{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T18:43:45Z","timestamp":1784918625892,"version":"3.55.0"},"reference-count":53,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2020,7,22]],"date-time":"2020-07-22T00:00:00Z","timestamp":1595376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Meteorological satellite images provide crucial information on solar irradiation and weather conditions at spatial and temporal resolutions which are ideal for short-term photovoltaic (PV) power forecasts. Following the introduction of next-generation meteorological satellites, investigating their application on PV forecasts has become imminent. In this study, Communications, Oceans, and Meteorological Satellite (COMS) and Himawari-8 (H8) satellite images were inputted in a deep neural network (DNN) model for 2 hour (h)- and 1 h-ahead PV forecasts. A one-year PV power dataset acquired from two solar power test sites in Korea was used to directly forecast PV power. H8 was used as a proxy for GEO-KOMPSAT-2A (GK2A), the next-generation satellite after COMS, considering their similar resolutions, overlapping geographic coverage, and data availability. In addition, two different data sampling setups were designed to implement the input dataset. The first setup sampled chronologically ordered data using a relatively more inclusive time frame (6 a.m. to 8 p.m. in local time) to create a two-month test dataset, whereas the second setup randomly sampled 25% of data from each month from the one-year input dataset. Regardless of the setup, the DNN model generated superior forecast performance, as indicated by the lowest normalized mean absolute error (NMAE) and normalized root mean squared error (NRMSE) results in comparison to that of the support vector machine (SVM) and artificial neural network (ANN) models. The first setup results revealed that the visible (VIS) band yielded lower NMAE and NRMSE values, while COMS was found to be more influential for 1 h-ahead forecasts. For the second setup, however, the difference in NMAE results between COMS and H8 was not significant enough to distinguish a clear edge in performance. Nevertheless, this marginal difference and similarity of the results suggest that both satellite datasets can be used effectively for direct short-term PV forecasts. Ultimately, the comparative study between satellite datasets as well as spectral bands, time frames, forecast horizons, and forecast models confirms the superiority of the DNN and offers insights on the potential of transitioning to applying GK2A for future PV forecasts.<\/jats:p>","DOI":"10.3390\/rs12152357","type":"journal-article","created":{"date-parts":[[2020,7,23]],"date-time":"2020-07-23T11:26:01Z","timestamp":1595503561000},"page":"2357","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Direct Short-Term Forecast of Photovoltaic Power through a Comparative Study between COMS and Himawari-8 Meteorological Satellite Images in a Deep Neural Network"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9504-5935","authenticated-orcid":false,"given":"Minho","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Civil and Environmental Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6899-6770","authenticated-orcid":false,"given":"Hunsoo","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongil","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,7,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"109327","DOI":"10.1016\/j.rser.2019.109327","article-title":"A deep learning algorithm to estimate hourly global solar radiation from geostationary satellite data","volume":"114","author":"Jiang","year":"2019","journal-title":"Renew. Sustain. Energ. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1016\/j.solener.2004.09.009","article-title":"Development of a method for generating operational solar radiation maps from satellite data for a tropical environment","volume":"78","author":"Janjai","year":"2005","journal-title":"Sol. Energy"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2692","DOI":"10.1016\/j.rse.2010.06.010","article-title":"Improving the spatio-temporal distribution of surface solar radiation data by merging ground and satellite measurements","volume":"114","author":"Bertrand","year":"2010","journal-title":"Remote Sens. Environ."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.solener.2014.09.009","article-title":"Data-driven model for solar irradiation based on satellite observations","volume":"110","author":"Bilionis","year":"2014","journal-title":"Sol. Energy"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hassanzadeh, M., Etezadi-Amoli, M., and Fadali, M.S. (2010, January 26\u201328). Practical approach for sub-hourly and hourly prediction of PV power output. Proceedings of the North American Power Symposium 2010, Arlington, TX, USA.","DOI":"10.1109\/NAPS.2010.5618944"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1016\/j.enconman.2017.11.019","article-title":"Solar photovoltaic generation forecasting methods: A review","volume":"156","author":"Sobri","year":"2018","journal-title":"Energy Convers. Manag."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1016\/j.rser.2019.02.006","article-title":"Automatic hourly solar forecasting using machine learning models","volume":"105","author":"Yagli","year":"2019","journal-title":"Renew. Sustain. Energ. Rev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.solener.2016.06.069","article-title":"Review of photovoltaic power forecasting","volume":"136","author":"Antonanzas","year":"2016","journal-title":"Sol. Energy"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.solener.2018.01.005","article-title":"A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data","volume":"162","author":"Srivastava","year":"2018","journal-title":"Sol. Energy"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Bird, L., Cochran, J., and Wang, X. (2014). Wind and Solar Energy Curtailment: Experience and Practices in the United States, NREL.","DOI":"10.2172\/1126842"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.jclepro.2017.08.081","article-title":"Application of extreme learning machine for short term output power forecasting of three grid-connected PV systems","volume":"167","author":"Hossain","year":"2017","journal-title":"J. Clean. Prod."