Identifying Effective Features and Classifiers for Short Term Rainfall Forecast Using Rough Sets Maximum Frequency Weighted Feature Reduction Technique

Abstract

Precise rainfall forecasting is a common challenge across the globe in meteorological predictions. As rainfall forecasting involves rather complex dynamic parameters, an increasing demand for novel approaches to improve the forecasting accuracy has heightened. Recently, Rough Set Theory (RST) has attracted a wide variety of scientific applications and is extensively adopted in decision support systems. Although there are several weather prediction techniques in the existing literature, identifying significant input for modelling effective rainfall prediction is not addressed in the present mechanisms. Therefore, this investigation has examined the feasibility of using rough set based feature selection and data mining methods, namely Naïve Bayes (NB), Bayesian Logistic Regression (BLR), Multi-Layer Perceptron (MLP), J48, Classification and Regression Tree (CART), Random Forest (RF), and Support Vector Machine (SVM), to forecast rainfall. Feature selection or reduction process is a process of identifying a significant feature subset, in which the generated subset must characterize the information system as a complete feature set. This paper introduces a novel rough set based Maximum Frequency Weighted (MFW) feature reduction technique for finding an effective feature subset for modelling an efficient rainfall forecast system. The experimental analysis and the results indicate substantial improvements of prediction models when trained using the selected feature subset. CART and J48 classifiers have achieved an improved accuracy of 83.42% and 89.72%, respectively. From the experimental study, relative humidity2 (a4) and solar radiation (a6) have been identified as the effective parameters for modelling rainfall prediction.

Artificial Intelligence Demand Forecasting Techniques in Supply Chain Management: A Systematic Literature Review

“…use multiple techniques on their study which are type-2 Fuzzy logic, hybrid computational intelligence and clustering algorithms on the field of oil and gas. Finally, in the marketing fields,Sudha and Balasubramanian (2016) use multiple techniques such as Naïve Bayes (NB), Bayesian Logistic Regression (BLR), Multi-Layer Perceptron (MLP), Classification and Regression Tree (CART and Random Forest (RF)) Chiu and Chiou (2016). use as well multiple techniques on the field of market trends which are Technology Road Mapping (TRM), radial bias function (RBF), fuzzy algorithms and Neural networks.…”