A hybrid AI model integrating LSTM, XGBoost, and K-means for interpretable prediction and clustering of water quality in data-scarce regions

Key Points

• This hybrid AI model integrates LSTM and XGBoost for superior predictive accuracy of water quality.
• In a data-scarce region context, the model achieves a significant prediction performance, with metrics showing a marked improvement.
• Assessment using a hybrid AI approach highlights the utility of K-means clustering for effective data organization.
• The findings suggest that implementing this model may enhance water management practices, particularly in regions with limited data.