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Nam, S., and Hur, J. (2018). Probabilistic forecasting model of solar power outputs based on the naive Bayes classifier and kriging models. Energies, 11.","DOI":"10.3390\/en11112982"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1016\/j.rser.2017.02.069","article-title":"Review of the methods for evaluation of renewable energy sources penetration and ramping used in the Scenario Outlook and Adequacy Forecast 2015. Case study for Poland","volume":"74","author":"Andrychowicz","year":"2017","journal-title":"Renew. Sustain. Energ. Rev."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Alsharif, M.H., Kim, J., and Kim, J.H. (2018). Opportunities and challenges of solar and wind energy in South Korea: A review. Sustainability, 10.","DOI":"10.3390\/su10061822"},{"key":"ref_15","first-page":"e335","article-title":"The rise and fall of green growth: Korea\u2019s energy sector experiment and its lessons for sustainable energy policy","volume":"8","author":"Ha","year":"2019","journal-title":"Wiley Interdiscip. Rev. Energy Environ."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wojtkiewicz, J., Hosseini, M., Gottumukkala, R., and Chambers, T.L. (2019). Hour-Ahead Solar Irradiance Forecasting Using Multivariate Gated Recurrent Units. Energies, 12.","DOI":"10.3390\/en12214055"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.rser.2013.06.042","article-title":"Review of solar irradiance forecasting methods and a proposition for small-scale insular grids","volume":"27","author":"Diagne","year":"2013","journal-title":"Renew. Sustain. Energ. Rev."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"021011","DOI":"10.1115\/1.4038983","article-title":"Direct power output forecasts from remote sensing image processing","volume":"140","author":"Larson","year":"2018","journal-title":"J. Sol. Energy Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.solener.2016.05.051","article-title":"Comparing support vector regression for PV power forecasting to a physical modeling approach using measurement, numerical weather prediction, and cloud motion data","volume":"135","author":"Wolff","year":"2016","journal-title":"Sol. Energy"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/s00703-017-0559-0","article-title":"Short-term cloudiness forecasting for solar energy purposes in Greece, based on satellite-derived information","volume":"131","author":"Nikitidou","year":"2019","journal-title":"Meteorol. Atmos. Phys."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"463","DOI":"10.7848\/ksgpc.2015.33.5.463","article-title":"Solar irradiance estimation in Korea by using modified Heliosat-II method and COMS-MI imagery","volume":"33","author":"Choi","year":"2015","journal-title":"J. Korean Soc. Surv. Geod. Photogramm. Cartogr."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1109\/TSTE.2016.2535466","article-title":"Solar power prediction based on satellite images and support vector machine","volume":"7","author":"Jang","year":"2016","journal-title":"IEEE Trans. Sustain. Energ."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yeom, J.M., Park, S., Chae, T., Kim, J.Y., and Lee, C.S. (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. Sensors, 19.","DOI":"10.3390\/s19092082"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Koo, Y., Oh, M., Kim, S.M., and Park, H.D. (2020). Estimation and Mapping of Solar Irradiance for Korea by Using COMS MI Satellite Images and an Artificial Neural Network Model. Energies, 13.","DOI":"10.3390\/en13020301"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1007\/s13143-014-0047-0","article-title":"Development of GWNU (Gangneung-Wonju National University) one-layer transfer model for calculation of solar radiation distribution of the Korean peninsula","volume":"50","author":"Zo","year":"2014","journal-title":"Asia Pac. J. Atmos. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1016\/j.energy.2015.07.103","article-title":"Retrieval of surface solar irradiance, based on satellite-derived cloud information, in Greece","volume":"90","author":"Nikitidou","year":"2015","journal-title":"Energy"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1772","DOI":"10.1016\/j.solener.2009.05.016","article-title":"Online short-term solar power forecasting","volume":"83","author":"Bacher","year":"2009","journal-title":"Sol. Energy"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1016\/j.solener.2012.04.004","article-title":"Assessment of forecasting techniques for solar power production with no exogenous inputs","volume":"86","author":"Pedro","year":"2012","journal-title":"Sol. Energy"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"792","DOI":"10.1016\/j.solener.2013.12.006","article-title":"A benchmark of statistical regression methods for short-term forecasting of photovoltaic electricity production, part I: Deterministic forecast of hourly production","volume":"105","author":"Zamo","year":"2014","journal-title":"Sol. Energy"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1016\/j.solener.2014.03.026","article-title":"A benchmark of statistical regression methods for short-term forecasting of photovoltaic electricity production, Part II: Probabilistic forecast of daily production","volume":"105","author":"Zamo","year":"2014","journal-title":"Sol. Energy"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/S0038-092X(00)00038-4","article-title":"Short-term forecasting of solar radiation: A statistical approach using satellite data","volume":"67","author":"Hammer","year":"1999","journal-title":"Sol. Energy"},{"key":"ref_32","unstructured":"Lorenz, E., Hammer, A., and Heinemann, D. (2004, January 20\u201323). Short term forecasting of solar radiation based on satellite data. Proceedings of the EUROSUN2004 (ISES Europe Solar Congress), Freiburg, Germany."