The optimal selection of characteristic bands and retrieval models for the hyperspectral retrieval of soil heavy metal concentrations poses a significant challenge. Additionally, satellite-based hyperspectral retrieval encounters several issues, including atmospheric effects, limitations in temporal and radiometric resolution, and data acquisition, among others. Given this, the retrieval performance of the soil arsenic (As) concentration in Pingtan Island, the largest island in Fujian Province and the fifth largest in China, is currently unclear. This study aimed to elucidate this issue by identifying optimal characteristic bands from the full spectrum from both statistical and physical perspectives. We tested three linear models, namely Multiple Linear Regression (MLR), Partial Least Squares Regression (PLSR) and Geographically Weighted Regression (GWR), as well as three nonlinear machine learning models, including Back Propagation Neural Network (BP), Support Vector Machine Regression (SVR) and Random Forest Regression (RFR). We then retrieved soil arsenic content using ground-based soil full spectrum data on Pingtan Island. Our results indicate that the RFR model consistently outperformed all others when using both original and optimal characteristic bands. This superior performance suggests a complex, nonlinear relationship between soil arsenic concentration and spectral variables, influenced by diverse landscape factors. The GWR model, which considers spatial non-stationarity and heterogeneity, outperformed traditional models such as BP and SVR. This finding underscores the potential of incorporating spatial characteristics to enhance traditional machine learning models in geospatial studies. When evaluating retrieval model accuracy based on optimal characteristic bands, the RFR model maintained its top performance, and linear models (MLR, PLSR and GWR) showed notable improvement. Specifically, the GWR model achieved the highest r value for the validation data, indicating that selecting optimal characteristic bands based on high Pearson’s correlation coefficients (e.g., abs(Pearson’s correlation coefficient) ≥0.45) and high sensitivity to soil active materials successfully mitigates uncertainties linked to characteristic band selection solely based on Pearson’s correlation coefficients. Consequently, two effective retrieval models were generated: the best-performing RFR model and the improved GWR model. Our study on Pingtan Island provides theoretical and technical support for monitoring and evaluating soil arsenic concentrations using satellite-based spectroscopy in densely populated, relatively independent island towns in China and worldwide.

Satellite remote sensing offers global-scale soil moisture (SM) estimation to assess water and energy cycles. However, the coarse resolution of SM products from microwave remote sensing is unsuitable for fine-scale analysis. This study explored spatial downscaling methods to refine the 0.25° ESA CCI SM product to a 1-km resolution, utilizing optical and thermal remote sensing data, including the normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), kernel NDVI (kNDVI), and plant phenology index (PPI), together with land surface temperature from MODIS products over two study areas in Europe. The vegetation temperature condition index based approach was used for downscaling, in which the wet and dry edges of the triangular feature space were determined by fitting a line to the maximum and minimum temperatures, respectively, for each VI. The PPI-based downscaling showed consistent results between the two study areas, having a good correlation coefficient and unbiased root-mean-square deviation (ubRMSD) against the in-situ measurements. The NDVI-based downscaling had poor performance overall in terms of ubRMSD and correlation. Results from the EVI- and kNDVI-based methods varied in the two study areas. Compared with the original coarse SM product, spatially downscaled SM products exhibited inferior performance against in-situ SM measurements in terms of evaluation metrics.

