HOW MACHINE LEARNING ALGORITHMS ARE USED IN METEOROLOGICAL DATA CLASSIFICATION: A COMPARATIVE APPROACH BETWEEN DT, LMT, M5-MT, GRADIENT BOOSTING AND GWLM-NARX MODELS

Rainfall prediction is one of the most challenging task faced by researchers over years. Many machine learning and AI based algorithms have been implemented on different datasets for better purposes, but there not a single solution which perfectly predicts rainfall. Accurate still remains question to researchers. We offer learning-based comparison evaluation rainfall models Kashmir province. Both local geographic features time horizon has influence weather forecasting. Decision trees, Logistic Model Trees (LMT), M5 model trees are examples predictive algorithms. GWLM-NARX, Gradient Boosting, other techniques were investigated. Weather predictors measured from three major meteorological stations in area UT J&K, India, utilized models. compared proposed their accuracy, kappa, interpretability, statistics, as well significance utilized. On original dataset, DT delivers an accuracy 80.12 percent, followed LMT boosting models, produce 87.23 percent 87.51 respectively. Furthermore, when continuous data was used M5-MT GWLM-NARX NARX performed better, with mean squared error (MSE) regression value (R) predictions 3.12 0.9899 training, 0.144 0.9936 validation, 0.311 0.9988 testing.