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1016\/j.solener.2013.02.023","article-title":"Hybrid solar forecasting method uses satellite imaging and ground telemetry as inputs to ANNs","volume":"92","author":"Marquez","year":"2013","journal-title":"Sol. Energy"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1016\/j.solener.2018.07.050","article-title":"Short-term forecasting of solar irradiance without local telemetry: A generalized model using satellite data","volume":"173","author":"Lago","year":"2018","journal-title":"Sol. Energy"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Song, H., Kim, G., Kim, M., and Kim, Y. (2019, January 1\u20134). Short-Term Forecasting of Photovoltaic Power Integrating Multi-Temporal Meteorological Satellite Imagery in Deep Neural Network. Proceedings of the 11th IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), Macao, China.","DOI":"10.1109\/APPEEC45492.2019.8994616"},{"key":"ref_36","unstructured":"Kim, G., Song, H., Kim, M., and Kim, Y. (2019, January 14\u201318). Multimodal Merging of Satellite Imagery with Meteorological and Power Plant Data in Deep Convolutional Neural Network for Short-Term Solar Energy Prediction. Proceedings of the 40th Asian Conference on Remote Sensing, Daejeon, Korea."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Choi, Y.Y., and Suh, M.S. (2018). Development of Himawari-8\/Advanced Himawari Imager (AHI) land surface temperature retrieval algorithm. Remote Sens., 10.","DOI":"10.3390\/rs10122013"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1007\/s13143-019-00156-3","article-title":"Development of GK-2A AMI Aerosol Detection Algorithm in the East-Asia Region Using Himawari-8 AHI Data","volume":"56","author":"Jee","year":"2020","journal-title":"Asia Pac. J. Atmos. Sci."},{"key":"ref_39","unstructured":"(2020, July 08). National Meteorological Satellite Center. Available online: http:\/\/datasvc.nmsc.kma.go.kr\/datasvc\/html\/main\/main.do?."},{"key":"ref_40","unstructured":"(2020, July 08). JAXA Himawari Monitor. Available online: http:\/\/www.eorc.jaxa.jp\/ptree\/index.html."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.solener.2014.11.017","article-title":"Short-term reforecasting of power output from a 48 MWe solar PV plant","volume":"112","author":"Chu","year":"2015","journal-title":"Sol. Energy"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.solener.2014.11.013","article-title":"Embedded nowcasting method using cloud speed persistence for a photovoltaic power plant","volume":"112","author":"Lipperheide","year":"2015","journal-title":"Sol. Energy"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.solener.2013.05.027","article-title":"Cloud motion vectors from a network of ground sensors in a solar power plant","volume":"95","author":"Bosch","year":"2013","journal-title":"Sol. Energy"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1016\/j.rser.2015.05.049","article-title":"Evaluation and performance comparison of different models for the estimation of solar radiation","volume":"50","author":"Teke","year":"2015","journal-title":"Renew. Sustain. Energ. Rev."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"884","DOI":"10.21105\/joss.00884","article-title":"pvlib python: A python package for modeling solar energy systems","volume":"3","author":"Holmgren","year":"2018","journal-title":"J. Open Source Softw."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Nespoli, A., Ogliari, E., Leva, S., Massi Pavan, A., Mellit, A., Lughi, V., and Dolara, A. (2019). Day-ahead photovoltaic forecasting: A comparison of the most effective techniques. Energies, 12.","DOI":"10.3390\/en12091621"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"81741","DOI":"10.1109\/ACCESS.2019.2923905","article-title":"Ensemble approach of optimized artificial neural networks for solar photovoltaic power prediction","volume":"7","author":"Ayadi","year":"2019","journal-title":"IEEE Access"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"912","DOI":"10.1016\/j.rser.2017.08.017","article-title":"Forecasting of photovoltaic power generation and model optimization: A review","volume":"81","author":"Das","year":"2018","journal-title":"Renew. Sustain. Energ. Rev."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1023\/B:STCO.0000035301.49549.88","article-title":"A tutorial on support vector regression","volume":"14","author":"Smola","year":"2004","journal-title":"Stat. Comput."},{"key":"ref_50","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_51","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_52","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2\u20134). Tensorflow: A system for large-scale machine learning. Proceedings of the 12th (USENIX) Symposium on Operating Systems Design and Implementation (OSDI 16), Savannah, GA, USA."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.matcom.2015.05.010","article-title":"Analysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power","volume":"131","author":"Leva","year":"2017","journal-title":"Math. Comput. Simulat."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/15\/2357\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:50:54Z","timestamp":1760176254000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/15\/2357"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,22]]},"references-count":53,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2020,8]]}},"alternative-id":["rs12152357"],"URL":"https:\/\/doi.org\/10.3390\/rs12152357","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,22]]}}}