Climate-stratified assessment of PM2.5 using machine learning: Geographic controls dominate meteorological factors
Someyo Kamal Utsho, Md Rawjatul Fahim, Ruhaidah Samsudin · 2026
Read Climate-stratified assessment of PM2.5 using machine learning: Geographic controls dominate meteorological factors by Someyo Kamal Utsho, Md Rawjatul Fahim, Ruhaidah Samsudin (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/pmc-13568498.txt.
Description
Utsho, Fahim, and Samsudin grade fine dust forecasts zone by zone with machine learning in this twenty twenty-six study. Fine dust is a top air health risk, yet forecast tools are rare-tested across unlike air zones. The team built a zone-split frame from five years of space-fed data.
Inside, near fifty thousand month rows span five broad air bands by width on the globe. A tuned tree model scored best in the sub-hot band and worst in the hot band. Place marks drove most of the score, well past wind and rain marks. When place marks were cut, the model's score fell through the floor in all zones. The frame is shared as free code for dust checks in thin-gauge lands.
Catalog record
| CREATOR | Someyo Kamal Utsho, Md Rawjatul Fahim, Ruhaidah Samsudin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |