Coupling meteorological stations data and satellite data for prediction of global solar radiation with machine learning models

被引：20

作者：

Zhao, Shuting ^{[1
,2
]}

Wu, Lifeng ^{[3
]}

Xiang, Youzhen ^{[1
,2
]}

Dong, Jianhua ^{[4
]}

Li, Zhen ^{[5
]}

Liu, Xiaoqiang ^{[1
,2
]}

Tang, Zijun ^{[1
,2
]}

Wang, Han ^{[1
,2
]}

Wang, Xin ^{[1
,2
]}

An, Jiaqi ^{[1
,2
]}

Zhang, Fucang ^{[1
,2
]}

Li, Zhijun ^{[1
,2
]}

机构：

[1] Northwest A&F Univ, Key Lab Agr Soil & Water Engn Arid & Semiarid Area, Minist Educ, Yangling 712100, Peoples R China

[2] Northwest A&F Univ, Inst Water saving Agr Arid Areas China, Yangling 712100, Peoples R China

[3] Nanchang Inst Technol, Sch Hydraul & Ecol Engn, Nanchang 330099, Peoples R China

[4] Wuhan Univ, State Key Lab Water Resources & Hydropower Engn Sc, Wuhan 430072, Peoples R China

[5] China Acad Space Technol, Inst Remote Sensing Satellite, Beijing 100094, Peoples R China

来源：

RENEWABLE ENERGY | 2022年 / 198卷

关键词：

Solar radiation; Machine learning; Input combination; Meteorological factors; SUPPORT VECTOR MACHINE; SUNSHINE DURATION; IRRADIANCE; RESOLUTION; ANN;

D O I：

10.1016/j.renene.2022.08.111

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

The simulation of solar radiation is of great significance to the sustainable development of energy, engineering, and many other fields. The Himawari series of satellites has the characteristics of high temporal, spatial resolution, which helps to solve the problem of insufficient ground radiation observation in China. However, the accuracy of this data needs to be further improved. Thus, four machine learning models with 13 ground and satellite-based input combinations were used to simulate daily solar radiation. The results showed that the simulation accuracy of the model based on a combination of meteorological data from different sources was significantly improved compared with the model based on single-source data. The RMSE was 32.4% and 44.6% lower than those of the model based on the ground meteorological stations data and the model based on the satellite data, respectively. SVM13 model showed the optimal simulation performance compared with other models, and its RMSE and R2 were 1.732 MJ m(-2) day(-1) and 0.939 in each climate region, respectively. Overall, we conclude that the SVM13 model is the most suitable model, and the model with a complex combination of more meteorological factors as input has higher simulation accuracy than the model with a relatively simple input combination.

引用

页码：1049 / 1064

页数：16

共 43 条

[1]

[Anonymous], ASES NAT SOL C M YOU

[2]

Bandy S., 2018, GEN SOLAR RAD ESTIMA

[3] Prediction of daily and mean monthly global solar radiation using support vector machine in an arid climate [J].