干旱区研究2026，Vol.43Issue(9)：1901-1910,10.DOI:10.13866/j.azr.2026.09.09
基于机器学习的青海荒漠区光伏电站土壤温度预测
Soil temperature prediction at a photovoltaic power station in the Qinghai desert using machine learning
摘要
Abstract
Photovoltaic array(PVA)layouts induce spatial differentiation in soil water and heat,which can affect soil nutrients and vegetation restoration in desert areas.This study examined soil temperature beneath fixed-axis and inclined single-axis PVAs at the Gonghe photovoltaic power station in Hainan Tibetan Autonomous Prefec-ture,Qinghai Province.We applied artificial neural networks(ANNs),random forests(RFs),support vector ma-chines,and AdaBoost models to predict soil temperatures at 10 cm,20 cm,and 40 cm depths,and compared pre-dictive performance across algorithms.Results showed that PVAs produced seasonal effects on soil temperature:a summer cooling effect of 4.15℃and a winter warming effect for fixed-axis arrays of 2.05℃.The key factor in-fluencing soil temperature under inclined single-axis PVAs and in the control area was the air temperature,while the saturated vapour pressure deficit was most influential beneath fixed-axis PVAs.Model performance varied by location and depth:the ANN model performed best in the control area at 10 cm depth(R2=0.983,RMSE=1.136℃),whereas the RF performed best beneath PVAs(R2=0.984,RMSE=1.040℃).Overall,prediction accura-cy declined with increasing soil depth,and accuracy under inclined single-axis arrays exceeded that under fixed-axis arrays.These results offer a practical reference for predicting soil temperature at power stations using PVAs in desert environments.关键词
荒漠区/光伏电站/土壤温度/机器学习Key words
desert area/photovoltaic power station/soil temperature/machine learning引用本文复制引用
岳生娟,石旭芳,闻锣,柏文文,叶得力,马鸿元..基于机器学习的青海荒漠区光伏电站土壤温度预测[J].干旱区研究,2026,43(9):1901-1910,10.基金项目
青海省科技厅基础研究计划项目(2025-ZJ-976Q) （2025-ZJ-976Q）
青海大学青年科研基金项目(2024-QGY-9) （2024-QGY-9）
青海大学科研实力提升项目(2025KTST07) （2025KTST07）
国家电投集团黄河上游水电开发有限责任公司科技项目(KY-C-2024-GF04,KY-C-2025-HB05) （KY-C-2024-GF04,KY-C-2025-HB05）
