What question did this study set out to answer?

April 12, 2026Scientific Reports0 citationsOpen Access

Estimation of onion crop evapotranspiration and crop coefficients using weighing lysimeters and machine learning models in semi-arid region

SSSaba Hashempour Motlagh ShiraziShiraz University FRFatemeh Razzaghi ASAli Reza Sepaskhah

Key Points

The aim is to estimate onion evapotranspiration and crop coefficients using weighing lysimeters and machine learning in a semi-arid region.
Conducted a two-year field experiment with digital weighing lysimeters to measure evapotranspiration.
Developed five machine learning models for predicting evapotranspiration using meteorological and crop parameters.
Calibrated and validated models with measured evapotranspiration as target output.
Evapotranspiration of onion was measured at 447.1 mm and 432.2 mm in the first and second years, respectively.
Soil evaporation contributed 36.6% and 32.8% to total evapotranspiration in the two years.
Highest predictive accuracy was achieved by Random Forest and Decision Tree models (R2 = 0.98).

Abstract

Water scarcity is a significant challenge in Iran’s agricultural sector, particularly for onion (Allium cepa L. ) cultivation, which is a vital crop for the country’s economy and diet. However, there is a lack of standardized data on onion evapotranspiration (ETc) in semi-arid conditions, making precise irrigation management difficult. To address this gap, a two-year field experiment was conducted at the Kooshkak Agricultural Research Station, Shiraz University, Iran to measure ETc using digital weighing lysimeters based on the water balance method and to develop predictive models using machine learning algorithms. The ETc of onion in the first and second years were 447. 1 mm and 432. 2 mm, respectively. Soil evaporation accounted for 36. 6% and 32. 8% of the total ETc in the first and second years, respectively. The average of single crop coefficient values for the initial, mid, and late growth stages across both years were 0. 41, 0. 68, and 0. 51, respectively. Additionally, the basal crop coefficient values for the initial, mid, and late growth stages were 0. 10, 0. 51, and 0. 37, respectively. To estimate ET₂ using easily accessible parameters, five machine learning algorithms were developed: Artificial Neural Network, Support Vector Machine, Decision Tree, Random Forest, and Lasso Regression. These models utilized meteorological variables (temperature, relative humidity, wind speed, net radiation) and crop parameters (leaf area index and plant height) as input features and measured ET₂ was utilized as target outputs for calibrating and validating the model. Among the algorithms, the RF and DT achieved the highest predictive accuracy (R2 = 0. 98, NRMSE = 0. 04), followed by ANN (R2 = 0. 97, NRMSE = 0. 07), SVR (R2 = 0. 97, NRMSE = 0. 08), and LASSO (R2 = 0. 85, NRMSE = 0. 18). Using lysimeter measurements as reliable reference data to evaluate machine-learning models provides a dependable framework for optimizing irrigation scheduling and enhancing water-use efficiency in onion cultivation under semi-arid conditions.

问 AI

Bookmark

View Full Paper