Abstract: In many applications, weather forecasting (WF) research is an essential endeavor. These applications always require accurate WF. The purpose of this study is to validate different machine learning (ML) classifiers for wet weather prediction. Several machine learning techniques, including support vector machines (SVM), decision trees (DT), and artificial neural networks (ANN), are validated and tested using the Koggle weather dataset. Extended surveys of ML and NN-based WF techniques are also included in this study. The different ML-based classifiers are validated by comparing their prediction accuracy. The five data classes are classified using four features. Overall, it is discovered that the verified accuracy of ANN and Random Forest is 84.35% each.

Keyword: Weather Forecasting, Rain, Classifier, Machine Learning. SVM, ANN, DT and Random Forest etc.

| DOI: 10.17148/IARJSET.2025.12631