Predicting reference evapotranspiration using the weighted instance handler wrapper algorithm

doi:10.1016/j.ecoinf.2026.103684

Predicting reference evapotranspiration using the weighted instance handler wrapper algorithm

2026-03-02

0

OA

AI

Javad Hatamiafkoueieh

DOI：10.1016/j.ecoinf.2026.103684

Original

Original request for help

Save

Abstract

En 中文

• Developed a machine learning framework for reference evapotranspiration prediction. • Models trained at one station and validated across four additional stations. • Two different techniques used to identify optimal input combinations. • Efficient inputs reduced prediction uncertainty by up to 31 %. • Models showed reliable performance and transferability to similar regions.

Keywords:

Reference evapotranspiration (ETo)

Ensemble-based machine learning

WIHW-AMTree-PSO

Feature selection

Efficient input scenario

California

Predicting reference evapotranspiration using the weighted instance handler wrapper algorithm

Abstract

Journal

Organization