[논문]Spatial mapping of short-term solar radiation prediction incorporating geostationary satellite images coupled with deep convolutional LSTM networks for South Korea

Yeom, Jong-Min; Deo, Ravinesh C; Adamowski, Jan F; Park, Seonyoung; Lee, Chang-Suk

doi:10.1088/1748-9326/ab9467

[해외논문] Spatial mapping of short-term solar radiation prediction incorporating geostationary satellite images coupled with deep convolutional LSTM networks for South Korea 원문보기

Environmental research letters : ERL, v.15 no.9, 2020년, pp.094025 -

Yeom, Jong-Min , Deo, Ravinesh C , Adamowski, Jan F , Park, Seonyoung , Lee, Chang-Suk

Abstract ▼ AI-Helper

AbstractA 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.

참고문헌 (59)

Appl. Energy Voyant 10.1016/j.renene.2016.12.095 105 569 2017 Machine learning methods for solar radiation forecasting: a review

상세보기
Appl. Energy Liu 10.1016/j.apenergy.2019.113596 253 2019 Ensemble spatiotemporal forecasting of solar irradiance using variational Bayesian convolutional gate recurrent unit network

상세보기
Energy Fouilloy 10.1016/j.energy.2018.09.116 165 620 2018 Solar irradiance prediction with machine learning: forecasting models selection method depending on weather variability

상세보기
Appl. Energy Lou 10.1016/j.apenergy.2016.08.093 181 367 2016 Prediction of diffuse solar irradiance using machine learning and multivariable regression

상세보기
Sol. Energy Martín 10.1016/j.solener.2010.07.002 84 1772 2010 Prediction of global solar irradiance based on time series analysis: application to solar thermal power plants energy production planning

상세보기
Sol. Energy Perez 10.1016/j.solener.2013.05.005 94 305 2013 Comparison of numerical weather prediction solar irradiance forecasts in the US, Canada and Europe

상세보기
Bull. Am. Meteor. Soc. Sun 10.1175/BAMS-D-11-00263.1 409 2014 Use of NWP for nowcasting convective precipitation: recent progress and challenges

상세보기
Prog. Energy Combust. Sci. Inman 10.1016/j.pecs.2013.06.002 39 535 2013 Solar forecasting methods for renewable energy integration

상세보기
Appl. Energy Deo 10.1016/j.apenergy.2016.01.130 168 568 2016 A wavelet-coupled support vector machine model for forecasting global incident solar radiation using limited meteorological dataset

상세보기
Appl. Energy Salcedo-Sanz 10.1016/j.apenergy.2017.10.076 209 79 2018 An efficient neuro-evolutionary hybrid modelling mechanism for the estimation of daily global solar radiation in the Sunshine State of Australia

상세보기
Renew. Sustain. Energy Rev. Ghimire 10.1016/j.rser.2019.109247 113 2019 Wavelet-based 3-phase hybrid SVR model trained with satellite-derived predictors, particle swarm optimization and maximum overlap discrete wavelet transform for solar radiation prediction

상세보기
Sol. Energy Behrang 10.1016/j.solener.2010.05.009 84 1468 2010 The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data

상세보기
Renew. Energy Huang 10.1016/j.renene.2014.07.015 72 195 2014 An analytical comparison of four approaches to modelling the daily variability of solar irradiance using meteorological records

상세보기
Sensors Yeom 10.3390/s19092082 19 2082 2019 Spatial assessment of solar radiation by machine learning and deep neural network models using data provided by the COMS MI geostationary satellite: a case study in South Korea

상세보기
Renew. Sustain. Energy Rev. Wang 10.1016/j.rser.2016.04.024 61 384 2016 Solar radiation prediction using different techniques: model evaluation and comparison

상세보기
Renew. Energy Zou 10.1016/j.renene.2017.01.042 106 343 2017 Prediction and comparison of solar radiation using improved empirical models and adaptive neuro-fuzzy inference systems

상세보기
Appl. Energy Fadare 10.1016/j.apenergy.2008.12.005 86 1410 2009 Modelling of solar energy potential in Nigeria using an artificial neural network model

상세보기
Bull. Math. Biophys. McCulloch 10.1007/BF02478259 5 115 1943 A logical calculus of the ideas immanent in nervous activity

상세보기
Renew. Sustain. Energy Rev. Keshtegar 10.1016/j.rser.2017.07.054 81 330 2018 Comparison of four heuristic regression techniques in solar radiation modeling: kriging method vs RSM, MARS and M5 model tree

상세보기
Renew. Sustain. Energy Rev. Qin 10.1016/j.rser.2017.08.037 81 579 2018 Comparison of deterministic and data-driven models for solar radiation estimation in China

상세보기
Renew. Sustain. Energy Rev. Deo 10.1016/j.rser.2017.01.114 72 828 2017 Forecasting long-term global solar radiation with an ANN algorithm coupled with satellite-derived (MODIS) land surface temperature (LST) for regional locations in Queensland

상세보기
J. Climate. Qin 10.1175/JCLI-D-18-0590.1 32 2761 2019 First effort at constructing a high-density photosynthetically active radiation dataset during 1961-2014 in China

상세보기
Remote Sens. Ndikumana 10.3390/rs10081217 10 1217 2018 Deep recurrent neural network for agricultural classification using multi temporal SAR Sentinel-1 for Camargue, France

상세보기
Remote Sens. Wang 10.3390/rs10071068 10 1068 2018 A fast dense spectral-spatial convolution network framework for hyperspectral images classification

상세보기
Atmos. Environ. Yu 10.1016/j.atmosenv.2019.117198 223 2020 Clear-sky solar radiation changes over arid and semi-arid areas in China and their determining factors during 2001-2015

상세보기
Int. J. Control. Chen 10.1080/00207179208934317 56 319 1992 Neural networks for nonlinear dynamic system modeling and identification

상세보기
Neural. Comput. LeRoux 10.1162/neco.2010.08-09-1081 22 2192 2010 Deep belief networks are compact universal approximators

상세보기
Ciresan 10.1109/CVPR.2012.6248110 p 3642 2012 Multi-column deep neural networks for image classification
IEEE Trans. Pattern Anal. Machine Intel. Kruger 10.1109/TPAMI.2012.272 35 1847 2013 Deep hierarchies in the primate visual cortex: what can we learn for computer vision?

상세보기
Sci. Total Environ. Qi 10.1016/j.scitotenv.2019.01.333 664 1 2019 A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory

상세보기
IEEE Geosci. Remote Sens. Mag. Zhu 10.1109/MGRS.2017.2762307 5 8 2017 Deep learning in remote sensing: a comprehensive review and list of resources

상세보기
Energies Ghimire 10.3390/en12122407 12 1 2019 Deep learning neural networks trained with MODIS satellite-derived predictors for long-term global solar radiation prediction

상세보기
Appl. Energy Ghimire 10.1016/j.apenergy.2019.113541 253 2019 Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms

상세보기
J. Clean. Prod. Ghimire 10.1016/j.jclepro.2019.01.158 216 288 2019 Global solar radiation prediction by ANN integrated with European Centre for medium range weather forecast fields in solar rich cites of Queensland Australia

상세보기
Neural. Comput. Hinton 10.1162/neco.2006.18.7.1527 18 1527 2006 The YW. A fast learning algorithm for deep belief nets

상세보기
Hinton 2012 Improving neural networks by preventing co-adaptation of feature detectors
Nair p 807 2010 Rectified linear units improve restricted Boltzmann Machines
Hydrol. Earth Syst. Sci. Peel 10.5555/3104322.3104425 11 1633 2007 Updated world map of the Köppen-Geiger climate classiﬁcation
2009 Development of meteorological data processing system for communication, ocean and meteorological satellite (ATBD)
Korean J. Remote Sens. Kim 10.7780/kjrs.2016.32.6.16 32 733 2016 The sensitivity analysis to observed frequency of daily composite insolation based on COMS

원문보기 상세보기
J. Oceanogr. Kawai 10.1007/s10872-005-0021-7 61 79 2005 Validation and improvement of satellite-derived surface solar radiation over the northwestern Pacific Ocean

상세보기
J. Oceanogr. Kawamura 10.1007/BF02742448 54 457 1998 Estimation of insolation over Pacific Ocean off the Sanriku Coast

상세보기
Asia-Pacific J. Atmos. Sci. Yeom 10.1007/s13143-012-0011-9 48 115 2012 Evaluation on penetration rate of cloud for incoming solar radiation using geostationary satellite data

상세보기
J. Sens. Yeom 10.1155/2016/4834579 2016 1 2016 Solar radiation received by slopes using COMS imagery, a physically-based radiation model, and GLOBE

상세보기
IEEE Trans. Neural Network. Bengio 10.1109/72.279181 5 157 1994 Learning long-term dependencies with gradient descent is difficult

상세보기
Hochreiter 237 2001
ISPRS Annal. Photogram. Remote Sens. Spatial Inf. Sci. Fan 10.5194/isprs-annals-IV-4-W2-15-2017 4 15 2017 A spatiotemporal prediction framework for air pollution based on deep RNN

상세보기
ISPRS Annal. Photogram. Remote Sens. Spatial Inf. Sci. Gong 10.5194/isprs-annals-IV-4-W2-153-2017 4 153 2017 Spatio-temporal simulation and analysis of regional ecological security based on LSTM

상세보기
Shi 2015 Convolutional LSTM network: a machine learning approach for precipitation nowcasting
Paparaju 2018 Video frame prediction with Keras
Pearce 2017 CIKM AnalytiCup 2017 challenge entry
Ioffe 2015 Batch normalization: accelerating deep network training by reducing internal covariate shift
He 1026 2015 Delving deep into rectifiers: surpassing human-level performance on ImageNet classification
Glorot p 249 2010 Understanding the difficulty of training deep feedforward neural networks
Comput. Geosci. Yeom 10.1016/j.cageo.2009.08.012 36 590 2010 Improved estimation of surface solar insolation using a neural network and MTSAT-1R data

상세보기
Mach. Learn. Breiman 10.1023/A:1010933404324 45 5 2001 Random forests
Atmos. Chem. Phys. Park 10.5194/acp-19-1097-2019 19 1097 2019 Estimation of ground-level particulate matter concentrations through the synergistic use of satellite observations and process-based models over South Korea

상세보기
Cook 2016
Renew. Sustain. Energy Rev. Qin 10.1016/j.rser.2017.08.037 81 579 2018 Comparison of deterministic and data-driven models for solar radiation estimation in China

상세보기

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증