A deep learning algorithm to estimate hourly global solar radiation from geostationary satellite data | |
Jiang, Hou2,3; Lu, Ning1,2; Qin, Jun4; Tang, Wenjun4; Yao, Ling1,2 | |
刊名 | RENEWABLE & SUSTAINABLE ENERGY REVIEWS |
2019-10-01 | |
卷号 | 114页码:13 |
关键词 | Global solar radiation Convolutional neural network Deep learning Geostationary satellite Temporal and spatial variations |
ISSN号 | 1364-0321 |
DOI | 10.1016/j.rser.2019.109327 |
通讯作者 | Lu, Ning(lvn@lreis.ac.cn) |
英文摘要 | To apply deep learning technique for estimating hourly global solar radiation (GSR) from geostationary satellite observations, a hybrid deep network is proposed, relying on convolutional neural network (CNN) to extract spatial pattern from satellite imagery, multi-layer perceptron (MLP) to link the abstract patterns and additional time/location information to target hourly GSR. Its representative advantage lies in the ability to characterize changeable cloud morphology and simulate complex non-linear relationships. The deep network is trained using ground measured GSR values at 90 Chinese radiation stations in 2008 as well as the radiative transfer model simulation at the top of Mt. Everest which serves as constraints of extrapolation for high elevation regions. The extensibility of trained network is validated at 5 independent stations in 2008, yielding an overall coefficient of determination (R-2) of 0.82, and at all stations in 2007 along with an R-2 of 0.88. Comparative experiments confirm that the combination of spatial pattern and point information can lead to more accurate estimation of hourly GSR, achieving a minimum root mean square error (RMSE) of 84.18 W/m(2) (0.30 MJ/m(2)), 1.92 MJ/m(2) and 1.08 MJ/m(2) in hourly, daily total and monthly total scales, respectively. Moreover, the deep network is capable of mapping spatially continuous hourly GSR which reflects the regional differences and reproduce the diurnal cycles of solar radiation properly. |
资助项目 | National Natural Science Foundation of China[41890854] |
WOS关键词 | ARTIFICIAL NEURAL-NETWORK ; INTELLIGENCE TECHNIQUES ; IRRADIANCE ; ENERGY ; MODEL ; PREDICTION |
WOS研究方向 | Science & Technology - Other Topics ; Energy & Fuels |
语种 | 英语 |
出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
WOS记录号 | WOS:000488871200004 |
资助机构 | National Natural Science Foundation of China |
内容类型 | 期刊论文 |
源URL | [http://ir.igsnrr.ac.cn/handle/311030/129492] |
专题 | 中国科学院地理科学与资源研究所 |
通讯作者 | Lu, Ning |
作者单位 | 1.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing 210023, Jiangsu, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 3.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Tibetan Plateau Res, Key Lab Tibetan Environm Changes & Land Surface P, Beijing 100085, Peoples R China |
推荐引用方式 GB/T 7714 | Jiang, Hou,Lu, Ning,Qin, Jun,et al. A deep learning algorithm to estimate hourly global solar radiation from geostationary satellite data[J]. RENEWABLE & SUSTAINABLE ENERGY REVIEWS,2019,114:13. |
APA | Jiang, Hou,Lu, Ning,Qin, Jun,Tang, Wenjun,&Yao, Ling.(2019).A deep learning algorithm to estimate hourly global solar radiation from geostationary satellite data.RENEWABLE & SUSTAINABLE ENERGY REVIEWS,114,13. |
MLA | Jiang, Hou,et al."A deep learning algorithm to estimate hourly global solar radiation from geostationary satellite data".RENEWABLE & SUSTAINABLE ENERGY REVIEWS 114(2019):13. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论