The Xiaoxinganling Mountains–Sanjiang Plain region represents a crucial ecological security barrier for the Northeast China Plain and serves as a vital region for national grain production. Over the past two decades, the region has undergone numerous ecological restoration projects. Nevertheless, the combined impact of enhanced vegetation greening and global climate change on the regional hydrological cycle remains inadequately understood. This study employed the distributed hydrological model ESSI-3, reanalysis datasets, and multi-source satellite remote sensing data to quantitatively evaluate the influences of climate change and vegetation dynamics on regional hydrological processes. The study period spans from 2000 to 2020, during which there were significant increases in regional precipitation and leaf area index (p < 0.05). The hydrological simulation results exhibited strong agreement with observed river discharge, evapotranspiration, and terrestrial water storage anomalies, thereby affirming the ESSI-3 model’s reliability in hydrological change assessment. By employing both a constant scenario that solely considered climate change and a dynamic scenario that integrated vegetation dynamics, the findings reveal that: (1) Regionally, climate change driven by increased precipitation significantly augmented runoff fluxes (0.4 mm/year) and water storage components (2.57 mm/year), while evapotranspiration trends downward, attributed primarily to reductions in solar radiation and wind speed; (2) Vegetation greening reversed the decreasing trend in evapotranspiration to an increasing trend, thus exerting a negative impact on runoff and water storage. However, long-term simulations demonstrated that regional runoff fluxes (0.38 mm/year) and water storage components (2.21 mm/year) continue to increase, mainly due to precipitation increments surpassing those of evapotranspiration; (3) Spatially, vegetation greening altered the surface soil moisture content trend in the eastern forested areas from an increase to a decrease. These findings suggested that sub-regional ecological restoration initiatives, such as afforestation, significantly influence the hydrological cycle, especially in areas with higher vegetation greening. Nevertheless, persistent increases in precipitation could effectively mitigate the moisture deficits induced by vegetation greening. The study’s outcomes provide a basis for alleviating concerns regarding potential water consumption risks associated with future ecological restoration and extensive vegetation greening projects, thereby offering scientific guidance for sustainable water resource management.

Accurate landslide susceptibility mapping is vital for disaster forecasting and risk management. To address the problem of limited accuracy of individual classifiers and lack of model interpretability in machine learning-based models, a coupled multi-model framework for landslide susceptibility mapping is proposed. Using Jiuzhaigou County, Sichuan Province, as a case study, we developed an evaluation index system incorporating 14 factors. We employed three base models—logistic regression, support vector machine, and Gaussian Naive Bayes—assessed through four ensemble methods: Stacking, Voting, Bagging, and Boosting. The decision mechanisms of these models were explained via a SHAP (SHapley Additive exPlanations) analysis. Results demonstrate that integrating machine learning with ensemble learning and SHAP yields more reliable landslide susceptibility mapping and enhances model interpretability. This approach effectively addresses the challenges of unreliable landslide susceptibility mapping in complex environments.

The Gravity Recovery and Climate Experiment (GRACE) enables large-scale monitoring of terrestrial water storage changes, significantly contributing to hydrology and related fields. However, the coarse resolution of groundwater storage anomaly (GWSA) data limits local-scale research utilizing GRACE and GRACE-FO missions. In this study, we develop a regional downscaling model based on the linear regression relationship between GWSA and environmental variables, reducing the grid resolution of GWSA obtained from GRACE from approximately 25 km to 1 km. First, we estimate the missing values of monthly continuous terrestrial water storage anomaly (TWSA) for the period from 2003 to 2020 using interpolated multi-channel singular spectrum analysis (IMSSA). Next, we apply the water balance equation to separate GWSA from TWSA, which is provided jointly by the Global Land Data Assimilation System (GLDAS) and the distributed ecohydrological model ESSI-3. We then employ a partial least squares regression (PLSR) model to identify the most significant environmental variables related to GWSA. Precipitation (Prec), normalized difference vegetation index (NDVI), and actual evapotranspiration (AET), with variable importance in projection (VIP) values greater than 1.0, are recognized as effective variables for reconstructing long-term, high-resolution groundwater storage changes. Finally, we downscale and reconstruct the long-term (2003–2020), high-resolution (1 km × 1 km) monthly GWSA in the Songhua River Basin using fused and supplemented GRACE/GRACE-FO data, employing either geographically weighted regression (GWR) or random forest (RF) models. The results demonstrate superior performance of the GWR model (CC = 0.995, NSE = 0.989, RMSE = 2.505 mm) compared to the RF model in downscaling. The downscaled GWSA in the Songhua River Basin not only achieves high spatial resolution but also exhibits improved accuracy when compared to in situ groundwater observation records. This research enhances understanding of spatiotemporal variations in regional groundwater due to local agricultural and industrial water use, providing a scientific basis for regional water resource management.

