Simulation of Diffuse Solar Radiation with Tree-Based Evolutionary Hybrid Models and Satellite Data
Diffuse solar radiation (R<sub>d</sub>) provides basic data for designing and optimizing solar energy systems. Owing to the notable unavailability in many regions of the world, R<sub>d</sub> is traditionally estimated by models through other easily available meteorological fa...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/7/1885 |
| _version_ | 1797607139418570752 |
|---|---|
| author | Shuting Zhao Youzhen Xiang Lifeng Wu Xiaoqiang Liu Jianhua Dong Fucang Zhang Zhijun Li Yaokui Cui |
| author_facet | Shuting Zhao Youzhen Xiang Lifeng Wu Xiaoqiang Liu Jianhua Dong Fucang Zhang Zhijun Li Yaokui Cui |
| author_sort | Shuting Zhao |
| collection | DOAJ |
| description | Diffuse solar radiation (R<sub>d</sub>) provides basic data for designing and optimizing solar energy systems. Owing to the notable unavailability in many regions of the world, R<sub>d</sub> is traditionally estimated by models through other easily available meteorological factors. However, in the absence of ground weather station data, such models often need to be supplemented according to satellite remote sensing data. The performance of Himawari-7 satellite inversion of R<sub>d</sub> was evaluated in the study, and hybrid models were established (XGBoost_DE, XGBoost_FPA, XGBoost_GOA, and XGBoost_GWO), so as to improve the satellite data and achieve a better utilization effect. The meteorological data of 14 R<sub>d</sub> stations in mainland China from 2011 to 2015 were used. Four input combinations (L1–L4) and eight input combinations (S1–S8) of meteorological factors corresponding to satellite remote sensing data were used for model simulation, while two optimal combinations (S7 and S8) were selected for cross-station application. The results revealed that the accuracy of Himawari-7 satellite R<sub>d</sub> data was low, with RMSE, R<sup>2</sup>, MAE, and MBE values of 2.498 MJ·m<sup>−2</sup>·d<sup>−1</sup>, 0.617, 1.799 MJ·m<sup>−2</sup>·d<sup>−1</sup>, and 0.323 MJ·m<sup>−2</sup>·d<sup>−1</sup>, respectively. The performance of these coupled models based on satellite data was significantly improved. The RMSE and MAE values increased by 15.5% and 9.4%, respectively, while the R<sup>2</sup> value decreased by 10.9 %. Compared with others based on satellite data, the XGBoost_GOA model exhibited optimal performance. The mean values of RMSE, R<sup>2</sup>, and MAE were 1.63 MJ·m<sup>−2</sup>·d<sup>−1</sup>, 0.76 and 1.21 MJ·m<sup>−2</sup>·d<sup>−1</sup>, respectively. The XGBoost_GWO model exhibited optimal performance in the cross-station application, and the average RMSE value was reduced by 2.3–10.5% compared with the other models. The meteorological factors input by the models exhibited different levels of significance in different scenarios. R<sub>d</sub>_s was the main meteorological parameter that affected the model based on satellite data, while RH exhibited a significant improvement in the XGBoost_FPA and XGBoost_GWO models based on ground weather stations data. Accordingly, the present authors believe that the XGBoost_GOA model has excellent ability for simulating R<sub>d</sub>, while the XGBoost_GWO model allows for cross-station simulation of R<sub>d</sub> from satellite data. |
| first_indexed | 2024-03-11T05:26:03Z |
| format | Article |
| id | doaj.art-a4e1d1ec876b4fe28616c1e8e362333a |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T05:26:03Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a4e1d1ec876b4fe28616c1e8e362333a2023-11-17T17:30:22ZengMDPI AGRemote Sensing2072-42922023-03-01157188510.3390/rs15071885Simulation of Diffuse Solar Radiation with Tree-Based Evolutionary Hybrid Models and Satellite DataShuting Zhao0Youzhen Xiang1Lifeng Wu2Xiaoqiang Liu3Jianhua Dong4Fucang Zhang5Zhijun Li6Yaokui Cui7School of Hydraulic and Ecological Engineering, Nanchang Institute of Technology, Nanchang 330099, ChinaInstitute of Water-Saving Agriculture in Arid Areas of China, Northwest A&F University, Yangling 712100, ChinaSchool of Hydraulic and Ecological Engineering, Nanchang Institute of Technology, Nanchang 330099, ChinaInstitute of Water-Saving Agriculture in Arid Areas of China, Northwest A&F University, Yangling 712100, ChinaState Key Laboratory of Water Resources and Hydropower Engineering Science, Wuhan University, Wuhan 430072, ChinaInstitute of Water-Saving Agriculture in Arid Areas of China, Northwest A&F University, Yangling 712100, ChinaSchool of Hydraulic and Ecological Engineering, Nanchang Institute of Technology, Nanchang 330099, ChinaInstitute of RS and GIS, School of Earth and Space Sciences, Peking University, Beijing 100871, ChinaDiffuse