What question did this study set out to answer?

The aim is to predict reference evapotranspiration using machine learning and regression models based on climate variables.

February 6, 2026Water Resources Management5 citationsOpen Access

Machine Learning as a Tool to Predict Reference Evapotranspiration

View Full Paper

SASafa AlkanjoSiirt Üniversitesi KKKübra KayaSiirt Üniversitesi VKVeysi KartalSiirt Üniversitesi

Key Points

The aim is to predict reference evapotranspiration using machine learning and regression models based on climate variables.
Utilized machine learning models (SVM, XgBoost, KNN, RF) and statistical regression models (Quartile, PLS, LASSO, Ridge, Elastic Net, NonParametric, Linear).
Applied Design of Experiments (DoE) for model optimization.
Analyzed climate variables such as temperature, humidity, wind speed, precipitation, and solar radiation.
Random Forest (RF) model achieved R²=0.948, indicating strong predictive performance.
XgBoost model had the lowest performance with R²=0.776.
NonParametric regression also reached R²=0.948, performing best among regression methods.
PLS regression was the weakest with R²=0.901.
DoE model provided the highest accuracy at R²=0.987, identifying average temperature as the key influence on ET.

Abstract

Abstract Reference evapotranspiration (ET) is essential for agricultural planning and water management, especially in semi-arid areas like Türkiye’s Siirt province. This study predicted monthly ET using machine learning methods (SVM, XgBoost, KNN, RF) and statistical regression models (Quartile, PLS, LASSO, Ridge, Elastic Net, NonParametric, Linear), as well as a Design of Experiments (DoE) approach. Models used climate variables such as temperature, humidity, wind speed, precipitation, sunshine hours, snow thickness, pressure, cloudiness, and solar radiation. RF was the best-performing machine learning model (R²=0.948), while XgBoost was the lowest (R²=0.776). Among regression methods, NonParametric regression performed best (R²=0.948), and PLS performed weakest (R²=0.901). The DoE model showed the highest accuracy overall (R²=0.987), identifying average temperature as the key variable affecting ET. The findings improve prediction accuracy and offer new insights for hydrological understanding and practical applications in water management, agriculture, and climate adaptation in Siirt.

KI fragen

Bookmark

View Full Paper

Cite This Study

Alkanjo et al. (Sun,) studied this question.

synapsesocial.com/papers/698585fe8f7c464f23009c96 https://doi.org/https://doi.org/10.1007/s11269-025-04460-8

KI fragen

Bookmark

View Full Paper