数字农科院2.0

Stomatal conductance modeling for drip-irrigated kiwifruit in seasonal drought regions of South China: Evaluation of improved empirical models and interpretable machine learning approaches

文献类型： 外文期刊

作者： Shunsheng Zheng;Ningbo Cui;Quanshan Liu;Shouzheng Jiang;Daozhi Gong;Xiaoxian Zhang

作者机构：

关键词： CatBoost;Growth stage;Kiwifruit vine;Soil water deficit;Stomatal conductance model

期刊名称： Agricultural Water Management

ISSN： 0378-3774

年卷期： 2026 年 325 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Accurate modeling of stomatal conductance (gs) enhances understanding of plant water relations and supports advancements in eco-physiological modeling and adaptive irrigation practices. This study provides a comprehensive evaluation of gs modeling for drip-irrigated kiwifruit through parallel development of three Jarvis-type empirical models (JV, JV1, JV2) and five machine learning algorithms (XGBoost, LightGBM, CatBoost, SVR, LR) based on three years of field measurements comprising synchronized records of gs and key environmental drivers. Models were assessed via year-wise grouped cross-validation, with performance measured by R2, RMSE, and MAE, and interpretability analyzed using SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDPs). Results showed that deficit irrigation significantly reduced gs, with sensitivity being most pronounced during stage II. The incorporation of soil water content (SWC) substantially improved the accuracy of both empirical and machine learning models. Among empirical models, JV2, featuring a stage-specific nonlinear SWC response function, demonstrated the highest accuracy (R2 ranging from 0.736 to 0.814) and minimized bias under extreme SWC conditions. Using vapor pressure deficit (VPD), air temperature (Ta), photosynthetically active radiation (PAR), and SWC as input variables, CatBoost outperformed both empirical models and other machine learning algorithms across all growth stages (R2 = 0.815–0.839; RMSE = 0.065–0.076 mol m−2 s−1; MAE = 0.054–0.064 mol m−2 s−1). SHAP analysis and PDPs identified VPD as the dominant driver of gs variation, followed by SWC. Overall, the improved JV2 model offers a structurally transparent framework for gs estimation with acceptable accuracy, while CatBoost combined with SHAP analysis and PDPs provides superior predictive performance and robust interpretability under complex environmental conditions. These findings support the reliable modeling and regulation of kiwifruit gs under varying SWC scenarios in drip-irrigated orchards.

分类号：

  • 相关文献

[1]Deficit drip irrigation improves kiwifruit quality and water productivity under rain-shelter cultivation in the humid area of South China. Shunsheng Zheng,Shouzheng Jiang,Ningbo Cui,Lu Zhao,Daozhi Gong,Yaosheng Wang,Zongjun Wu,Quanshan Liu. 2023

[2]CatBoost algorithm for estimating maize above-ground biomass using unmanned aerial vehicle-based multi-source sensor data and SPAD values. Weiguang Zhai,Changchun Li,Shuaipeng Fei,Yanghua Liu,Fan Ding,Qian Cheng,Zhen Chen. 2023

[3]Improving Forest Above-Ground Biomass Estimation by Integrating Individual Machine Learning Models. Mi Luo,Shoaib Ahmad Anees,Qiuyan Huang,Xin Qin,Zhihao Qin,Jianlong Fan,Guangping Han,Liguo Zhang,Helmi Zulhaidi Mohd Shafri. 2024

[4]A novel approach for predicting aflatoxin B1 production using regression models and whole-cell biosensors in moldy maize and peanut kernels. Lu Sun,Junning Ma,Yongping Jiang,Giorgia Purcaro,Yuanyuan Tian,Gang Wang,Weizhao Li,Bowen Tai,Fuguo Xing. 2025

[5]Morphological fractions, chemical compositions and in vitro gas production of rice straw from wild and brittle culm1 variety harvested at different growth stages. Wang, Haifeng,Wu, Yueming,Liu, Jianxin,Qian, Qian. 2006

[6]Effects of Arsenic on Nutrients Uptake of Wheat (Triticum aestivum L) at Different Growth Stages. Liu, Quanji,Zheng, Chuangmu,Liu, Quanji,Hu, Chengxiao,Tan, Qiling,Sun, Xuecheng.

[7]Threshold of Soil Olsen-P in Greenhouses for Tomatoes and Cucumbers. Wu, Xue-Ping,Wu, Hui-Jun,Wang, Xiao-Bin,Li, Yin-Kun,Zhang, Yan-Cai,Li, Ruo-Nan,Wang, Li-Ying,Zhai, Cai-Xia,Chen, Li-Li,Wu, Xue-Ping,Wu, Hui-Jun,Wang, Xiao-Bin.

[8]Canopy Spatial Distribution and Identification Using Hyperspectal Data in Winter Wheat. Lu, Yan-Li,Li, Shao-Kun,Lu, Yan-Li,Bai, You-Lu,Lu, Yan-Li,Bai, You-Lu,Jones, Carol L.,Wang, Ji-Hua.

[9]Biochar application promotes crops yield through regulating root development and the community structure of root endophytic fungi in wheat-maize rotation. Shuo Han,Hongbo Li,Zed Rengel,Zhangliu Du,Ning Hu,Yanan Wang,Aiping Zhang. 2023

[10]Improved Crop Biomass Algorithm with Piecewise Function (iCBA-PF) for Maize Using Multi-Source UAV Data. Lin Meng,Dameng Yin,Minghan Cheng,Shuaibing Liu,Yi Bai,Yuan Liu,Yadong Liu,Xiao Jia,Fei Nan,Yang Song,Haiying Liu,Xiuliang Jin. 2023

[11]How to Better Use Canopy Height in Soybean Biomass Estimation. Zhu, Yanqin,Fan, Fan,Zhang, Zhen,Yu, Xun,Jiang, Tiantian,Li, Liming,Liu, Yadong,Bai, Yali,Tang, Ziqian,Liu, Shuaibing,Yin, Dameng,Jin, Xiuliang. 2025

作者其他论文 更多>>