solar radiation (R<sub>d</sub>) provides basic data for designing and optimizing solar energy systems. Owing to the notable unavailability in many regions of the world, R<sub>d</sub> is traditionally estimated by models through other easily available meteorological factors. However, in the absence of ground weather station data, such models often need to be supplemented according to satellite remote sensing data. The performance of Himawari-7 satellite inversion of R<sub>d</sub> was evaluated in the study, and hybrid models were established (XGBoost_DE, XGBoost_FPA, XGBoost_GOA, and XGBoost_GWO), so as to improve the satellite data and achieve a better utilization effect. The meteorological data of 14 R<sub>d</sub> stations in mainland China from 2011 to 2015 were used. Four input combinations (L1–L4) and eight input combinations (S1–S8) of meteorological factors corresponding to satellite remote sensing data were used for model simulation, while two optimal combinations (S7 and S8) were selected for cross-station application. The results revealed that the accuracy of Himawari-7 satellite R<sub>d</sub> data was low, with RMSE, R<sup>2</sup>, MAE, and MBE values of 2.498 MJ·m<sup>−2</sup>·d<sup>−1</sup>, 0.617, 1.799 MJ·m<sup>−2</sup>·d<sup>−1</sup>, and 0.323 MJ·m<sup>−2</sup>·d<sup>−1</sup>, respectively. The performance of these coupled models based on satellite data was significantly improved. The RMSE and MAE values increased by 15.5% and 9.4%, respectively, while the R<sup>2</sup> value decreased by 10.9 %. Compared with others based on satellite data, the XGBoost_GOA model exhibited optimal performance. The mean values of RMSE, R<sup>2</sup>, and MAE were 1.63 MJ·m<sup>−2</sup>·d<sup>−1</sup>, 0.76 and 1.21 MJ·m<sup>−2</sup>·d<sup>−1</sup>, respectively. The XGBoost_GWO model exhibited optimal performance in the cross-station application, and the average RMSE value was reduced by 2.3–10.5% compared with the other models. The meteorological factors input by the models exhibited different levels of significance in different scenarios. R<sub>d</sub>_s was the main meteorological parameter that affected the model based on satellite data, while RH exhibited a significant improvement in the XGBoost_FPA and XGBoost_GWO models based on ground weather stations data. Accordingly, the present authors believe that the XGBoost_GOA model has excellent ability for simulating R<sub>d</sub>, while the XGBoost_GWO model allows for cross-station simulation of R<sub>d</sub> from satellite data.https://www.mdpi.com/2072-4292/15/7/1885diffuse solar radiationextreme gradient boostingheuristic algorithmscross-stationinput combinations |
| spellingShingle | Shuting Zhao Youzhen Xiang Lifeng Wu Xiaoqiang Liu Jianhua Dong Fucang Zhang Zhijun Li Yaokui Cui Simulation of Diffuse Solar Radiation with Tree-Based Evolutionary Hybrid Models and Satellite Data Remote Sensing diffuse solar radiation extreme gradient boosting heuristic algorithms cross-station input combinations |
| title | Simulation of Diffuse Solar Radiation with Tree-Based Evolutionary Hybrid Models and Satellite Data |
| title_full | Simulation of Diffuse Solar Radiation with Tree-Based Evolutionary Hybrid Models and Satellite Data |
| title_fullStr | Simulation of Diffuse Solar Radiation with Tree-Based Evolutionary Hybrid Models and Satellite Data |
| title_full_unstemmed | Simulation of Diffuse Solar Radiation with Tree-Based Evolutionary Hybrid Models and Satellite Data |
| title_short | Simulation of Diffuse Solar Radiation with Tree-Based Evolutionary Hybrid Models and Satellite Data |
| title_sort | simulation of diffuse solar radiation with tree based evolutionary hybrid models and satellite data |
| topic | diffuse solar radiation extreme gradient boosting heuristic algorithms cross-station input combinations |
| url | https://www.mdpi.com/2072-4292/15/7/1885 |
| work_keys_str_mv | AT shutingzhao simulationofdiffusesolarradiationwithtreebasedevolutionaryhybridmodelsandsatellitedata AT youzhenxiang simulationofdiffusesolarradiationwithtreebasedevolutionaryhybridmodelsandsatellitedata AT lifengwu simulationofdiffusesolarradiationwithtreebasedevolutionaryhybridmodelsandsatellitedata AT xiaoqiangliu simulationofdiffusesolarradiationwithtreebasedevolutionaryhybridmodelsandsatellitedata AT jianhuadong simulationofdiffusesolarradiationwithtreebasedevolutionaryhybridmodelsandsatellitedata AT fucangzhang simulationofdiffusesolarradiationwithtreebasedevolutionaryhybridmodelsandsatellitedata AT zhijunli simulationofdiffusesolarradiationwithtreebasedevolutionaryhybridmodelsandsatellitedata AT yaokuicui simulationofdiffusesolarradiationwithtreebasedevolutionaryhybridmodelsandsatellitedata |