AI-DRIVEN GROUNDWATER LEVEL PREDICTION USING A GENETIC ALGORITHM–OPTIMIZED NEURAL NETWORK MODEL

Abstract

This research introduces a hybrid artificial intelligence framework for groundwater level prediction by integrating Artificial Neural Networks (ANN) with Genetic Algorithms (GA) for optimal performance. Traditional groundwater forecasting techniques often fail to capture the complex nonlinear interactions among hydrological, meteorological, and geological parameters. The proposed GA-optimized ANN model automatically tunes neural network weights and biases, significantly enhancing prediction accuracy and convergence speed. Real-world groundwater datasets are utilized to validate the model, demonstrating superior results when compared to classical statistical and standalone ANN methods. This approach provides an efficient and intelligent decision-support tool for sustainable water management, enabling proactive measures against groundwater depletion and environmental risks.