AI-driven improvement of monthly average rainfall forecasting in Mecca using grid search optimization for LSTM networks

Abstract

Predicting the average monthly rainfall in Mecca is crucial for sustainable development, resource management, and infrastructure protection in the region. This study aims to enhance the accuracy of long short-term memory (LSTM) deep regression models used for rainfall forecasting using an advanced grid-search-based hyperparameter optimization technique. The proposed model was trained and validated on a historical dataset of Mecca's monthly average rainfall. The model's performance improved by 5.0% post-optimization, reducing the root-mean-squared error (RMSE) from 0.1201 to 0.114. The results signify the value of grid search optimization in improving the LSTM model's accuracy, demonstrating its superiority over other common hyperparameter optimization techniques. The insights derived from this research provide valuable input for decision-makers in effectively managing water resources, mitigating environmental risks, and fostering regional development. HIGHLIGHTS Utilized grid search optimization to fine-tune LSTM network parameters, achieving unprecedented forecasting accuracy.; Demonstrated the effectiveness of the proposed method through extensive validation against historical rainfall data.; Highlighted the potential of the method for improving water resource management and planning in arid regions.; Contributed to the body of knowledge in meteorological forecasting with a scalable and adaptable AI approach.;

Keywords

• agricultural planning
• artificial intelligence
• grid search
• hyperparameter optimization
• lstm deep regression model
• machine learning