The Long Short-Term Memory (LSTM) neural network model is an effective deep learning approach for predicting streamflow, and the investigation of the interpretability of deep learning models in streamflow prediction is of great significance for model transfer and improvement. In this study, four key hydrological stations in the Xijiang River Basin (XJB) in South China are taken as examples, and the performance of the LSTM model and its variant models in runoff prediction were evaluated under the same foresight period, and the impacts of different foresight periods on the prediction results were investigated based on the SHapley Additive exPlanations (SHAP) method to explore the interpretability of the LSTM model in runoff prediction. The results showed that (1) LSTM was the optimal model among the four models in the XJB; (2) the predicted results of the LSTM model decreased with the increase in foresight period, with the Nash–Sutcliffe efficiency coefficient (NSE) decreasing by 4.7% when the foresight period increased from one month to two months, and decreasing by 3.9% when the foresight period increased from two months to three months; (3) historical runoff had the greatest impact on streamflow prediction, followed by precipitation, evaporation, and the North Pacific Index (NPI); except evaporation, all the others were positively correlated. The results can provide a reference for monthly runoff prediction in the XJB.

Accurate and reliable short-term runoff prediction plays a pivotal role in water resource management, agriculture, and flood control, enabling decision-makers to implement timely and effective measures to enhance water use efficiency and minimize losses. To further enhance the accuracy of runoff prediction, this study proposes a FA-LSTM model that integrates the Firefly algorithm (FA) with the long short-term memory neural network (LSTM). The research focuses on historical daily runoff data from the Dahuangjiangkou and Wuzhou Hydrology Stations in the Xijiang River Basin. The FA-LSTM model is compared with RNN, LSTM, GRU, SVM, and RF models. The FA-LSTM model was used to carry out the generalization experiment in Qianjiang, Wuxuan, and Guigang hydrology stations. Additionally, the study analyzes the performance of the FA-LSTM model across different forecasting horizons (1–5 days). Four quantitative evaluation metrics—mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R²), and Kling–Gupta efficiency coefficient (KGE)—are utilized in the evaluation process. The results indicate that: (1) Compared to RNN, LSTM, GRU, SVM, and RF models, the FA-LSTM model exhibits the best prediction performance, with daily runoff prediction determination coefficients (R²) reaching as high as 0.966 and 0.971 at the Dahuangjiangkou and Wuzhou Stations, respectively, and the KGE is as high as 0.965 and 0.960, respectively. (2) FA-LSTM model was used to conduct generalization tests at Qianjiang, Wuxuan and Guigang hydrology stations, and its R² and KGE are 0.96 or above, indicating that the model has good adaptability in different hydrology stations and strong robustness. (3) As the prediction period extends, the R² and KGE of the FA-LSTM model show a decreasing trend, but the whole model still showed feasible forecasting ability. The FA-LSTM model introduced in this study presents an effective new approach for daily runoff prediction.

The Chushandian Reservoir, a key control project on the Huaihe River, is vital for flood control, water allocation, and maintaining ecological baseflow. This study analyzes runoff evolution and provides predictive insights for sustainable water management. Methods employed include Extremum Symmetric Mode Decomposition (ESMD) for decomposing complex signals, a mutation detection algorithm to identify significant changes in time-series data, and cross-wavelet transform to examine correlations and phase relationships between time series across frequencies. Additionally, the hybrid models GM-BP and CNN-LSTM were used for runoff forecasting. Results show cyclical fluctuations in annual runoff every 2.3, 5.3, and 14.5 years, with a significant decrease observed in 2010. Among climate factors, the Atlantic Multidecadal Oscillation (AMO) had the strongest correlation with runoff variability, while ENSO and PDO showed more localized impacts. Model evaluations indicated strong predictive performance, with Nash–Sutcliffe Efficiency (NSE) scores of 0.884 for GM-BP and 0.909 for CNN-LSTM. These findings clarify the climatic drivers of runoff variability and provide valuable tools for water resource management at the Chushandian Reservoir under future climate uncertainties.

Under the combined influence of climate change and human activities, the non-stationarity of reservoir runoff has significantly intensified, posing challenges for traditional statistical models to accurately capture its multi-scale abrupt changes. This study focuses on Qianping (QP) Reservoir and systematically integrates climate-driven mechanisms with machine learning approaches to uncover the patterns of runoff evolution and develop high-precision prediction models. The findings offer a novel paradigm for adaptive reservoir operation under non-stationary conditions. In this paper, we employ methods including extreme-point symmetric mode decomposition (ESMD), Bayesian ensemble time series decomposition (BETS), and cross-wavelet transform (XWT) to investigate the variation trends and mutation features of the annual runoff in QP Reservoir. Additionally, four models—ARIMA, LSTM, LSTM-RF, and LSTM-CNN—are utilized for runoff prediction and analysis. The results indicate that: (1) the annual runoff of QP Reservoir exhibits a quasi-8.25-year mid-short-term cycle and a quasi-13.20-year long-term cycle on an annual scale; (2) by using Bayesian estimators based on abrupt change year detection and trend variation algorithms, an abrupt change point with a probability of 79.1% was identified in 1985, with a confidence interval spanning 1984 to 1986; (3) cross-wavelet analysis indicates that the periodic associations between the annual runoff of QP Reservoir and climate-driving factors exhibit spatiotemporal heterogeneity: the AMO, AO, and PNA show multi-scale synergistic interactions; the DMI and ENSO display only phase-specific weak coupling; while solar sunspot activity modulates runoff over long-term cycles; and (4) The NSE of the ARIMA, LSTM, LSTM-RF, and LSTM-CNN models all exceed 0.945, the RMSE is below 0.477 × 10⁹ m³, and the MAE is below 0.297 × 10⁹ m³, Among them, the LSTM-RF model demonstrated the highest accuracy and the most stable predicted fluctuations, indicating that future annual runoff will continue to fluctuate but with a decreasing amplitude.

Lakes, as key freshwater reserves and ecosystem cores, supply human water, regulate climate, sustain biodiversity, and are vital for global ecological balance and human sustainability. Lake Chaohu, as a crucial ecological barrier in the middle and lower reaches of the Yangtze River, faces significant environmental challenges to regional sustainable development due to water quality deterioration and consequent eutrophication issues. To address the limitations of conventional monitoring techniques, including insufficient spatiotemporal coverage and high operational costs in lake water quality assessment, this study proposes an enhanced Informer model optimized by the Whale Optimization Algorithm (WOA) for predictive analysis of concentration trends of key water quality parameters—dissolved oxygen (DO), permanganate index (CODMn), total phosphorus (TP), and total nitrogen (TN)—across multiple time horizons (4 h, 12 h, 24 h, 48 h, and 72 h). The results demonstrate that the WOA-optimized Informer model (WOA-Informer) significantly improves long-term water quality prediction performance. Comparative evaluation shows that the WOA-Informer model achieves average reductions of 9.45%, 8.76%, 7.79%, 8.54%, and 11.80% in RMSE metrics for 4 h, 12 h, 24 h, 48 h, and 72 h prediction windows, respectively, along with average improvements of 3.80%, 5.99%, 11.23%, 17.37%, and 23.26% in R² values. The performance advantages become increasingly pronounced with extended prediction durations, conclusively validating the model’s superior capability in mitigating error accumulation effects and enhancing long-term prediction stability. Spatial visualization through Kriging interpolation confirms strong consistency between predicted and measured values for all parameters (DO, CODMn, TP, and TN) across all time horizons, both in concentration levels and spatial distribution patterns, thereby verifying the accuracy and reliability of the WOA-Informer model. This study successfully enhances water quality prediction precision through model optimization, providing robust technical support for water environment management and decision-making processes.