis and continuous variable projection were employed to identify key inversion factors. The regression effects of partial least squares regression (PLSR), geographically weighted regression (GWR), long short-term memory networks (LSTM), and extreme gradient boosting (XGBoost) were compared. The optimal model was selected to estimate soil salinity in the study area from 2019 to 2023. The results showed that the XGBoost model fitted optimally, the test set had high R² (0.76) and the ratio of performance to deviation (2.05), and the estimation results were consistent with the measured salinity values. SHAP analysis revealed that the salinity index and topographic factors were the primary inversion factors. Notably, the same inversion factor influenced varying soil salinity estimates at different locations. The saline soils of the study area in 2019 and 2023 were 65% and 44%, respectively, and the overall trend of soil salinization decreased. From the viewpoint of spatial distribution, the degree of soil salinization showed a gradually increasing trend from south to north, and it was most serious on the side near the Yellow River. This study is of great significance for the quantitative estimation of salinized soil in the irrigated area on the south bank of the Yellow River, the prevention and control of soil salinization, and the sustainable development of agriculture. Full article

Global precipitation products (GPPs) are vital in weather forecasting, efficient water management, and monitoring floods and droughts. However, the precision of these datasets varies considerably across different climatic regions and topographic conditions. Therefore, the accuracy assessment of the precipitation dataset is crucial at the local scale before its application. The current study initially compared the performance of recently modified and upgraded precipitation datasets, including Climate Research Unit Time-Series (CRU TS v4.08), fifth-generation ERA5-Land (ERA-5), Integrated Multi-satellite Retrievals for GPM (IMERG) final run (IMERG v07B), and Multi-Source Weighted-Ensemble Precipitation (MSWEP v2.8), against ground observations on the provincial basis across Pakistan from 2003 to 2020. Later, the study area was categorized into four regions based on the elevation to observe the impact of elevation gradients on GPPs’ skills. The monthly and seasonal precipitation estimations of each product were validated against in situ observations using statistical matrices, including the correlation coefficient (CC), root mean square error (RMSE), percent of bias (PBias), and Kling–Gupta efficiency (KGE). The results reveal that IMERG7 consistently outperformed across all the provinces, with the highest CC and lowest RMSE values. Meanwhile, the KGE (0.69) and PBias (−0.65%) elucidated, comparatively, the best performance of MSWEP2.8 in Sindh province. Additionally, all the datasets demonstrated their best agreement with the reference data toward the southern part (0–500 m elevation) of Pakistan, while their performance notably declined in the northern high-elevation glaciated mountain regions (above 3000 m elevation), with considerable overestimations. The superior performance of IMERG7 in all the elevation-based regions was also revealed in the current study. According to the monthly and seasonal scale evaluation, all the precipitation products except ERA-5 showed good precipitation estimation ability on a monthly scale, followed by the winter season, pre-monsoon season, and monsoon season, while during the post-monsoon season, all the datasets showed weak agreement with the observed data. Overall, IMERG7 exhibited comparatively superior performance, followed by MSWEP2.8 at a monthly scale, winter season, and pre-monsoon season, while MSWEP2.8 outperformed during the monsoon season. CRU TS showed a moderate association with the ground observations, whereas ERA-5 performed poorly across all the time scales. In the current scenario, this study recommends IMERG7 and MSWEP2.8 for hydrological and climate studies in this region. Additionally, this study emphasizes the need for further research and experiments to minimize bias in high-elevation regions at different time scales to make GPPs more reliable for future studies. Full article

Approximately 1 million tons of green tides decompose naturally in the Yellow Sea of China every year, releasing large quantities of nutrients that disrupt the marine ecological balance and cause significant environmental consequences. Currently, the identification of areas affected by green tides primarily relies on certain methods, such as ground sampling and biochemical analysis, which limit the ability to quickly and dynamically identify decomposition regions at large spatial and temporal scales. While multi-source remote sensing data can monitor the extent of green tides, accurately identifying areas of algal decomposition remains a challenge. Therefore, satellite data were integrated with key biochemical parameters, such as the carbon-to-nitrogen ratio (C/N), to develop a method for identifying green tide decomposition regions (DRIM). The DRIM shows a high accuracy in identifying green tide decomposition areas, validated through regional repetition rates and UAV measurements. Results indicate that the annual C/N threshold for green tide decomposition regions is 1.2. The method identified the primary decomposition areas in the Yellow Sea from 2015 to 2020, concentrated mainly in the southeastern region of the Shandong Peninsula, covering an area of approximately 1909.4 km². In 2015, 2016, and 2017, the decomposition areas were the largest, with an average annual duration of approximately 35 days. Our method provides a more detailed classification of the dissipation phase, offering reliable scientific support for accurate and detailed monitoring and management of green tide disasters. Full article