气候变化领域集成服务门户(CCPortal): Spatial mapping of short-term solar radiation prediction incorporating geostationary satellite images coupled with deep convolutional LSTM networks for South Korea

CCPortal

DOI	10.1088/1748-9326/ab9467
	Spatial mapping of short-term solar radiation prediction incorporating geostationary satellite images coupled with deep convolutional LSTM networks for South Korea
	Yeom J.-M.; Deo R.C.; Adamowski J.F.; Park S.; Lee C.-S.
发表日期	2020
ISSN	17489318
卷号	15 期号:9
英文摘要	A practical approach to continuously monitor and provide real-time solar energy prediction can help support reliable renewable energy supply and relevant energy security systems. In this study on the Korean Peninsula, contemporaneous solar radiation images obtained from the Communication, Ocean and Meteorological Satellite (COMS) Meteorological Imager (MI) system, were used to design a convolutional neural network and a long short-term memory network predictive model, ConvLSTM. This model was applied to predict one-hour ahead solar radiation and spatially map solar energy potential. The newly designed ConvLSTM model enabled reliable prediction of solar radiation, incorporating spatial changes in atmospheric conditions and capturing the temporal sequence-to-sequence variations that are likely to influence solar driven power supply and its overall stability. Results showed that the proposed ConvLSTM model successfully captured cloud-induced variations in ground level solar radiation when compared with reference images from a physical model. A comparison with ground pyranometer measurements indicated that the short-term prediction of global solar radiation by the proposed ConvLSTM had the highest accuracy [root mean square error (RMSE) = 83.458 W • m-2, mean bias error (MBE) = 4.466 W • m-2, coefficient of determination (R2) = 0.874] when compared with results of conventional artificial neural network (ANN) [RMSE = 94.085 W • m-2, MBE =-6.039 W • m-2, R2 = 0.821] and random forest (RF) [RMSE = 95.262 W • m-2, MBE =-11.576 W • m-2, R2 = 0.839] models. In addition, ConvLSTM better captured the temporal variations in predicted solar radiation, mainly due to cloud attenuation effects when compared with two selected ground stations. The study showed that contemporaneous satellite images over short-term or near real-time intervals can successfully support solar energy exploration in areas without continuous environmental monitoring systems, where satellite footprints are available to model and monitor solar energy management systems supporting real-life power grid systems. © 2020 The Author(s). Published by IOP Publishing Ltd.
英文关键词	COMS-MI; Convolutional neural network; Deep learning; Long short-term memory; Pyranometer; Solar radiation prediction
语种	英语
scopus关键词	Continuous time systems; Convolution; Convolutional neural networks; Decision trees; Electric power transmission networks; Energy management systems; Energy policy; Energy security; Environmental management; Forecasting; Geostationary satellites; Mean square error; Monitoring; Predictive analytics; Radiation effects; Real time systems; Solar energy; Solar power generation; Solar power plants; Solar power satellites; Solar radiation; Atmospheric conditions; Coefficient of determination; Environmental monitoring system; Global solar radiation; Predictive modeling; Root mean square errors; Short term prediction; Solar radiation predictions; Long short-term memory; geostationary satellite; machine learning; prediction; satellite imagery; solar radiation; spatial data; South Korea
来源期刊	Environmental Research Letters
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/153802
作者单位	Satellite Application Division, Korea Aerospace Research Institute, 115 Gwahangno, Yuseong-gu, Daejeon, 34133, South Korea; Centre for Sustainable Agricultural Systems, School of Sciences, University of Southern QueenslandQLD 4300, Australia; Department of Bioresource Engineering, Faculty of Agricultural and Environmental Sciences, McGill University, Montreal, Canada; National Institute of Environmental Research, 42 Hwangyong-ro, Seogu, Incheon, 22689, South Korea
推荐引用方式 GB/T 7714	Yeom J.-M.,Deo R.C.,Adamowski J.F.,et al. Spatial mapping of short-term solar radiation prediction incorporating geostationary satellite images coupled with deep convolutional LSTM networks for South Korea[J],2020,15(9).
APA	Yeom J.-M.,Deo R.C.,Adamowski J.F.,Park S.,&Lee C.-S..(2020).Spatial mapping of short-term solar radiation prediction incorporating geostationary satellite images coupled with deep convolutional LSTM networks for South Korea.Environmental Research Letters,15(9).
MLA	Yeom J.-M.,et al."Spatial mapping of short-term solar radiation prediction incorporating geostationary satellite images coupled with deep convolutional LSTM networks for South Korea".Environmental Research Letters 15.9(2020).