Environmental Chemistry•2026•DOI: 10.7524/j.issn.0254-6108.2025102801
This study develops a multivariate time-series forecasting model for water quality in the Lhasa River, focusing on four key indicators: water temperature, pH, dissolved oxygen, and turbidity. Data preprocessing integrated multiple missing-value imputation strategies and interquartile range (IQR) outlier removal. Boxplots and relative standard deviation (RSD) assessed data distribution and dispersion, while autocorrelation and Pearson correlation analyses revealed periodic patterns and inter-variable relationships. Four representative algorithms—Support Vector Regression (SVR), Extreme Gradient Boosting (XGBoost), CNN-BiLSTM-Attention, and TCN-Transformer—were optimized via Bayesian hyperparameter tuning. Model performance was evaluated using MAE, MSE, RMSE, and R². The study systematically compared the effects of different missing-value handling methods, both independently and combined with IQR outlier removal. Results indicate that CNN-BiLSTM-Attention excels in water temperature prediction, suitable for relatively stable and simple patterns. In contrast, TCN-Transformer demonstrates superior performance for pH, dissolved oxygen, and turbidity, which exhibit strong nonlinearity and long-term dependencies, effectively capturing temporal dependencies and coupling relationships. The findings provide a viable technical route and theoretical reference for river water quality monitoring and intelligent early-warning systems.
Environmental Chemistry•2026•DOI: 10.7524/j.issn.0254-6108.2025042103
This study investigated the spatiotemporal distribution, ecological risk, and sources of seven heavy metals (Cr, Cd, Cu, Ni, Pb, Zn, As) in surface sediments of Ranwu Lake, Xizang. Twelve samples were collected during the glacial ablation period (July 2024) and late glacial ablation period (November 2024). Concentrations were determined and analyzed using inverse distance weighting (IDW) for spatial patterns, geo-accumulation index (Igeo) and potential ecological risk index (RI) for risk assessment, and correlation analysis (CA), principal component analysis (PCA), and absolute principal component score-multiple linear regression (APCS-MLR) for source apportionment. Results showed that during glacial ablation, mean Cr, Cd, Pb, and As exceeded Xizang soil background values, while in the late ablation period only Cd, Pb, and As remained elevated. Spatial distribution varied between periods, with high concentrations in the middle and lower lake during ablation, shifting to the lower lake in the late period. Igeo and RI indicated overall low ecological risk, with Cd as the primary risk factor; mean RI values were 81.79 and 98.30 for the two periods, respectively. Source apportionment revealed that heavy metals mainly originated from natural and transportation sources, with traffic emissions being the major contributor to ecological risk. Specifically, Cr, Ni, and As were predominantly natural, Cd and Pb were mainly traffic-related, and Cu and Zn were influenced by both natural and traffic sources.