干旱区地理2025，Vol.48Issue(12)：2087-2098,12.DOI:10.12118/j.issn.1000-6060.2024.756
基于XGBoost的干旱区典型绿洲主要作物需水量预测模型研究
Prediction model of water requirements for main crops in typical oases in arid areas based on XGBoost
摘要
Abstract
Climate change and water scarcity significantly threaten agriculture in arid regions.The Cele Oasis,lo-cated at the southern margin of the Taklimakan Desert in Xinjiang,China,is a typical arid-area oasis with a frag-ile ecology.An accurate prediction of the water requirements for cultivating crops in this area is crucial for the ra-tional allocation of water resources and the development of sustainable agricultural practices.This study is dedi-cated to designing a prediction model applicable to the water requirements of the major crops in the Cele Oasis,revealing the intricate relationships among meteorological factors,crop growth characteristics,and water require-ments,and circumventing the data-acquisition challenges associated with the Penman formula.This research inte-grated the Penman formula with the crop coefficient method.The daily water requirement was designated as the target variable.Based on the attribution analysis results,relevant meteorological parameters such as relative hu-midity,sunshine hours,and maximum temperature were selected to construct"XGBoost",a water requirement prediction model.Moreover,different base learner types of XGBoost,including gbtree,gblinear,and dart,were explored to identify which among them was most suitable for the model.The results of this study were remark-able.XGBoost-based regression analysis revealed that relative humidity,sunshine hours,and maximum tempera-ture were the dominant meteorological factors influencing crop water requirements,with a cumulative impor-tance ratio reaching 75.81%.Among them,relative humidity demonstrated the highest impact,with an average feature importance of 39.84%,followed by sunshine hours(20.25%)and maximum temperature(15.72%).In terms of performance,the gbtree-XGBoost model demonstrated superior accuracy compared to the gblinear-XG-Boost model.The R2 value of the former increased by～84.35%relative to the latter,with the root mean square er-ror decreasing by～0.625.The gbtree-XGBoost model could capture the complex nonlinear relationships between variables more effectively,and its predictions correlated markedly with the actual crop water requirements.In conclusion,this study successfully established a crop water requirement prediction model for the Cele Oasis.It could effectively capture the complex relationships among meteorological factors,crop growth characteristics,and water requirements.Among them,the gbtree-XGBoost model showed excellent performance and can be a re-liable tool for guiding irrigation and allocating water resources in the Cele Oasis.It provides a scientific basis for the rational management of agricultural water resources in arid oases,which is conducive to improving water use efficiency,ensuring better crop yields,and promoting the sustainable development of agriculture in arid regions.This research also provides valuable references for similar studies in other arid areas,contributing to global ef-forts in designing water-saving agriculture methods and sustainable water resource management.关键词
作物需水量/彭曼公式/XGBoost回归/需水量预测模型/策勒绿洲Key words
crop water requirement/Penman-Monteith equation/XGBoost regression/water requirement pre-diction model/Cele Oasis引用本文复制引用
WANG Weijie,YU Yang,SUN Lingxiao,HE Jing,ZHANG Lingyun..基于XGBoost的干旱区典型绿洲主要作物需水量预测模型研究[J].干旱区地理,2025,48(12):2087-2098,12.基金项目
国家自然科学基金青年基金资助项目(E1120103) （E1120103）
中国科学院基础与交叉前沿科研B类先导专项(XDB0720200) （XDB0720200）
新疆维吾尔自治区重点研发计划项目(2022B01032-4)资助 （2022B01032-4）
