Digital elevation models (DEMs) depression processing is a critical preprocessing step in hydrological modelling. In this study, the evolution of depression processing algorithms across DEMs resolutions was systematically examined, tracing the paradigm shift from traditional data modification methods for coarse-resolution DEMs to modern data preservation strategies for high-precision DEMs that maintain original terrain fidelity. Quantitative analysis of the acceleration ratio indicator revealed that algorithmic engineering efficiency can differ by as much as 189
China’s ambitious “dual carbon” policy requires a major transformation of the national energy sector. Given the water-intensive nature of energy production, this transformation is closely tied to future water resource challenges. This study develops a top-down water accounting framework to systematically quantify the current water consumption associated with energy production in China. Combining Shared Socioeconomic Pathways (SSPs) with policy scenarios, it further projects the spatiotemporal evolution of water consumption, aiming to uncover the potential impacts of the “dual carbon” policy on China’s future water consumption in energy production. Results show pronounced spatial heterogeneity in China’s current water consumption for energy production, generally decreasing from north to south, with fossil-fired power generation accounting for 73.6
Hydrological systems exhibit increasingly nonlinear and abrupt responses to climate variability and land use change, yet traditional models struggle to reproduce such dynamics due to parameter rigidity, data scarcity, and substantial uncertainty. We introduce VMD-CT-LSTM, integrating Variational Mode Decomposition (VMD), a correlation test (CT), and Long Short-Term Memory (LSTM) networks, to reduce input redundancy and improve computational efficiency. The model was evaluated on monthly runoff at three stations in the Weihe River basin and evaluated against standard LSTM and VMD-LSTM models. NSE values at all three stations exceeded 0.94, surpassing VMD-LSTM and substantially outperforming LSTM, particularly in capturing abrupt runoff fluctuations, a scenario where VMD-LSTM showed pronounced underestimation. Compared with VMD-LSTM, VMD-CT-LSTM reduced input variables by 64.3–85.7
Accurate prediction of urban water consumption is of great significance for water resources management and the development of efficient decision-support systems. In this study, key influencing factors of water consumption are identified using causation entropy, and a randomly distributed embedding (RDE) model is established to forecast multiple categories of water consumption in data-scarce scenarios. The performance of the RDE model is validated using water consumption data from the Longdong Energy Base in China. The result shows that with only 15 training samples, the correlation coefficients of RDE for many water consumption categories exceed 0.9. In Pingliang, population, actual irrigation area, effective irrigation area, and GDP are the dominant driving factors of water consumption, whereas in Qingyang, GDP and industrial added value are the most influential factors. Finally, the RDE model is employed to predict water demand in the Longdong Energy Base. In brief, irrigation water demand shows an upward trend and total water consumption exhibits a clear decreasing trend in Qingyang. In Pingliang, irrigation water demand rises slightly. Overall, all categories of water demand in the Longdong Energy Base remain relatively stable, with total water demand projected to reach approximately 0.54 billion cubic meters by 2030. Therefore, the RDE model provides a novel and effective approach for water consumption prediction under small-sample conditions.
Although data-driven models have demonstrated high performance in runoff forecasting, their predictions are inherently sensitive to the quality and representation of precipitation forcing, and the internal mechanisms through which precipitation signals are translated into discharge responses are not always transparent. To address the challenges, this study integrates deep learning (DL) models with explainable artificial intelligence(XAI) techniques to (i) investigate the influence of precipitation-product discrepancies on data-driven runoff modeling, and (ii) reveal the hydrological significance of DL-based predictions across temporal and spatial scales. A long short-term memory (LSTM) model and a hybrid convolutional neural network (CNN)-LSTM model are driven by five sets of reanalysis precipitation datasets. The integrated gradients (IG) method and CNN visualization were employed to interpret the internal mechanisms of the models. The framework was applied in the upper, middle and lower reach of the Yangtze River basin. The results demonstrate that input-induced varabilities are especially pronounced during heavy rainfall and rainstorm events, emphasizing the critical impact of precipitation quality on DL-based runoff prediction. These findings indicate that precipitation discrepancies in hydrologically effective regions are more likely to amplify prediction errors, suggesting that targeted improvements in spatial precipitation representation may enhance model robustness, particularly in basins exhibiting higher sensitivity. Given the pronounced hydro-climatic heterogeneity and frequent flood hazards along the Yangtze River Basin, particularly the transition from snow-influenced upstream regions to rainfall-dominated mid- and lower reaches, these insights are especially relevant for improving region-specific flood forecasting and precipitation data prioritization strategies within this basin.
