A Combined System for Predicting Weather Using Machine Learning and Optimization Techniques

Abstract

Abstract: Accurate weather prediction plays a vitalrole in fields like farming, transportation, and emergency planning. This work presents an integrated approach that combines machine learning algorithms with optimization techniques to enhance forecasting performance. The model is built using past weatherdata, including features like temperature, humidity, wind speed, and rainfall. Algorithms such as Decision Tree, Support Vector Machine (SVM), and Random Forest are used for training. To improve the accuracy of these models, optimization methods like Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) are applied to fine-tune their parameters. The proposed system is tested on real-world weather datasets and delivers improved prediction results compared to standard methods. This method helps produce more reliable forecasts, supporting better planning and decision-making in weather-sensitive sectors