Estimation of Solar Diffuse Radiation in Chongqing Based on Random Forest

Solar diffuse radiation (DIFRA) is an important component of solar radiation, but current research into the estimation of DIFRA is relatively limited. This study, based on remote sensing data, topographic data, meteorological reanalysis materials, and measured data from radiation observation station...

Full description

Saved in:
Bibliographic Details
Main Authors: Peihan Wan, Yongjian He, Chaoyu Zheng, Jiaxiong Wen, Zhuting Gu
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/4/836
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849719235428745216
author Peihan Wan
Yongjian He
Chaoyu Zheng
Jiaxiong Wen
Zhuting Gu
author_facet Peihan Wan
Yongjian He
Chaoyu Zheng
Jiaxiong Wen
Zhuting Gu
author_sort Peihan Wan
collection DOAJ
description Solar diffuse radiation (DIFRA) is an important component of solar radiation, but current research into the estimation of DIFRA is relatively limited. This study, based on remote sensing data, topographic data, meteorological reanalysis materials, and measured data from radiation observation stations in Chongqing, combined key factors such as the solar elevation angle, water vapor, aerosols, and cloud cover. A high-precision DIFRA estimation model was developed using the random forest algorithm, and a distributed simulation of DIFRA in Chongqing was achieved. The model was validated using 8179 measured data points, demonstrating good predictive capability with a correlation coefficient (R<sup>2</sup>) of 0.72, a mean absolute error (MAE) of 35.99 W/m<sup>2</sup>, and a root mean square error (RMSE) of 50.46 W/m<sup>2</sup>. Further validation was conducted based on 14 radiation observation stations, with the model demonstrating high stability and applicability across different stations and weather conditions. In particular, the fit was optimal for the model under overcast conditions, with R<sup>2</sup> = 0.70, MAE = 32.20 W/m<sup>2</sup>, and RMSE = 47.51 W/m<sup>2</sup>. The results indicate that the model can be effectively adapted to all weather calculations, providing a scientific basis for assessing and exploiting solar energy resources in complex terrains.
format Article
id doaj-art-964be943b2714bfc94e7a6aa2c7d28d6
institution DOAJ
issn 1996-1073
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-964be943b2714bfc94e7a6aa2c7d28d62025-08-20T03:12:11ZengMDPI AGEnergies1996-10732025-02-0118483610.3390/en18040836Estimation of Solar Diffuse Radiation in Chongqing Based on Random ForestPeihan Wan0Yongjian He1Chaoyu Zheng2Jiaxiong Wen3Zhuting Gu4School of Geographical Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Geographical Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaFujian Provincial Climate Center, Fujian Provincial Meteorological Bureau, Fuzhou 350001, ChinaSchool of Geographical Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Geographical Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSolar diffuse radiation (DIFRA) is an important component of solar radiation, but current research into the estimation of DIFRA is relatively limited. This study, based on remote sensing data, topographic data, meteorological reanalysis materials, and measured data from radiation observation stations in Chongqing, combined key factors such as the solar elevation angle, water vapor, aerosols, and cloud cover. A high-precision DIFRA estimation model was developed using the random forest algorithm, and a distributed simulation of DIFRA in Chongqing was achieved. The model was validated using 8179 measured data points, demonstrating good predictive capability with a correlation coefficient (R<sup>2</sup>) of 0.72, a mean absolute error (MAE) of 35.99 W/m<sup>2</sup>, and a root mean square error (RMSE) of 50.46 W/m<sup>2</sup>. Further validation was conducted based on 14 radiation observation stations, with the model demonstrating high stability and applicability across different stations and weather conditions. In particular, the fit was optimal for the model under overcast conditions, with R<sup>2</sup> = 0.70, MAE = 32.20 W/m<sup>2</sup>, and RMSE = 47.51 W/m<sup>2</sup>. The results indicate that the model can be effectively adapted to all weather calculations, providing a scientific basis for assessing and exploiting solar energy resources in complex terrains.https://www.mdpi.com/1996-1073/18/4/836diffuse radiationrandom forestspatiotemporal distributionall weather
spellingShingle Peihan Wan
Yongjian He
Chaoyu Zheng
Jiaxiong Wen
Zhuting Gu
Estimation of Solar Diffuse Radiation in Chongqing Based on Random Forest
Energies
diffuse radiation
random forest
spatiotemporal distribution
all weather
title Estimation of Solar Diffuse Radiation in Chongqing Based on Random Forest
title_full Estimation of Solar Diffuse Radiation in Chongqing Based on Random Forest
title_fullStr Estimation of Solar Diffuse Radiation in Chongqing Based on Random Forest
title_full_unstemmed Estimation of Solar Diffuse Radiation in Chongqing Based on Random Forest
title_short Estimation of Solar Diffuse Radiation in Chongqing Based on Random Forest
title_sort estimation of solar diffuse radiation in chongqing based on random forest
topic diffuse radiation
random forest
spatiotemporal distribution
all weather
url https://www.mdpi.com/1996-1073/18/4/836
work_keys_str_mv AT peihanwan estimationofsolardiffuseradiationinchongqingbasedonrandomforest
AT yongjianhe estimationofsolardiffuseradiationinchongqingbasedonrandomforest
AT chaoyuzheng estimationofsolardiffuseradiationinchongqingbasedonrandomforest
AT jiaxiongwen estimationofsolardiffuseradiationinchongqingbasedonrandomforest
AT zhutinggu estimationofsolardiffuseradiationinchongqingbasedonrandomforest