Climate change may cause severe hydrological droughts, leading to water shortages which will require to be assessed using high-resolution data. Gravity Recovery and Climate Experiment (GRACE) satellite Terrestrial Water Storage (TWSA) estimates offer a promising solution to monitor hydrological drought, but its coarse resolution (1°) limits its applications to small regions of the Indus Basin Irrigation System (IBIS). Here we employed machine learning models such as Extreme Gradient Boosting (XGBoost) and Artificial Neural Network (ANN) to downscale GRACE TWSA from 1° to 0.25°. The findings revealed that the XGBoost model outperformed the ANN model with Nash Sutcliff Efficiency (NSE) (0.99), Pearson correlation (R) (0.99), Root Mean Square Error (RMSE) (5.22 mm), and Mean Absolute Error (MAE) (2.75 mm) between the predicted and GRACE-derived TWSA. Further, Water Storage Deficit Index (WSDI) and WSD (Water Storage Deficit) were used to determine the severity and episodes of droughts, respectively. The results of WSDI exhibited a strong agreement when compared with the Standardized Precipitation Evapotranspiration Index (SPEI) at different time scales (1-, 3-, and 6-months) and self-calibrated Palmer Drought Severity Index (sc-PDSI). Moreover, the IBIS had experienced increasing drought episodes, e.g., eight drought episodes were detected within the years 2010 and 2016 with WSDI of −1.20 and −1.28 and total WSD of −496.99 mm and −734.01 mm, respectively. The Partial Least Square Regression (PLSR) model between WSDI and climatic variables indicated that potential evaporation had the largest influence on drought after precipitation. The findings of this study will be helpful for drought-related decision-making in IBIS.

Previous studies on carrying capacity have primarily focused on measuring agricultural production conditions while neglecting the coupling effects among production conditions, production materials, and the external environment (the coupling effects of agricultural water, soil, energy, and the external environment). Therefore, this paper introduces the concept of the carrying capacity of a regional agricultural water–land–energy coupling system (WLECS); develops an evaluation framework comprising 27 indicators from the perspectives of stability, collaboration, and resilience and constructs an improved random forest model based on the red-billed blue magpie optimizer (RBMO). Finally, it is applied to the evaluation of WLECS carrying capacity in China’s main grain producing area (Heilongjiang Province). The results demonstrate that the constructed RBMO-RF model exhibits stability and reasonableness with high fitting accuracy. The collaboration weight accounts for the highest proportion (0.438), indicating that the collaboration within the subsystem has the greatest impact on the carrying capacity. In terms of time scale, the WLECS carrying capacity in Heilongjiang Province shows an upward trend, characterized by three stages: a “low-level fluctuation period”, a “growth period”, and a “rapid growth period”. In terms of spatial scale, the overall spatial pattern is low in the West and high in the East, and stable in the North and South. The key driving factors are the effective irrigation index, indirect water footprint, and agricultural water-land matching degree. The research results demonstrate the carrying capacity of the WLE coupling system holds significant implications for formulating regional agricultural resource optimization allocation plans and promoting agricultural sustainable development.

Droughts are expected to become more severe due to climate disturbances, posing a serious risk to ecosystems. Therefore, quantifying the drought severity and the resilience of soil moisture and vegetation greening is essential for studying whether the local ecosystem is approaching an alternative state that may be dangerous for agriculture. This study aimed to explore the interactions among vegetation, soil moisture, and drought severity to identify the sensitivity of grid cells to drought under maximum cumulative water deficit critical thresholds and the influence of adaptation factors. Drought severity and climate disturbance in a local ecosystem were quantified using dynamically adjusted thresholds, a composite drought index, and a dimensionless index based on water-use efficiency. Moderate and severe drought events were observed using only the drought index. However, these identified events differed across grid cells using the leaf area index representing vegetation health and soil moisture thresholds, suggesting less coverage of drought-affected areas. A substantially reduced drought severity event using adaptation factors showed that local climate and adaptation could significantly change these events. These findings provide new insights into vegetation greening and soil moisture resilience in various regions under drought conditions. The adaptation factor approach significantly reduced the severity of drought tipping events, indicating that local climate and adaptation may affect drought tipping events.

To enhance the precision of regional agricultural drought resilience evaluation, a convolutional neural network optimized with Adam with weight decay (AdamW–CNN) was constructed. Based on local agricultural economic development regulations and utilizing the Driving Force–Pressure–State–Impact–Response (DPSIR) conceptual model, sixteen indicators of agricultural drought resilience were selected. Subsequently, data preprocessing was conducted for Qiqihar City, Heilongjiang Province, China, which encompasses an area of 42,400 km². The drought resilience was accurately assessed based on the developed AdamW–CNN model from 2000 to 2021 in the study area. The key driving factors behind the spatiotemporal evolution of drought resilience were identified using gray relational analysis, and the future evolution trend of agricultural drought resilience was revealed through Ridge regression analysis improved by the Kepler optimization algorithm (KOA–Ridge). The results indicated that the agricultural drought resilience in Qiqihar City exhibited a trend of initial fluctuations, followed by a significant increase in the middle phase, and then stable development in the later stage. Precipitation, investment in the primary industry, grain output per unit of cultivated area, per capita cultivated land area, and the proportion of effective irrigation area were the primary driving factors in the study area. By simulating the drought resilience index of four typical regions and analyzing its evolution, it was found that the AdamW–CNN model, combined with the KOA–Ridge model, has greater advantages over the RMSProp-CNN model and the CNN model in terms of fit, stability, reliability, and evaluation accuracy. These findings provide a robust model for measuring agricultural drought resilience, offering valuable insights for regional drought prevention and management.