Explainable machine learning reveals diverse yield-determining factors among Thai rice farmer cohorts: Implications for targeted agricultural support
Manusnan Suriyalaksh, Benjapon Prommawin, Pimkhuan Hannanta-anan, Tanee Sreewongchai, Parichart Promchote, Sutkhet Nakasathien · 2026
Read Explainable machine learning reveals diverse yield-determining factors among Thai rice farmer cohorts: Implications for targeted agricultural support by Manusnan Suriyalaksh, Benjapon Prommawin, Pimkhuan Hannanta-anan, Tanee Sreewongchai, Parichart Promchote, Sutkhet Nakasathien (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-0349688.txt.
Description
Thai rice farmers work small plots under very different conditions, so one recipe for higher yields fits few. Manusnan Suriyalaksh and colleagues gathered data from more than seventeen hundred smallholders in central Thailand, covering fifty-eight farming and money variables, for this 2026 PLOS One study.
Four automated prediction systems competed, and the best forecast yields with fair accuracy. An explanation method then ranked what mattered: farmers' social networks topped the list, ahead of harvest rental and labor costs. Better-connected farmers harvested more, likely through shared know-how. Grouping farmers by profile showed different drivers per group, arguing for support tailored to each type rather than blanket advice.
Catalog record
| CREATOR | Manusnan Suriyalaksh, Benjapon Prommawin, Pimkhuan Hannanta-anan, Tanee Sreewongchai, Parichart Promchote, Sutkhet Nakasathien |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51352 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |