Evaluating machine learning models for estimating evapotranspiration in Colombia’s Cauca River Valley
Julián Felipe Rueda Cadavid, Dallan Michell Cañón Castillo, Christian José Mendoza Castiblanco, Andrés Felipe Rodríguez Vásquez, César Andrés Cortés Bello · 2025
Read Evaluating machine learning models for estimating evapotranspiration in Colombia’s Cauca River Valley by Julián Felipe Rueda Cadavid, Dallan Michell Cañón Castillo, Christian José Mendoza Castiblanco, Andrés Felipe Rodríguez Vásquez, César Andrés Cortés Bello (2025) 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-12770521.txt.
Description
Julián Rueda Cadavid and four co-authors compare in 2025 machine learning methods for estimating crop water loss in Colombia's Cauca River Valley. Water that leaves soil and plants, called evapotranspiration, drives irrigation planning. The standard physics formula needs weather inputs that are not always on hand.
Models from simple regression to neural networks were trained on weather station data and judged against the standard formula. Thirteen mixes of three climate inputs were tried. Mixes using net radiation and wind speed predicted best, while humidity and temperature mixes lagged. The results tell growers which few sensors matter most for sound water estimates, a practical gain for precision farming in the valley.
Catalog record
| CREATOR | Julián Felipe Rueda Cadavid, Dallan Michell Cañón Castillo, Christian José Mendoza Castiblanco, Andrés Felipe Rodríguez Vásquez, César Andrés Cortés Bello |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |