In this study, an integrated approach involving multiple standardized indicators and hydrological modeling (Soil and Water Assessment Tool, SWAT) was evaluated to reconstruct and characterize meteorological, agricultural and hydrological droughts in Upper Kafue River Basin of Zambia during 1984–2013. Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) were used to identify meteorological droughts. Standardized Soil Moisture Index (SSI) was applied to characterize agricultural droughts and Standardized Runoff Index (SRI) was calculated to illustrate hydrological droughts. Input data for SRI and SSI computation was obtained from SWAT model which simulated daily and monthly runoff well with Nash–Sutcliffe efficiency (NSE) and coefficient of determination (R²) greater than 0.65. The results showed that: (1) all indices were able to detect temporal variability of major drought events in a humid subtropical basin in Southern Africa; (2) SWAT successfully simulated runoff and soil moisture although soil moisture requires further calibration to increase accuracy; (3) the average duration and intensity for meteorological droughts at three-month time scale were lower but frequencies were higher compared to agricultural and hydrological droughts at 3- and 12-month aggregates; and (4) drought events exhibited a negative trend as evaluated by Mann–Kendall on SPEI, indicating an increase in drought severity, and correlation analysis between SPEI and SRI revealed that SPEI at 9–15 months has a strong link with hydrological conditions. This study showed that a comprehensive assessment of droughts by integrating multiple variables provided a versatile tool for drought monitoring and mitigation.

Hydrological modeling is a crucial tool in hydrology and water resource management for analyzing runoff evolution patterns. In this study, the process-driven soil and water assessment tool (SWAT) model and data-driven machine learning techniques (XGBoost, random forest, LSTM, BILSTM, and GRU) were employed to simulate runoff at monthly and daily intervals in the Fenhe River basin, situated in the middle reaches of the Yellow River, respectively. The SWAT model demonstrated effective performance in simulating runoff at various scales, with the coefficient of determination (R²) exceeding 0.80 and the Nash–Sutcliffe efficiency (NSE) surpassing 0.79. Sensitivity analysis reveals varying degrees of sensitivity among the model parameters. Furthermore, the deep learning techniques (LSTM, BILSTM, and GRU) exhibited superior simulation generalization capabilities compared to the SWAT model across various scales. Additionally, the generalization abilities of traditional machine learning techniques (XGBoost and random forest) were comparable to the SWAT model. This indicates that deep learning techniques demonstrate remarkable stability and generalization capabilities across various scales. This analysis was motivated by the use of external continuous time series data as input and the application of deep learning techniques to internal mechanisms. Moreover, an integrated modeling approach was used to enhance simulation accuracy by combining the SWAT model with machine learning techniques. The results indicate that the integrated modeling approach improves simulation performance across various scales compared to the single-model approach. This research is significant for improving the efficiency of water resource utilization and management in the Fenhe River basin.

A high concentration of nitrate (NO₃⁻) in surface water threatens aquatic systems and human health. Revealing nitrate characteristics and identifying its sources are fundamental to making effective water management strategies. However, nitrate sources in multi-tributaries and mix land use watersheds remain unclear. In this study, based on 20 surface water sampling sites for more than two years’ monitoring from April 2012 to December 2014, water chemical and dual isotopic approaches (δ¹⁵N-NO₃⁻ and δ¹⁸O-NO₃⁻) were integrated for the first time to evaluate nitrate characteristics and sources in the Huashan watershed, Jianghuai hilly region, China. Nitrate-nitrogen concentrations (ranging from 0.02 to 8.57 mg/L) were spatially heterogeneous that were influenced by hydrogeological and land use conditions. Proportional contributions of five potential nitrate sources (i.e., precipitation; manure and sewage, M & S; soil nitrogen, NS; nitrate fertilizer; nitrate derived from ammonia fertilizer and rainfall) were estimated by using a Bayesian isotope mixing model. The results showed that nitrate sources contributions varied significantly among different rainfall conditions and land use types. As for the whole watershed, M & S (manure and sewage) and NS (soil nitrogen) were major nitrate sources in both wet and dry seasons (from 28% to 36% for manure and sewage and from 24% to 27% for soil nitrogen, respectively). Overall, combining a dual isotopes method with a Bayesian isotope mixing model offered a useful and practical way to qualitatively analyze nitrate sources and transformations as well as quantitatively estimate the contributions of potential nitrate sources in drinking water source watersheds, Jianghuai hilly region, eastern China.

Real-time control (RTC) can be applied to optimize the operation of the anaerobic–anoxic–oxic (A2O) process in wastewater treatment for energy saving. In recent years, many studies have utilized deep reinforcement learning (DRL) to construct a novel AI-based RTC system for optimizing the A2O process. However, existing DRL methods require the use of A2O process mechanistic models for training. Therefore they require specified data for the construction of mechanistic models, which is often difficult to achieve in many wastewater treatment plants (WWTPs) where data collection facilities are inadequate. Also, the DRL training is time-consuming because it needs multiple simulations of mechanistic model. To address these issues, this study designs a novel data-driven RTC method. The method first creates a simulation model for the A2O process using LSTM and an attention module (LSTM-ATT). This model can be established based on flexible data from the A2O process. The LSTM-ATT model is a simplified version of a large language model (LLM), which has much more powerful ability in analyzing time-sequence data than usual deep learning models, but with a small model architecture that avoids overfitting the A2O dynamic data. Based on this, a new DRL training framework is constructed, leveraging the rapid computational capabilities of LSTM-ATT to accelerate DRL training. The proposed method is applied to a WWTP in Western China. An LSTM-ATT simulation model is built and used to train a DRL RTC model for a reduction in aeration and qualified effluent. For the LSTM-ATT simulation, its mean squared error remains between 0.0039 and 0.0243, while its R-squared values are larger than 0.996. The control strategy provided by DQN effectively reduces the average DO setpoint values from 3.956 mg/L to 3.884 mg/L, with acceptable effluent. This study provides a pure data-driven RTC method for the A2O process in WWTPs based on DRL, which is effective in energy saving and consumption reduction. It also demonstrates that purely data-driven DRL can construct effective RTC methods for the A2O process, providing a decision-support method for management.