智慧农业（中英文）2026，Vol.8Issue(4)：192-203,12.DOI:10.12133/j.smartag.SA202511007
基于特征优选与优化算法的干热河谷区柑橘蒸腾模拟
Estimation of Citrus Transpiration in a Savanna Valley Based on Feature Selection and Optimization Algorithms
摘要
Abstract
[Objective]As the core physiological process determining crop water demand,transpiration profoundly influences irrigation-district water regulation and allocation strategies.During the dry season,water stress is particularly acute in the Yunnan savanna re-gion.For smart,sensor-driven irrigation management,reliable orchard-scale transpiration estimation is essential for real-time irriga-tion scheduling and water allocation.However,traditional mechanistic models face challenges such as difficulties in parameter acqui-sition,high sensitivity to specific parameters,and limited applicability in complex terrains.To address these issues in the development of smart irrigation districts,a high-precision citrus transpiration estimation model was constructed with low parameter dependence.[Methods]A citrus orchard with 10-year-old trees in the savanna region was selected as the study site.Three years of stem sap flow ob-servations and synchronous environmental-factor data were collected.Sap flow was accumulated to the daily scale and used to esti-mate field-scale transpiration.A Random Forest-based wrapper feature selection method was applied to identify an optimal subset of key predictors from 16 original environmental parameters and the day of year(DOY).Specifically,the wrapper method iteratively re-moved the variable with the lowest feature importance and rebuilt the model,continuing until only one variable remained.During this process,model performance under different numbers of variables was recorded for each iteration,and the best feature subset was de-termined based on performance.In addition,a heatmap was used to quantify linear correlations among variables to better understand redundant parameters removed by the model.After identifying the optimal feature combination,the built-in feature importance meth-od of Random Forest was used for importance evaluation.Based on these parameters,extreme gradient boosting(XGB),support vec-tor regression(SVR),and random forest(RF)models were established.Particle swarm optimization(PSO),bayesian optimization(BO),and the asynchronous successive halving algorithm(ASHA)were introduced for hyperparameter tuning,resulting in 12 simula-tion models in total.The dataset was split into 80%for training and 20%for validation.During training,10-fold cross-validation was adopted,and mean absolute error(MAE)was used as the fitness function.Model performance was comprehensively evaluated using the coefficient of determination(R2),root mean square error(RMSE),MAE,and uncertainty metrics.[Results and Discussions]The RF wrapper feature selection reduced the 16 meteorological input parameters to four:actual vapor pressure(ea),soil water content(VWC),wind speed at 2 m(u2),and mean air temperature(Ta).In addition,the DOY was readily obtainable and was identified as the most critical feature,effectively characterizing the unique seasonal climatic variations of the Savanna Valley and citrus phenological characteristics;meanwhile,ea,VWC,Ta,and u2 mainly characterize short-term atmospheric evaporative demand and soil moisture con-straints.While substantially reducing data requirements,the proposed method still achieved high prediction accuracy.Among all mod-el combinations,XGB-ASHA performed best,reaching R2=0.91 and RMSE=0.19 mm/d for daily-scale transpiration prediction.Hyper-parameter optimization improved model robustness,further reducing RMSE and MAE compared with non-optimized baselines.Com-pared with commonly used mechanistic models in the region,the proposed machine-learning approach does not require complex pa-rameter calibration,is less sensitive to input errors,and shows better application feasibility.Uncertainty evaluation further indicates that this framework can provide not only accurate point predictions but also reliable confidence information for operational decision-making.[Conclusions]The proposed model requires monitoring only four environmental parameters to achieve high-accuracy,oper-ational daily-scale transpiration estimation for citrus orchards in the savanna region.The optimal configuration,XGB-ASHA,is suitable for embedding into smart irrigation systems,supporting water-saving irrigation scheduling and irrigation-district-scale wa-ter management.Future work will integrate multi-source data and explore more advanced learning models to further improve transferability and generalization across orchards and years.关键词
蒸腾耗水/机器学习/特征选择/智慧农业/水资源管理Key words
transpiration water consumption/machine learning/feature selection/smart agriculture/water resource management分类
农业科技引用本文复制引用
吴明清,黄锦焘,高志永,李伟康,王静,李靖,裴仁涛,黄海涛,邱皇皇,雷楚靖,赵多..基于特征优选与优化算法的干热河谷区柑橘蒸腾模拟[J].智慧农业（中英文）,2026,8(4):192-203,12.基金项目
云南省农业基础研究联合专项面上项目(202301BD070001-181) （202301BD070001-181）
国家重点研发计划项目(2023YFD1901203) Yunnan Province Agricultural Fundamental Research Joint Special Project(202301BD070001-181) （2023YFD1901203）
National Key Research and Development Program of China(2023YFD1901203) （2023YFD1901203）
