In response to the global ecological and agricultural challenges posed by coastal saline-alkali areas, this study focuses on Dongying City as a representative region, aiming to develop a high-precision soil salinity prediction mapping method that integrates multi-source remote sensing data with machine learning techniques. Utilizing the SCORPAN model framework, we systematically combined diverse remote sensing datasets and innovatively established nine distinct strategies for soil salinity prediction. We employed four machine learning models—Support Vector Regression (SVR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Geographical Gaussian Process Regression (GGPR) for modeling, prediction, and accuracy comparison, with the objective of achieving high-precision salinity mapping under complex vegetation cover conditions. The results reveal that among the models evaluated across the nine strategies, the SVR model demonstrated the highest accuracy, followed by RF. Notably, under Strategy IX, the SVR model achieved the best predictive performance, with a coefficient of determination (R²) of 0.62 and a root mean square error (RMSE) of 0.38 g/kg. Analysis based on SHapley Additive exPlanations (SHAP) values and feature importance indicated that Vegetation Type Factors contributed significantly and consistently to the model’s performance, maintaining higher importance than traditional salinity indices and playing a dominant role. In summary, this research successfully developed a comprehensive, high-resolution soil salinity mapping framework for the Dongying region by integrating multi-source remote sensing data and employing diverse predictive strategies alongside machine learning models. The findings highlight the potential of Vegetation Type Factors to enhance large-scale soil salinity monitoring, providing robust scientific evidence and technical support for sustainable land resource management, agricultural optimization, ecological protection, efficient water resource utilization, and policy formulation.

Asymmetrical changes in day and night temperatures (Td, Tn) have become a hot topic in climate change research. Using the MODIS 8-day synthetic temperature (MOD11A2) and the SPOT-VGT/PROBA_V 10-day synthetic normalized difference vegetation index (NDVI), we analyzed the spatiotemporal trends of Td and Tn in spring and autumn in Northeast China during the period of 2001–2016 and the partial correlation between temperature and vegetation phenology (start of season, SOS; end of season, EOS). We revealed that spring Td was the main negative factor pertaining to SOS. An increasing Td resulted in a delayed SOS in arid and semiarid regions, while in boreal areas, an increasing Td ensured the heat required for vegetation growth and prompted the SOS to advance. Conversely, EOS was positively correlated with Tn in autumn. Areas showing positive correlations between Tn and EOS totaled 73.26%, and 14.19% of the areas had a significant correlation (p < 0.05). However, the effects of Td on EOS were not as significant as Tn, and only at a 10.62% correlation did Td achieve significance, which was mostly attributable to areas of high elevation and latitude. Our results are crucial for future improvements in dynamic vegetation activities in response to climate change.

Crop classification is one of the most important agricultural applications of remote sensing. Many studies have investigated crop classification using SAR data, while few studies have focused on the classification of dryland crops by the new Gaofen-3 (GF3) SAR data. In this paper, taking Hengshui city as the study area, the performance of the Freeman–Durden, Sato4, Singh4 and multi-component decomposition methods for dryland crop type classification applications are evaluated, and the potential of full-polarimetric GF3 data in dryland crop type classification are also investigated. The results show that the multi-component decomposition method produces the most accurate overall classifications (88.37%). Compared with the typical polarization decomposition techniques, the accuracy of the classification results using the new decomposition method is improved. In addition, the Freeman method generally yields the third-most accurate results, and the Sato4 (87.40%) and Singh4 (87.34%) methods yield secondary results. The overall classification accuracy of the GF3 data is very positive. These results demonstrate the great promising potential of GF3 SAR data for dryland crop monitoring applications.

Accurate agricultural parcel data serves as crucial foundational information in modern agriculture. Addressing the urgent demand for fine-grained extraction of agricultural parcels from high-resolution remote sensing imagery, this paper proposes a Fine Extraction Method for Farmland Plots Based on Remote Sensing with Semantic and Edge Feature Fusion (FFENet). FFENet takes high-resolution remote sensing imagery as input, and mainly comprises core components such as a semantic feature encoding module, an edge feature encoding module (EEM), a Hybrid Attention-based Edge Attention Module (HA-EAM), a feature fusion module (FFM), a feature generation module, and a classification module (EDWC). Specifically, the FFM is employed for hierarchical fusion of semantic features and edge features, the HA-EAM utilizes edge features to predict potential parcel boundaries, and the feature generation module decodes the output of the FFM to generate pixel-wise features. Finally, EDWC integrates the pixel-wise features and their probability of being a boundary to determine the parcel classification of each pixel. To verify the effectiveness and generalization capability of the proposed method, this study selected Tai'an City and Juye County of Shandong Province as research areas, and used GF-2 PMS imagery as the data source for the experiments. Comparative results against mainstream models such as DeeplabV3+, Swin-Unet, and EIGNet demonstrated that FFENet achieved optimal performance in the parcel extraction task, The results showed that FFENet achieved an F1-score of 94.6% and an IoU of 89.5% on this dataset, significantly outperforming the comparison models. The proposed approach exhibits superior performance in boundary extraction accuracy and shape consistency, proving its significant advantages in the fine-grained extraction of agricultural parcels.