[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127009-en":3,"doc-seo-127009-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127009,2336474466412,"Ezra","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","A Physics-Informed Machine Learning Approach Utilizing Multiband Satellite Data for Solar Irradiance Estimation - Proceedings Paper","Solar irradiance is essential for weather and climate analyses, and high-precision estimation supports the creation of gridded, areal products that reflect regional characteristics. This study develops a physics-informed machine learning framework using multiband meteorological satellite observations. To prevent overfitting under clear-sky and thin-cloud conditions, the model incorporates physical and meteorological prior knowledge, including a radiative transfer model and clear-sky probability. Validation results demonstrate significantly improved estimation accuracy.","A Physics-Informed Machine Learning Approach utilizing Multiband Satellite  \nData for Solar Irradiance Estimation  \nJun Sasaki * 1 Maki Okada * 1 Kenji Utsunomiya 1 Koji Yamaguchi 1  \narXiv:2407.04283v1 [[physics. ao-ph](physics. ao-ph)] 5 Jul 2024  \nAbstract  \nSolar irradiance is fundamental data crucial for analyses related to weather and climate. Highprecision estimation models are necessary to create areal data for solar irradiance. In this study, we developed a novel estimation model by utilizing machine learning and multiband data from meteorological satellite observations. Particularly under clear-sky and thin clouds, satellite observations can be influenced by surface reflections, which may lead to overfitting to ground observations. To make the model applicable at any location, we constructed the model incorporating prior information such as radiative transfer models and clear-sky probability, based on physical and meteorological knowledge. As a result, the estimation accuracy significantly improved at validation sites.  \n1. Introduction  \nSolar irradiance data is essential for monitoring solar power, assessing potential output, climate simulations, and climate monitoring. These applications often require high-precision areal data reflecting regional characteristics. In principle, it is possible to estimate solar irradiance through radiative transfer calculations (Mueller et al., 2009 ; Xie et al., 2016 ; Zhang et al., 2018); however there are some challenges such as cloud modeling and computational costs. As a result, statistical models based on meteorological satellite data are widely used (Engerer et al., 2017 ; Saito et al., 2018 ; Hashimoto & Yoshimoto, 2023) .  \nHowever, these standard models are simplistic, utilizing limited band information. For example, Saito et al. (2018) uses visible and infrared band data for weather classification with  \n*Equal contribution 1Department of Environment and Energy, Japan Weather Association, Tokyo, Japan. Correspondence to: Jun Sasaki \u003C[sasaki.jun@jwa.or.jp](sasaki.jun@jwa.or.jp) >, Maki Okada \u003C[okada.maki@jwa.or.jp](okada.maki@jwa.or.jp) >.  \nProceedings of the Machine Learning for Earth System Modeling workshop at the 41 st International Conference on Machine Learning, Vienna, Austria. Copyright 2024 by the author(s) .  \nrule-based algorithms and piecewise linear regression for estimation. Actually, the relationship between solar irradiance and satellite observations is highly complex due to the diversity of clouds, suggesting that combining multiband observation data with machine learning models can lead to more precise estimations of solar irradiance.  \nIn previous studies where machine learning was applied to solar irradiance estimation models, primarily limited elements such as the visible band and simpler architectures like MLPs (Multilayer Perceptrons) were used, indicating that there is potential for improvement in accuracy (CornejoBueno et al., 2019 ; Jiang et al., 2019 ; Yeom et al., 2019 ; Palacios et al., 2022) .  \nThis study aims to develop a high-precision model applicable at any location, leveraging multiband satellite images and machine learning. To avoid overfitting to ground observations and ensure applicability at any site, we incorporated constraints based on physical and meteorological knowledge to enhance the model’s generalizability. we have quantitatively demonstrated the model’s superiority by comparing it with the Saito’s standard model (2018) under consistent conditions.  \n2. Data description  \nIn this study, we used satellite image data from Japan’s Himawari-8, the imager on board of which has 16 observation bands ranging from 0 .47µm to 13.3µm in wavelength. Six of these bands are in the shortwave spectrum (visible and near-infrared) and ten in the longwave spectrum (infrared), with the visible bands strongly correlating with solar irradiance due to their high spectral intensity. Near-infrared bands reflect the size and phase state (water or ice","cbCaid9wavfE9TEz","https://ap.wps.com/l/cbCaid9wavfE9TEz","pdf",609677,1,5,"English","en",105,"# Introduction\n## Data description\n## Methodology\n## Clear-Sky Solar Irradiance Estimation Model","[{\"question\":\"What problem does the study address in solar irradiance estimation?\",\"answer\":\"It targets the need for high-precision, areal solar irradiance estimates suitable for weather, climate simulation, and monitoring.\"},{\"question\":\"Why can conventional satellite-based models fail to generalize?\",\"answer\":\"Standard approaches often use limited band information, and under clear skies and thin clouds satellite signals can be affected by surface reflections, which may cause overfitting to ground observations.\"},{\"question\":\"How does the proposed approach improve generalizability to new locations?\",\"answer\":\"It integrates prior physical and meteorological information, including a radiative transfer model and clear-sky probability, into a machine learning framework so the model applies beyond the training sites.\"}]","A Physics-Informed Machine Learning Approach Utilizing Multiband Satellite Data for Solar Irradiance Estimation - Proceedings Paper | PDF",1785936263,13,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-physics-informed-machine-learning-approach-utilizing-multiband-satellite-data-for-solar-irradiance-estimation-proceedings-paper","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-physics-informed-machine-learning-approach-utilizing-multiband-satellite-data-for-solar-irradiance-estimation-proceedings-paper/127009/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address in solar irradiance estimation?","Question",{"text":75,"@type":76},"It targets the need for high-precision, areal solar irradiance estimates suitable for weather, climate simulation, and monitoring.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why can conventional satellite-based models fail to generalize?",{"text":80,"@type":76},"Standard approaches often use limited band information, and under clear skies and thin clouds satellite signals can be affected by surface reflections, which may cause overfitting to ground observations.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed approach improve generalizability to new locations?",{"text":84,"@type":76},"It integrates prior physical and meteorological information, including a radiative transfer model and clear-sky probability, into a machine learning framework so the model applies beyond the training sites.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":21,"slug":137},19,"General","general"]