Can a history of crop rotations improve the prediction of soil organic carbon in the Andes? integrating machine learning multi-annual crop classification as a proxy of soil management
Marcelo Bueno, Hildo Loayza, Johan Ninanya, Javier Rinza, Percy Briceño, Luis Silva, Carlos Mestanza, Ronal Otiniano · 2026
Read Can a history of crop rotations improve the prediction of soil organic carbon in the Andes? integrating machine learning multi-annual crop classification as a proxy of soil management by Marcelo Bueno, Hildo Loayza, Johan Ninanya, Javier Rinza, Percy Briceño, Luis Silva, Carlos Mestanza, Ronal Otiniano (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-0353966.txt.
Description
Marcelo Bueno and eight colleagues ask whether a field's cropping history helps predict how much carbon its soil holds, in this 2026 PLOS ONE study of Peru's northern highlands. Andean soils are carbon-rich but threatened as farming expands. The team trained a satellite-based classifier on more than five hundred fields to reconstruct which crops rotated where between 2019 and 2022, then tested whether that history improved a soil-carbon model.
The full model explained about two thirds of the variation. Soil properties themselves mattered most, but among management signals, how often a field lay fallow was the strongest single clue. Dropping climate data hurt the model more than dropping rotation history — useful guidance for where to spend measurement effort.
Catalog record
| CREATOR | Marcelo Bueno, Hildo Loayza, Johan Ninanya, Javier Rinza, Percy Briceño, Luis Silva, Carlos Mestanza, Ronal Otiniano |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 59217 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |