[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120880-en":3,"doc-seo-120880-105":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},120880,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Uncertainty estimation of machine learning spatial precipitation predictions from satellite data","Merging satellite precipitation retrievals with gauge observations through machine learning enables high-resolution gridded rainfall products, yet uncertainty estimates are frequently absent. This work benchmarks six algorithms for quantifying predictive uncertainty in spatial precipitation downscaling, focusing on approximating full predictive distributions at nine quantile levels. Using 15 years of monthly CONUS data with predictors from PERSIANN and IMERG plus elevation, performance is assessed via quantile scoring functions and the quantile scoring rule.","Uncertainty estimation of machine learning spatial precipitation predictions from satellite data  \nGeorgia Papacharalampous1,*, Hristos Tyralis2, Nikolaos Doulamis3, Anastasios Doulamis4  \n1 Department of Topography, School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, Iroon Polytechniou 5, 157 80 Zografou, Greece ([papacharalampous.georgia@gmail.com](papacharalampous.georgia@gmail.com), [gpapacharalampous@hydro.ntua.gr](gpapacharalampous@hydro.ntua.gr), [https://orcid.org/0000-0001-5446-954X](https://orcid.org/0000-0001-5446-954X))  \n2 Department of Topography, School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, Iroon Polytechniou 5, 157 80 Zografou, Greece ([montchrister@gmail.com](montchrister@gmail.com), [hristos@itia.ntua.gr](hristos@itia.ntua.gr), [https://orcid.org/0000-0002-8932-](https://orcid.org/0000-0002-8932-)[ ](https://orcid.org/0000-0002-8932-)4997)  \n3 Department of Topography, School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, Iroon Polytechniou 5, 157 80 Zografou, Greece ([ndoulam@cs.ntua.gr](ndoulam@cs.ntua.gr), [https://orcid.org/0000-0002-4064-8990](https://orcid.org/0000-0002-4064-8990))  \n4 Department of Topography, School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, Iroon Polytechniou 5, 157 80 Zografou, Greece ([adoulam@cs.ntua.gr](adoulam@cs.ntua.gr), [https://orcid.org/0000-0002-0612-5889](https://orcid.org/0000-0002-0612-5889))  \n* Corresponding author  \nThis is the accepted manuscript of an article published in Machine Learning: Science and Technology. Please cite the article as: Papacharalampous GA, Tyralis H, Doulamis N, Doulamis A (2024) Uncertainty estimation of machine learning spatial precipitation predictions from satellite data. Machine Learning: Science and Technology 5:035044 .  \n[https://doi.org/10.1088/2632-2153/ad63f3](https://doi.org/10.1088/2632-2153/ad63f3)  \nAbstract: Merging satellite and gauge data with machine learning produces highresolution precipitation datasets, but uncertainty estimates are often missing. We addressed the gap of how to optimally provide such estimates by benchmarking six algorithms, mostly novel even for the more general task of quantifying predictive uncertainty in spatial prediction settings. On 15 years of monthly data from over the  \ncontiguous United States (CONUS), we compared quantile regression (QR), quantile regression forests (QRF), generalized random forests (GRF), gradient boosting machines (GBM), light gradient boosting machine (LightGBM), and quantile regression neural networks (QRNN). Their ability to issue predictive precipitation quantiles at nine quantile levels (0.025, 0.050, 0.100, 0.250, 0.500, 0.750, 0.900, 0.950, 0.975), approximating the full probability distribution, was evaluated using quantile scoring functions and the quantile scoring rule. Predictors at a site were nearby values from two satellite precipitation retrievals, namely PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks) and IMERG (Integrated MultisatellitE Retrievals), and the site’s elevation. The dependent variable was the monthly mean gauge precipitation. With respect to QR, LightGBM showed improved performance in terms of the quantile scoring rule by 11.10%, also surpassing QRF (7.96%), GRF (7.44%), GBM (4.64%) and QRNN (1.73%). Notably, LightGBM outperformed all random forest variants, the current standard in spatial prediction with machine learning. To conclude, we propose a suite of machine learning algorithms for estimating uncertainty in spatial data prediction, supported with a formal evaluation framework based on scoring functions and scoring rules.  \nKeywords: bias correction; precipitation downscaling; probabilistic prediction; scoring functions; scoring rules; uncertainty quantification  \n1. Introduction  \nMerging s","cbCaihB16uRBkOVt","https://ap.wps.com/l/cbCaihB16uRBkOVt","pdf",1918065,1,27,"English","en",105,"# Introduction\n## Satellite–gauge data merging for precipitation downscaling\n## Regression-to-spatial prediction and the need for uncertainty\n## Quantifying predictive uncertainty via probabilistic forecasts","[{\"question\":\"Why is uncertainty estimation important for spatial precipitation predictions from satellite data?\",\"answer\":\"Satellite-guided spatial downscaling can correct biases using sparse gauges, but resulting predictions still contain uncertainty. Quantifying predictive uncertainty supports better decisions than point estimates alone.\"},{\"question\":\"Which algorithms are benchmarked for predictive uncertainty estimation in this study?\",\"answer\":\"The study benchmarks quantile regression (QR), quantile regression forests (QRF), generalized random forests (GRF), gradient boosting machines (GBM), LightGBM, and quantile regression neural networks (QRNN).\"},{\"question\":\"How is model performance evaluated for predicting precipitation quantiles?\",\"answer\":\"Performance is evaluated by predicting precipitation quantiles at nine levels and scoring them using quantile scoring functions and the quantile scoring rule.\"}]","Uncertainty estimation of machine learning spatial precipitation predictions from satellite data | PDF",1785732467,68,{"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},"uncertainty-estimation-of-machine-learning-spatial-precipitation-predictions-from-satellite-data","",{"@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/uncertainty-estimation-of-machine-learning-spatial-precipitation-predictions-from-satellite-data/120880/",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","2026-08-03",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},"Why is uncertainty estimation important for spatial precipitation predictions from satellite data?","Question",{"text":75,"@type":76},"Satellite-guided spatial downscaling can correct biases using sparse gauges, but resulting predictions still contain uncertainty. Quantifying predictive uncertainty supports better decisions than point estimates alone.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which algorithms are benchmarked for predictive uncertainty estimation in this study?",{"text":80,"@type":76},"The study benchmarks quantile regression (QR), quantile regression forests (QRF), generalized random forests (GRF), gradient boosting machines (GBM), LightGBM, and quantile regression neural networks (QRNN).",{"name":82,"@type":73,"acceptedAnswer":83},"How is model performance evaluated for predicting precipitation quantiles?",{"text":84,"@type":76},"Performance is evaluated by predicting precipitation quantiles at nine levels and scoring them using quantile scoring functions and the quantile scoring rule.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]