摘要
Abstract
To address challenge of spatial temperature interpolation caused by complex terrain and uneven distribution of meteorological stations in Xinjiang Uygur Autonomous Region(abbreviated as Xinjiang),a Stacking ensemble RF-SVR-MLP model based on Bayesian optimization has been proposed.Based on data from 84 meteorological stations in Xinjiang from 2011 to 2024,model has in-tegrated multi-source topographic covariates such as elevation and slope.Random forest(RF)and support vector regression(SVR)have been employed as base models to explore nonlinear relationships,while multilayer perceptron(MLP)serves as meta-model to in-tegrate prediction results.Bayesian optimization combined with K-5 fold cross-validation have been used to optimize hyperparameters.Multi-time scale validation showed that model's annual-scale mean absolute error was 1.105 ℃,root mean square error was 1.337 ℃,and coefficient of determination(R2)was 0.836.Compared to optimal single model,MAE and RMSE were reduced by 35.2%and 31.0%,respectively,while goodness of fit improved by 27.4%.In summer,model has resolved issues of single-model failure(R2=0.759),and in winter,it has adapted to temperature inversion characteristics(reducing mean absolute error by 40.2%).Dur-ing critical period from April to October,mean absolute error consistently remained below 1.2 ℃.This model has effectively broken through limitations of traditional methods and single machine learning models,accurately adapting to complex terrain and sparsely popu-lated station areas.It has provided high-precision temperature data for agricultural planning and ecological protection in arid regions,thereby enriching methodological system for climate variables spatialization.关键词
平均气温/空间插值/Stacking集成模型/贝叶斯优化/复杂地形Key words
average temperature/spatial interpolation/Stacking ensemble model/Bayesian optimization/complex terrain分类
农业科技
