Station-specific thunderstorm forecasting using climate predictors with seasonal decomposition analysis in Bangladesh’s most vulnerable regions
5 affiliations
- 1Bangladesh Meteorological Department (BMD), Dhaka, Bangladesh
- 2Department of Statistics and Data Science, Jahangirnagar University, Dhaka, Bangladesh
- 3Department of Business and Law, University of Wollongong, Wollongong, NSW, Australia
- 4School of Business and Economics, North South University, Dhaka, Bangladesh
- 5WTO Branch-3, Ministry of Commerce, Dhaka, Bangladesh
Abstract
Thunderstorms pose significant threats to life, agriculture, and infrastructure in Bangladesh, particularly in the northeastern regions of Sylhet, Sreemangal, and Mymensingh. This study develops and rigorously evaluates localized thunderstorm frequency forecasting models for these high-risk stations using 40 years (1985–2024) of monthly data and thirty six modeling approaches encompassing classical time series (SARIMA/SARIMAX, ETS/ETSX), machine learning (ANN/ANNX, SVR/SVRX, XGBoost/XGBoostX), and deep learning (LSTM/LSTMX) architectures, applied to raw and seasonally adjusted (X-11, STL) data under both univariate and exogenous frameworks incorporating five climatic variables (temperature, relative humidity, cloud cover, rainfall, atmospheric pressure). Correlation analysis identified cloud cover (r = 0.83–0.88), atmospheric pressure (r = −0.79 to −0.85), temperature (r = 0.77–0.79), and rainfall (r = 0.74–0.78) as dominant meteorological drivers of thunderstorm activity. Seasonal pre-adjustment using STL substantially improved forecast accuracy, with STL-XGBoost achieving the lowest univariate errors (Sylhet: RMSE = 2.53; Sreemangal: 2.09; Mymensingh: 2.08). Inclusion of exogenous variables dramatically enhanced predictive skill with tree-based and kernel methods: STL-XGBoostX with climate predictors proved optimal for Sylhet (MASE = 0.22), while STL-SVRX with climate predictors was optimal for Sreemangal and Mymensingh (MASE = 0.17), representing over 80% improvement compared to univariate benchmarks. Seasonal forecasts (2025–2028) project peak monsoon activity reaching 100.5 frequency at Sreemangal and identify April–August as the critical preparedness window for these stations. This study provides the Bangladesh Meteorological Department with a validated, operational framework for station-specific thunderstorm frequency forecasting, demonstrating that explicit seasonal decomposition combined with tree-based ensemble and kernel methods offers robust accuracy for early warning systems. The methodology can be extended to additional stations and integrated with socio-economic data to enhance disaster preparedness and climate adaptation strategies for Bangladesh’s most thunderstorm-vulnerable communities.
Related
- PhyTGNet: A Physics‐Prior‐Guided Interpretable Forecasting Method for Thunderstorm Gusts in the Beijing–Tianjin–Hebei Region
- Hybrid machine learning framework for drought forecasting: integration of LSBoost, RQNN, CNN-RNN, CNN-LSTM and advanced data decomposition
- Explainable spatiotemporal Graph Neural Networks: Multi-City PM2.5 forecasting in Bangladesh with geographic graph topology validation
- Mediterranean Warming Amplified the Convective Environment During the December 13, 2024 Severe Thunderstorm at Rome–Fiumicino Airport
- Characterization of thunderstorm-generated travelling ionospheric disturbances by dense GNSS sensors network over Western Europe
BibTeX
@article{khan2026stationspecific,
title = {{Station-specific thunderstorm forecasting using climate predictors with seasonal decomposition analysis in Bangladesh’s most vulnerable regions}},
author = {Mohammad Mahboob Hussain Khan and Amrin Binte Ahmed and Adisha Dulmini and Rawfun Nahin Kowbi and Dulsaba Azmain and Muhammad Abu Sufian and Md. Mahin Uddin Qureshi and Mustafizur Rahman and Rumana Rois},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0358795},
url = {https://doi.org/10.1371/journal.pone.0358795},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Station-specific thunderstorm forecasting using climate predictors with seasonal decomposition analysis in Bangladesh’s most vulnerable regions
AU - Mohammad Mahboob Hussain Khan
AU - Amrin Binte Ahmed
AU - Adisha Dulmini
AU - Rawfun Nahin Kowbi
AU - Dulsaba Azmain
AU - Muhammad Abu Sufian
AU - Md. Mahin Uddin Qureshi
AU - Mustafizur Rahman
AU - Rumana Rois
PY - 2026
DA - 2026/09/24
JO - PLOS One
DO - 10.1371/journal.pone.0358795
UR - https://doi.org/10.1371/journal.pone.0358795
AB - Thunderstorms pose significant threats to life, agriculture, and infrastructure in Bangladesh, particularly in the northeastern regions of Sylhet, Sreemangal, and Mymensingh. This study develops and rigorously evaluates localized thunderstorm frequency forecasting models for these high-risk stations using 40 years (1985–2024) of monthly data and thirty six modeling approaches encompassing classical time series (SARIMA/SARIMAX, ETS/ETSX), machine learning (ANN/ANNX, SVR/SVRX, XGBoost/XGBoostX), and deep learning (LSTM/LSTMX) architectures, applied to raw and seasonally adjusted (X-11, STL) data under both univariate and exogenous frameworks incorporating five climatic variables (temperature, relative humidity, cloud cover, rainfall, atmospheric pressure). Correlation analysis identified cloud cover (r = 0.83–0.88), atmospheric pressure (r = −0.79 to −0.85), temperature (r = 0.77–0.79), and rainfall (r = 0.74–0.78) as dominant meteorological drivers of thunderstorm activity. Seasonal pre-adjustment using STL substantially improved forecast accuracy, with STL-XGBoost achieving the lowest univariate errors (Sylhet: RMSE = 2.53; Sreemangal: 2.09; Mymensingh: 2.08). Inclusion of exogenous variables dramatically enhanced predictive skill with tree-based and kernel methods: STL-XGBoostX with climate predictors proved optimal for Sylhet (MASE = 0.22), while STL-SVRX with climate predictors was optimal for Sreemangal and Mymensingh (MASE = 0.17), representing over 80% improvement compared to univariate benchmarks. Seasonal forecasts (2025–2028) project peak monsoon activity reaching 100.5 frequency at Sreemangal and identify April–August as the critical preparedness window for these stations. This study provides the Bangladesh Meteorological Department with a validated, operational framework for station-specific thunderstorm frequency forecasting, demonstrating that explicit seasonal decomposition combined with tree-based ensemble and kernel methods offers robust accuracy for early warning systems. The methodology can be extended to additional stations and integrated with socio-economic data to enhance disaster preparedness and climate adaptation strategies for Bangladesh’s most thunderstorm-vulnerable communities.
SN - 1932-6203
ER -