An Application of Ensemble Spatiotemporal Data Mining Techniques for Rainfall Forecasting

Engineering Proceedings

article

Shanthi Saubhagya¹  Chandima Tilakaratne¹  Musa Mammadov²  Pemantha Lakraj¹ 

[1] Department of Statistics, University of Colombo;School of Info Technology, Faculty of Science, Engineering and Built Environment, Geelong Waurn Ponds Campus, Deakin University

关键词: deep learning;    spatial kriging;    ensemble;    cost-sensitive;    data mining;    imbalance learning;   

DOI  :  10.3390/engproc2023039006

来源: mdpi

【 摘 要 】

The study proposes an ensemble spatiotemporal methodology for short-term rainfall forecasting using several data mining techniques. Initially, Spatial Kriging and CNN methods were employed to generate two spatial predictor variables. The three days prior values of these two predictors and of other selected weather-related variables were fed into six cost-sensitive classification models, SVM, Naïve Bayes, MLP, LSTM, Logistic Regression, and Random Forest, to forecast rainfall occurrence. The outperformed models, SVM, Logistic Regression, Random Forest, and LSTM, were extracted to apply Synthetic Minority Oversampling Technique to further address the class imbalance problem. The Random Forest method showed the highest test accuracy of 0.87 and the highest precision, recall and an F1-score of 0.88.

【 授权许可】

Unknown