Precise Weather Prediction with Optimization of Machine Learning Algorithms and Hybrid Feature Selection Techniques
Main Article Content
Abstract
Weather prediction is crucial for various sectors including agriculture, disaster management, and transportation, as it helps in mitigating risks and planning effectively. This study focuses on the implementation and evaluation of several machine learning algorithms, specifically decision trees, random forests, and support vector machines, using the WEKA tool. These algorithms are employed to predict weather-related outcomes. To enhance the performance of these models, an optimized hybrid feature selection technique (PSO + RF) is applied, aiming to improve both accuracy and efficiency. The optimized hybrid feature selection combined with Random Forest classification significantly outperforms other techniques, achieving an impressive accuracy of 97%. The results demonstrate that incorporating optimized feature selection significantly enhances the predictive capabilities of the machine learning models, providing a robust approach for accurate weather forecasting. This study underscores the potential of advanced machine learning techniques in improving weather prediction, thereby contributing to better decision-making and risk management in weather-dependent activities.