岳生娟 1石旭芳 1闻锣 1柏文文 1叶得力 马鸿元1
作者信息
- 1. 基于机器学习的青海荒漠区光伏电站土壤温度预测
- 折叠
摘要
光伏阵列布置使土壤水热呈现空间分异，进而可能对荒漠区土壤养分、植被恢复产生影响。本文以青海海南共和光伏电站内固定轴和斜单轴光伏阵列板下土壤为研究对象，利用人工神经网络（ANN）、随机森林（RF）、支持向量机（SVM）以及集成提升树（AdaBoost）模型预测3个深度（10 cm、20 cm和40 cm）的土壤温度，并比较不同机器学习算法的预测性能。结果表明：（1）光伏阵列板对土壤温度影响具有季节性差异，春、夏季具有降温作用，降温幅度为4.15 ℃，而冬季固定轴光伏阵列板具有增温作用，增温幅度为2.05 ℃。（2）斜单轴光伏阵列板下和对照区影响土壤温度的关键因子是气温，而固定轴光伏阵列板下为饱和水汽压差。（3）ANN模型在对照区10 cm土壤温度预测中精度最高（R2=0.983，RMSE=1.136 ℃），而RF模型对光伏阵列板下预测精度最高（R2=0.984，RMSE=1.040 ℃），且斜单轴光伏阵列板下土壤温度预测精度高于固定轴光伏阵列板下。随着土壤深度增加，各模型的预测精度呈下降趋势。研究结果可为荒漠区光伏电站土壤温度预测提供参考。
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 Prefecture,Qinghai Province. We applied artificial neural networks (ANNs), random forests (RFs), support vector machines,and AdaBoost models to predict soil temperatures at 10 cm, 20 cm, and 40 cm depths, and compared predictiveperformance 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 influencing soil temperature under inclined single-axis PVAs and in the control area was the air temperature, whilethe 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 accuracy declined with increasing soil depth, and accuracy under inclined single-axis arrays exceeded that under fixedaxis 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[EB/OL].(2026-09-11)[2026-09-13].https://chinaxiv.org/abs/202609.00102.学科分类
环境科学基础理论
