Tian et al. (2026) Environmental drivers and machine-learning analysis of grapevine sap flow on hilly slopes in Southwest China

Identification

• Journal: Agricultural Water Management
• Year: 2026
• Date: 2026-09-02
• Authors: Mengyao Tian, Rongfei Zhang, Chengcheng Yang, Qing Wang, Liangliang Xu, Zhuping Sheng
• DOI: 10.1016/j.agwat.2026.110743

Research Groups

• College of Environment and Ecology, Chongqing University
• Key Laboratory of the Three Gorges Reservoir Region’s Eco-environment, Ministry of Education, Chongqing University
• Department of Civil and Environmental Engineering, School of Engineering, Morgan State University

Short Summary

This study investigated grapevine sap flow dynamics on hilly slopes in Southwest China using machine learning analysis. The results showed that photosynthetically active radiation was the key factor affecting sap flow, and Random Forest and XGBoost models accurately predicted daily grapevine sap flow.

Objective

• To quantify grapevine sap flow dynamics at annual, monthly, and diel scales
• To identify the key environmental drivers and their direct and indirect influence pathways on grapevine sap flow
• To evaluate the performance of RF and XGBoost models in predicting daily grapevine sap flow

Study Configuration

• Spatial Scale: Hilly slopes in Southwest China
• Temporal Scale: 2023-2024

Methodology and Data

• Models used: Random Forest (RF) and eXtreme Gradient Boosting (XGBoost)
• Data sources: Sap flow measurements, environmental variables (temperature, humidity, radiation, soil moisture), and machine learning algorithms

Main Results

• Photosynthetically active radiation was the key factor affecting sap flow
• RF and XGBoost models accurately predicted daily grapevine sap flow with high accuracy (R²: 0.888 and 0.891 respectively)
• The XGBoost model had better generalization ability (RMSE: 0.086, MAE: 0.059)

Contributions

• This study provides a scientific basis for the formulation of orchard irrigation schedules and water resource management of fruit trees under climate change on the hilly slopes of Southwest China

Funding

• This research was supported by the National Natural Science Foundation of China (Grant No. 51979014)
• The authors acknowledge the financial support from the Key Laboratory of the Three Gorges Reservoir Region’s Eco-environment, Ministry of Education, Chongqing University

Citation

@article{Tian2026Environmental,
  author = {Tian, Mengyao and Zhang, Rongfei and Yang, Chengcheng and Wang, Qing and Xu, Liangliang and Sheng, Zhuping},
  title = {Environmental drivers and machine-learning analysis of grapevine sap flow on hilly slopes in Southwest China},
  journal = {Agricultural Water Management},
  year = {2026},
  doi = {10.1016/j.agwat.2026.110743},
  url = {https://doi.org/10.1016/j.agwat.2026.110743}
}