A machine learning–coupled APSIM model pipeline for projected oil palm yield in Surat Thani, Thailand
Napat Jantaraprasit, Parichart Promchote, Shih–Yu Simon Wang, Sugontee Daengnui, Sajad Khoshnood Motlagh, Andre Geraldo de Lima Moraes, Luthiene França, Jin–Ho Yoon · 2026
Read A machine learning–coupled APSIM model pipeline for projected oil palm yield in Surat Thani, Thailand by Napat Jantaraprasit, Parichart Promchote, Shih–Yu Simon Wang, Sugontee Daengnui, Sajad Khoshnood Motlagh, Andre Geraldo de Lima Moraes, Luthiene França, Jin–Ho Yoon (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-0349782.txt.
Description
Napat Jantaraprasit and colleagues built a forecasting chain for oil palm harvests in Surat Thani, Thailand. Good forecasts guide farm work and long term climate planning, yet coarse weather grids and crop model bias blur accuracy. Their chain sharpens weather data to fine local scale, feeds a crop simulator, then lets a learning model mop up leftover errors.
The hybrid cut forecast error by more than half versus the simulator alone. Seasonal outlooks made with sharpened data matched those made with past observed weather, giving useful forecasts up to eight months ahead. Century scale outlooks hint at steady yields early on, a modest mid century dip, and later change. Growers gain lead time to plan labour, milling, and planting.
Catalog record
| CREATOR | Napat Jantaraprasit, Parichart Promchote, Shih–Yu Simon Wang, Sugontee Daengnui, Sajad Khoshnood Motlagh, Andre Geraldo de Lima Moraes, Luthiene França, Jin–Ho Yoon |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49968 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |