International Journal of Intelligent Systems and Applications (IJISA)
IJISA Vol. 17, No. 6, 8 Dec. 2025
Cover page and Table of Contents: PDF (size: 1572KB)
An Innovative System for Daily Thunderstorm Event Prediction using Deep Learning
PDF (1572KB), PP.16-32
Views: 0 Downloads: 0
Author(s)
Index Terms
Thunderstorm Prediction, Deep Learning, GRU, LSTM, Time-Series Data, and Mobile Application
Abstract
Thunderstorms are weather disturbances that can cause lightning, stormy winds, dense clouds, tornadoes, and heavy rain. Thunderstorms can cause extensive damage to people's lives, property, and economies, as well as livestock and national infrastructure. Early warning of thunderstorms can save people's lives and property. Previous thunderstorm prediction research did not develop a system for daily thunderstorm prediction with high accuracy for Bangladeshi citizens by assessing a wide range of meteorological variables. To address this issue, this work develops a daily high accuracy based localized thunderstorm event prediction system that analyzes various meteorological factors, dates, and specific location information. This dataset was analyzed using a variety of machine learning models, including traditional statistical models like ARMA, ARIMA, and SARIMA, as well as XGBoost ensemble methods and some deep learning models such as ANN, LSTM, and GRU. The results show that advanced neural network models, particularly GRU and LSTM, outperform others in terms of RMSE, R2, MAE, and MAPE. The GRU model outperformed all other schemes, with an RMSE of 0.794, R2 of 0.998, MAE of 0.476, and MAPE of 3.544%. The mobile application provides users with accurate, localized thunderstorm forecasts, allowing for better safety, event planning, and environmental preparedness. User feedback-based mobile app assessment confirms that more than 55% of users are highly satisfied with the thunderstorm assistance app’s features and usefulness.
Cite This Paper
Md. Tasfirul Alam Siyam, Mahfuzul H. Chowdhury, "An Innovative System for Daily Thunderstorm Event Prediction using Deep Learning", International Journal of Intelligent Systems and Applications(IJISA), Vol.17, No.6, pp.16-32, 2025. DOI:10.5815/ijisa.2025.06.02
Reference
[1]B. K. Chakravorti et al., “Thunderstorm and lightning: The temperature effect on climate change of rangpur region in bangladesh,” Science Journal of Energy Engineering, vol. 6, no. xx, pp. 31–36, 2018.
[2]B. Chakravorti et al., “Earthquake forecasting in bangladesh and its surrounding regions,” European Scientific Journal, vol. 11, no. 18, pp. 238–244, 2015.
[3]A. Biswas et al., “Lightning injury is a disaster in bangladesh?-exploring its magnitude and public health needs,” F1000Research journal, vol. 5, no. 2931, pp. 1-11, 2016.
[4]T. R. Saha et al., “Variability and trends of annual and seasonal thunderstorm frequency over bangladesh,” International Journal of Climatology, vol. 36, no. 14, pp. 4651–4666, 2016.
[5]R. Wilhelmson, “The life cycle of a thunderstorm in three dimensions,” Journal of Atmospheric Sciences, vol. 31, no. 6, pp. 1629–1651, 1974.
[6]R. S. Schumacher and K. L. Rasmussen, “The formation, character and changing nature of mesoscale convective systems,” Nature Reviews Earth and Environment, vol. 1, no. 6, pp. 300–314, 2020.
[7]J E. Kessler, “Thunderstorm morphology and dynamics, US Department of Commerce, National Oceanic and Atmospheric Administration, Book publication, pp. 1-587, 1982.
[8]R. L. Holle, “Lightning fatalities in tropical and subtropical regions,” 29th Conference on Hurricanes and Tropical Meteorology, pp. 1-10, 2010.
[9]M. Azad et al., “Development of novel hybrid machine learning models for monthly thunderstorm frequency prediction over bangladesh,” Natural Hazards, vol. 108, pp. 1109– 1135, 2021.
[10]J. S. Leon Colqui et al., “The impact of transmission line modeling on lightning overvoltage,” Energies, vol. 16, no. 3, p. 1343, 2023.
[11]R. L. Holle, “Lightning-caused deaths and injuries related to agriculture,” in International conference on lightning protection (ICLP 2016), 2016, pp. 1–6.
[12]C. Gomes and Z. Kadir, “Efficient lightning protection: Optimization of economic, environmental and safety aspects,” Environmental Engineering and Management Journal (EEMJ), vol. 14, no. 8, 2015.
[13]K. Wapler and P. James, “Thunderstorm occurrence and characteristics in central europe under different synoptic conditions,” Atmospheric Research, vol. 158, pp. 231–244, 2015.
[14]M. M. Islam et al., “Forecasting thunderstorms in bangladesh: A time series modeling approach,” International Journal of Statistics and Applications, vol. 11, no. 1, pp. 1–7, 2021.
[15]A. Mahabub et al., “Effectiveness of ensemble machine learning algorithms in weather forecasting of bangladesh,” in 11th International Conference on Innovations in Bio-Inspired Computing and Applications (IBICA 2020), pp. 267–277, 2020.
[16]W. Collins and P. Tissot, “2.2 use of an artificial neural network to forecast thunderstorm location,” Fifth Conference on Artificial Intelligence Applications to Environmental Science, pp. 1-10, 2007.
[17]N. Umakanth et al., “Statistical and dynamical based thunderstorm prediction over southeast india,” Journal of Earth System Science, vol. 130, pp. 1–18, 2021.
[18]Y. Mi, “Daily temperature prediction exploiting linear regression and lstmbased model,” in International Conference on Computer Vision, Application, and Algorithm, vol. 12613, 2023, pp. 293–302.
[19]H. Darmawan et al., “Gru and xgboost performance with hyperparameter tuning using gridsearchcv and bayesian optimization on an iot-based weather prediction system, ” International Journal on Advanced Science, Engineering and Information Technology, vol. 13, no. 3, 2023.
[20]N. GHRC, “Lis space time domain search,” https://lightning.nsstc.nasa.gov/nlisib/lissearch.pl?origin=ST&lat=21&lon=85&alat=10&alon=10&donob=both, last accessed on may 2024.
[21]Climate change service, “ERA5 hourly data on single levels from 1940 to present,” https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-single-levels?tab=overview, last accessed on may 2024.
[22]R. F. Adler et al., “Thunderstorm cloud height–rainfall rate relations for use with satellite rainfall estimation techniques,” Journal of climate and applied meteorology, pp. 280–296, 1984.
[23]C. Price, “Global thunderstorm activity,” in Sprites, elves and intense lightning discharges, Springer, vol. 225, pp. 85–99, 2006.
[24]M. S. Islam et al., “Analysis and determination the correlation between thunderstorm occurrence and cloud coverage in srimangal region of bangladesh,” vol. 9, Dew drop journal, Bangladesh Meteorological Department pp. 108-114, 2023.
[25]A. Ben Abbes et al., “Comparative study of three satellite image time-series decomposition methods for vegetation change detection,” European Journal of Remote Sensing, vol. 51, no. 1, pp. 607–615, 2018.
[26]J. D. Cryer, “Time series analysis,” Duxbury Press, book publication, pp. 1-286, 1986.
[27]R. H. Shumway et al., “Time series analysis and its applications,” Springer text in statistics, 2010, third edition, text book, pp. 1-606.
[28]T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794, 2016.
[29]S. J. Taylor and B. Letham, “Forecasting at scale,” The American Statistician, vol. 72, no. 1, pp. 37–45, 2018.
[30]I. Goodfellow et al., “Deep Learning,” MIT press, book publication, pp. 1-800, ISBN: 0262035618, 2016.