Station-specific thunderstorm forecasting using climate predictors with seasonal decomposition analysis in Bangladesh’s most vulnerable regions
Mohammad Mahboob Hussain Khan, Amrin Binte Ahmed, Adisha Dulmini, Rawfun Nahin Kowbi, Dulsaba Azmain, Muhammad Abu Sufian, Md Mahin Uddin Qureshi, Mustafizur Rahman · 2026
Read Station-specific thunderstorm forecasting using climate predictors with seasonal decomposition analysis in Bangladesh’s most vulnerable regions by Mohammad Mahboob Hussain Khan, Amrin Binte Ahmed, Adisha Dulmini, Rawfun Nahin Kowbi, Dulsaba Azmain, Muhammad Abu Sufian, Md Mahin Uddin Qureshi, Mustafizur Rahman (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0358795.txt.
Description
Mohammad Mahboob Hussain Khan leads a team of eight authors in a 2026 PLOS ONE study on forecasting thunderstorms in Bangladesh. Storms there threaten lives, crops, and buildings, above all in the northeast. The authors build separate forecast models for three high risk weather stations, Sylhet, Sreemangal, and Mymensingh, using four decades of monthly records.
They test thirty-six approaches, from classic time series statistics to neural networks, with and without climate inputs such as cloud cover, pressure, temperature, and rain. Removing the seasonal pattern first helped a great deal, and tree based models came out best at each station. Cloud cover proved the strongest single clue. Station level forecasts like these could give farmers and local officials earlier, more useful warnings.
Catalog record
| CREATOR | Mohammad Mahboob Hussain Khan, Amrin Binte Ahmed, Adisha Dulmini, Rawfun Nahin Kowbi, Dulsaba Azmain, Muhammad Abu Sufian, Md Mahin Uddin Qureshi, Mustafizur Rahman |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 79162 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |