Scholarlink

<p>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 (ET<sub>c</sub>) 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 ET<sub>c</sub> using digital weighing lysimeters based on the water balance method and to develop predictive models using machine learning algorithms. The ET<sub>c</sub> of onion in the first and second years were 447.1&#xa0;mm and 432.2&#xa0;mm, respectively. Soil evaporation accounted for 36.6% and 32.8% of the total ET<sub>c</sub> 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 <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\({\text{E}\text{T}}_{\text{c}}\)</EquationSource> </InlineEquation> 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 <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\({\text{E}\text{T}}_{\text{c}}\)</EquationSource> </InlineEquation> was utilized as target outputs for calibrating and validating the model. Among the algorithms, the RF and DT achieved the highest predictive accuracy (R<sup>2</sup> = 0.98, NRMSE = 0.04), followed by ANN (R<sup>2</sup> = 0.97, NRMSE = 0.07), SVR (R<sup>2</sup> = 0.97, NRMSE = 0.08), and LASSO (R<sup>2</sup> = 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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月9日

查看全文
  • Saba Hashempour Motlagh Shirazi,
  • Fatemeh Razzaghi,
  • Ali Reza Sepaskhah

摘要

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 \({\text{E}\text{T}}_{\text{c}}\) 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 \({\text{E}\text{T}}_{\text{c}}\) 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.