A Hybrid Machine Learning Framework for Water Quality Index Prediction Using Feature-Based Neural Network Initialization

Accurate prediction of the Water Quality Index (WQI) is essential for protecting public health and managing freshwater resources. Existing models often rely on arbitrary weight initialization and make limited use of ensemble learning, which results in unstable performance and reduced interpretability. This study introduces a hybrid machine learning framework that combines feature-informed neural network initialization with gradient boosting (XGBoost) to address these limitations. Neural network weights are initialized using feature significance scores derived from SHapley Additive exPlanations (SHAP) and predictions are iteratively refined using XGBoost. The model was trained and evaluated using the public Quality of Freshwater dataset and compared against several baselines, including Random Forest, Support Vector Regression (SVR), a conventional Artificial Neural Network (ANN) with Xavier initialization and an XGBoost-only model. Our framework achieved an accuracy of 86.9%, an F1-score of 0.849 and a Receiver Operating Characteristic–Area Under the Curve (ROC-AUC) of 0.894, outperforming all comparative methods. Ablation experiments showed that both the SHAP-based initialization and the boosting component each improved performance over simpler baselines.