Rapid urbanization has placed the sustainable development of some watershed ecosystems in jeopardy. In order to achieve sustainable urban development, it is vital to identify the coupling mechanisms between urbanization and the ecological environment quality. This study establishes indicators to evaluate the Jiulong River Basin’s urbanization and ecological environment systems. These are utilized to analyze spatial and temporal changes and build a coupling coordination degree model. This research investigates the level of development coordination between urbanization and the ecological environment quality in the basin. The data sources include nighttime lighting and Landsat data from 2000 to 2020. The findings indicated the following: 1) Urbanization levels in the basin rise annually, and the years 2010–2020 represent a stage of high urbanization growth. In addition, the development levels are spatially heterogeneous, with high levels in the south and low levels in the north. 2) The ecological environment quality category for the basin is generally Excellent; however, many facets of the climate and human activity drastically lowered this grade in 2005. 3) In the basin, there is a basic coordination relationship between urbanization and environmental quality, but the number of cities falling into the moderate imbalance category has grown. 4) Increasing the urbanization level raises the coordination between urbanization and the ecological environment more than improving environmental quality, but antagonistic effects make it necessary to strengthen the protection of the ecological environment alongside economic development. From the viewpoint of counties, this study examines the long-term interactions between the ecological environment and urbanization in Fujian Province, China. Recommendations for balancing urban development and environmental concerns in coastal watersheds are presented, providing references to the fact that the future of this area of China can be sustainable.

Deep neural network fusion approaches utilizing multimodal remote sensing are essential for crop mapping. However, challenges such as insufficient spatiotemporal feature extraction and ineffective fusion strategies still exist, leading to a decrease in mapping accuracy and robustness when these approaches are applied across spatial‒temporal regions. In this study, we propose a novel rice mapping approach based on dual-branch transformer fusion networks, named RDTFNet. Specifically, we implemented a dual-branch encoder that is based on two improved transformer architectures. One is a multiscale transformer block used to extract spatial–spectral features from a single-phase optical image, and the other is a Restormer block used to extract spatial–temporal features from time-series synthetic aperture radar (SAR) images. Both extracted features were then combined into a feature fusion module (FFM) to generate fully fused spatial–temporal–spectral (STS) features, which were finally fed into the decoder of the U-Net structure for rice mapping. The model’s performance was evaluated through experiments with the Sentinel-1 and Sentinel-2 datasets from the United States. Compared with conventional models, the RDTFNet model achieved the best performance, and the overall accuracy (OA), intersection over union (IoU), precision, recall and F1-score were 96.95%, 88.12%, 95.14%, 92.27% and 93.68%, respectively. The comparative results show that the OA, IoU, accuracy, recall and F1-score improved by 1.61%, 5.37%, 5.16%, 1.12% and 2.53%, respectively, over those of the baseline model, demonstrating its superior performance for rice mapping. Furthermore, in subsequent cross-regional and cross-temporal tests, RDTFNet outperformed other classical models, achieving improvements of 7.11% and 12.10% in F1-score, and 11.55% and 18.18% in IoU, respectively. These results further confirm the robustness of the proposed model. Therefore, the proposed RDTFNet model can effectively fuse STS features from multimodal images and exhibit strong generalization capabilities, providing valuable information for governments in agricultural management.

Persistent cloud cover and frequent rainfall in subtropical regions throughout the year significantly limit the applicability of optical remote sensing for tree species identification, thereby constraining dynamic forest monitoring and precise management of forest resources. To address this challenge, this study proposes a tree species identification method that integrates multi-source remote sensing temporal features. By combining multi-temporal optical imagery from Sentinel-2 and dual-polarisation Synthetic Aperture Radar (SAR) data from Sentinel-1, we constructed a comprehensive feature set that incorporates spectral, structural, and phenological attributes, including various vegetation indices, backscatter coefficients, and polarimetric decomposition parameters. Through correlation analysis and assessment of temporal feature variability, five distinct integration strategies (T1-T5) were developed to classify six typical subtropical tree species: Pinus massoniana, Pinus elliottii, Acacia, Eucalyptus grandis, Mangrove, and Other hardwoods, using a random forest classifier. The results indicate that the multi-source feature fusion approach significantly outperforms single-source models, with the T5 strategy achieving the highest overall accuracy (OA) of 95.33% and a Kappa coefficient of 0.94. The red-edge vegetation indices and SAR polarimetric features were identified as major contributors to improving the classification accuracy of hardwood species. This study demonstrates that multi-source remote sensing data fusion can effectively mitigate the spatiotemporal constraints of optical imagery, providing a viable solution and technical framework for high-accuracy remote sensing classification in complex subtropical forest environments.