Scholarlink

<p>Accurate prediction of the water quality index (WQI) in karst water systems remains challenging due to pronounced seasonal hydrological heterogeneity, dual-porosity flow regimes, and complex multi-factor pollution mechanisms. This study developed a season-stratified, explainable machine-learning framework for the Guilin karst water system (Guangxi, China), based on 208 samples from 104 stations covering the wet (June to August) and dry (December to February) seasons. A sample-adaptive feature engineering step, followed by a three-stage selection pipeline (Pearson correlation filtering, variance inflation factor (VIF) screening, and Random Forest importance ranking), reduced 16 candidate features to ten predictors per season. Ten base learners (Ridge, Lasso, ElasticNet, support vector regression (SVR), random forest (RF), gradient boosting (GBM), eXtreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), categorical boosting (CatBoost) and adaptive boosting (AdaBoost)) were trained separately for each season, and the top three per season were stacked through a regularised Ridge meta-learner. XGBoost performed best in the wet season (R<sup>2</sup> = 0.9655, RMSE = 3.0938, MAE = 2.6754); the Stacking ensemble performed best in the dry season (R<sup>2</sup> = 0.9785, RMSE = 2.9142, MAE = 2.4278), beating every individual learner. regression receiver operating characteristic (RROC) analysis confirmed these rankings via the Area Over the Curve (|AOC|) and exposed a cross-seasonal inversion: ensemble models improved from wet to dry season (|AOC| ratio 0.45–0.54), while linear baselines worsened by a factor of 4.1 to 4.3, supporting season-specific model selection. SHAP analysis showed a clear seasonal shift in the dominant drivers. NH<sub>3</sub>–N controlled wet-season WQI (53.47% importance); in the dry season, control was shared by NH<sub>3</sub>–N (26.00%), TN (25.09%), DO (21.29%) and the pollution-load index (20.19%), and total phosphorus dropped from 7.73 to 0.06%, reflecting carbonate-mediated sequestration specific to karst. The framework offers a transferable, interpretable template for season-aware WQI modelling in monsoonal subtropical karst settings and provides a practical basis for season-differentiated pollution control.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Seasonal water quality index prediction in Guilin karst water system: an explainable machine learning approach

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月19日

查看全文
  • Kun Dong,
  • Yang Huang,
  • Jiayu Yang,
  • Haixiang Li,
  • Sze-Mun Lam,
  • Jin-Chung Sin,
  • Dunqiu Wang

摘要

Accurate prediction of the water quality index (WQI) in karst water systems remains challenging due to pronounced seasonal hydrological heterogeneity, dual-porosity flow regimes, and complex multi-factor pollution mechanisms. This study developed a season-stratified, explainable machine-learning framework for the Guilin karst water system (Guangxi, China), based on 208 samples from 104 stations covering the wet (June to August) and dry (December to February) seasons. A sample-adaptive feature engineering step, followed by a three-stage selection pipeline (Pearson correlation filtering, variance inflation factor (VIF) screening, and Random Forest importance ranking), reduced 16 candidate features to ten predictors per season. Ten base learners (Ridge, Lasso, ElasticNet, support vector regression (SVR), random forest (RF), gradient boosting (GBM), eXtreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), categorical boosting (CatBoost) and adaptive boosting (AdaBoost)) were trained separately for each season, and the top three per season were stacked through a regularised Ridge meta-learner. XGBoost performed best in the wet season (R2 = 0.9655, RMSE = 3.0938, MAE = 2.6754); the Stacking ensemble performed best in the dry season (R2 = 0.9785, RMSE = 2.9142, MAE = 2.4278), beating every individual learner. regression receiver operating characteristic (RROC) analysis confirmed these rankings via the Area Over the Curve (|AOC|) and exposed a cross-seasonal inversion: ensemble models improved from wet to dry season (|AOC| ratio 0.45–0.54), while linear baselines worsened by a factor of 4.1 to 4.3, supporting season-specific model selection. SHAP analysis showed a clear seasonal shift in the dominant drivers. NH3–N controlled wet-season WQI (53.47% importance); in the dry season, control was shared by NH3–N (26.00%), TN (25.09%), DO (21.29%) and the pollution-load index (20.19%), and total phosphorus dropped from 7.73 to 0.06%, reflecting carbonate-mediated sequestration specific to karst. The framework offers a transferable, interpretable template for season-aware WQI modelling in monsoonal subtropical karst settings and provides a practical basis for season-differentiated pollution control.