Synthetic Aperture Radar (SAR) technology offers unparalleled advantages by delivering high-quality images under all-weather conditions, enabling effective flood monitoring. This capability provides massive remote sensing data for flood mapping, while recent rapid advances in deep learning (DL) offer methodologies for large-scale flood mapping. However, the full potential of deep learning in large-scale flood monitoring utilizing remote sensing data remains largely untapped, necessitating further exploration of both data and methodologies. This paper presents an innovative approach that harnesses convolutional neural networks (CNNs) with Sentinel-1 SAR images for large-scale inundation detection and dynamic flood monitoring in the Yangtze River Basin (YRB). An efficient CNN model entitled FloodsNet was constructed based on multi-scale feature extraction and reuse. The study compiled 16 flood events comprising 32 Sentinel-1 images for CNN training, validation, inundation detection, and flood mapping. A semi-automatic inundation detection approach was developed to generate representative flood samples with labels, resulting in a total of 5296 labeled flood samples. The proposed model FloodsNet achieves 1–2% higher F1-score than the other five DL models on this dataset. Experimental inundation detection in the YRB from 2016 to 2021 and dynamic flood monitoring in the Dongting and Poyang Lakes corroborated the scheme’s outstanding performance through various validation procedures. This study marks the first application of deep learning with SAR images for large-scale flood monitoring in the YRB, providing a valuable reference for future research in flood disaster studies. This study explores the potential of SAR imagery and deep learning in large-scale flood monitoring across the Yangtze River Basin, providing a valuable reference for future research in flood disaster studies.

The Sanjiang Plain (SJP) in Northeast China, a crucial black soil region, serves as a quintessential example of a high-intensity agricultural development zone and stands as China’s largest commercial grain production base. In the context of global climate change, pronounced global warming and increased vegetation greening are expected to significantly impact the agricultural water resource supply and its alignment with crop water requirements in the SJP. This study assesses how climate change and vegetation greening affect the crop water supply–demand relationship in the SJP, addressing the critical question of whether natural precipitation can sustain regional agricultural development. Using the extensively validated ESSI-3 distributed hydrological model, integrated with reanalysis and multi-source satellite data, we analyzed data from 1982 to 2018. The results indicate a statistically significant rise in the regional temperature and leaf area index (p < 0.05), with a notable shift around 2000. Key findings include (1) an increase in crop irrigation water requirements (IWR) post-2000, with significant spatial variation; the central and western regions experienced the highest increases, while the eastern region saw reduced risk to crop water security. Furthermore, (2) climate change accounted for approximately 37.9% of the increased IWR in central and western regions, with vegetation greening contributing about 21.2%. Conversely, in the eastern region, vegetation dynamics had a more pronounced effect (28.6%), while climate change contributed less (12.3%). These results suggest a shift in crop water deficit risk boundaries toward the east and north. To optimize water use, expanding high-water-demand crops in the eastern regions and reducing their cultivation in the west is recommended, enhancing alignment between natural precipitation and crop water needs.