{"title":"Thunderstorm Forecasting by Using Machine Learning Techniques: A Comparative Model Analysis Leveraging Historic Climatic Records of Bangladesh","authors":"Mahiyat Tanzim, Sabina Yasmin","doi":"10.1002/joc.8853","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>Accurate thunderstorm forecasting is essential for protecting communities and minimising disruptions to agriculture, infrastructure and human lives, particularly in Bangladesh. However, predicting thunderstorms remains challenging due to the complex interplay of meteorological factors, data limitations and regional variations. This study addresses these challenges by integrating historical meteorological data with advanced machine learning and deep learning techniques to improve prediction accuracy. Using data from the Bangladesh Meteorological Department, we compare various models, evaluating their performance based on the coefficient of determination (<i>R</i><sup>2</sup>) and root mean squared error (RMSE). Among traditional machine learning models, the Support Vector Machine (SVM) Regressor performed best with an <i>R</i><sup>2</sup> of 0.658 and RMSE of 3.65. Among deep learning models, Convolutional Neural Networks (CNNs) achieved superior accuracy with an <i>R</i><sup>2</sup> of 0.743 and RMSE of 3.17, effectively capturing spatial patterns in thunderstorm occurrences. Additionally, deep learning models such as CNN, ANN and LSTM successfully detected annual trends and fluctuations, improving prediction reliability. These findings highlight the potential of deep learning in enhancing thunderstorm forecasting, contributing to more effective disaster preparedness and risk management in thunderstorm-prone regions.</p>\n </div>","PeriodicalId":13779,"journal":{"name":"International Journal of Climatology","volume":"45 8","pages":""},"PeriodicalIF":3.5000,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Climatology","FirstCategoryId":"89","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/joc.8853","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Accurate thunderstorm forecasting is essential for protecting communities and minimising disruptions to agriculture, infrastructure and human lives, particularly in Bangladesh. However, predicting thunderstorms remains challenging due to the complex interplay of meteorological factors, data limitations and regional variations. This study addresses these challenges by integrating historical meteorological data with advanced machine learning and deep learning techniques to improve prediction accuracy. Using data from the Bangladesh Meteorological Department, we compare various models, evaluating their performance based on the coefficient of determination (R2) and root mean squared error (RMSE). Among traditional machine learning models, the Support Vector Machine (SVM) Regressor performed best with an R2 of 0.658 and RMSE of 3.65. Among deep learning models, Convolutional Neural Networks (CNNs) achieved superior accuracy with an R2 of 0.743 and RMSE of 3.17, effectively capturing spatial patterns in thunderstorm occurrences. Additionally, deep learning models such as CNN, ANN and LSTM successfully detected annual trends and fluctuations, improving prediction reliability. These findings highlight the potential of deep learning in enhancing thunderstorm forecasting, contributing to more effective disaster preparedness and risk management in thunderstorm-prone regions.
期刊介绍:
The International Journal of Climatology aims to span the well established but rapidly growing field of climatology, through the publication of research papers, short communications, major reviews of progress and reviews of new books and reports in the area of climate science. The Journal’s main role is to stimulate and report research in climatology, from the expansive fields of the atmospheric, biophysical, engineering and social sciences. Coverage includes: Climate system science; Local to global scale climate observations and modelling; Seasonal to interannual climate prediction; Climatic variability and climate change; Synoptic, dynamic and urban climatology, hydroclimatology, human bioclimatology, ecoclimatology, dendroclimatology, palaeoclimatology, marine climatology and atmosphere-ocean interactions; Application of climatological knowledge to environmental assessment and management and economic production; Climate and society interactions