[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122215-en":3,"doc-seo-122215-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},122215,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","CLOUD DETECTION AND PM2:5 ESTIMATION USING MACHINE LEARNING - Dissertation","Machine learning methods are developed to address key challenges in Earth observation–based PM2:5 analysis, including gaps caused by clouds and limitations of data availability and quality in cloud-contaminated areas. The work includes three connected studies: cloud pixel detection from remote sensing imagery using labeled Landsat 8 subsets; high temporal resolution PM2:5 modeling using NEXRAD weather radar with meteorological inputs and local ground observations; and nationwide PM2:5 estimation combining GOES-16 high temporal AOD, meteorological variables, and ancillary datasets.","CLOUD DETECTION AND PM2:5 ESTIMATION USING MACHINE LEARNING  \nby  \nXiaohe Yu  \nAPPROVED BY SUPERVISORY COMMITTEE:  \n\n| Yongwan Chun, Co-Chair |\n| --- |\n| David J. Lary, Co-Chair |\n| Fang Qiu |\n\nMay Yuan  \nCopyright © 2021 Xiaohe Yu  \nAll rights reserved  \nCLOUD DETECTION AND PM2:5 ESTIMATION USING MACHINE LEARNING  \nby  \nXIAOHE YU, BS, MS  \nDISSERTATION  \nPresented to the Faculty of  \nThe University of Texas at Dallas in Partial Ful􀀌llment of the Requirements  \nfor the Degree of  \nDOCTOR OF PHILOSOPHY IN  \nGEOSPATIAL INFORMATION SCIENCES  \nTHE UNIVERSITY OF TEXAS AT DALLAS  \nDecember 2021  \nACKNOWLEDGMENTS  \nMy sincere gratitude is extended to both my advisors, Dr. Yongwan Chun and Dr. David J. Lary, for their encouragement and assistance throughout my PhD period. It was their knowledge, experience, and rigorous academic attitude that encouraged me throughout my academic career. I am grateful for the time and patience they have given to proofread andreexamine various aspects of my dissertation.  \nI would like to express my gratitude to Dr. Qiu Fang and Dr. May Yuan for serving as my committee, and for their valuable comments and suggestions to help improve my research.  \nI appreciate Dr. Simmons' contribution for his time and e􀀋ort in providing technical assistance. Also, I would like to thank my lab mates, Lakitha Wijeratne and Yichao Zhang, for their support to my research.  \nPlease accept my sincerest gratitude for the continuous and unparalleled love, assistance and support I have received from my family. This academic journey would not have been possible if not for them.  \nNovember 2021  \nCLOUD DETECTION AND PM2:5 ESTIMATION USING MACHINE LEARNING  \nXiaohe Yu, PhD  \nThe University of Texas at Dallas, 2021  \nSupervising Professors: Yongwan Chun, Co-Chair  \nDavid J. Lary, Co-Chair  \nEarth observation (EO) is the gathering of information about the physical, chemical, and biological systems of the planet via remote-sensing technologies, supplemented by Earthsurveying techniques, which encompasses the collection, analysis, and presentation of data. Research on exploring e􀀋ective methods for earth observation data analysis has increased over the years because of the increasing amount of data generated by earth observation systems, such as remote sensing imagery and weather radars. Researchers have therefore taken an interest in machine learning, a technique that allows computer algorithms to learn from samples. In general, the more comprehensive our training samples are, the better the machine learning performance will be. This feature makes machine learning an ideal approach for analyzing earth observation data. Particulate matter of 􀀌ne size, such as particulate matter 2.5 (PM2:5), poses a severe health risk to humans and is associated with many di􀀋erent health problems. PM2:5 concentrations are in􀀍uenced by factors such as meteorological conditions, local population density, and the geographic context. As a result of the large quantity of information provided by Earth observation, they become a valuable tool for studying PM2:5 . They are huge and come from di􀀋erent platforms, with di􀀋erent spatial and temporal resolutions, and in di􀀋erent formats, which challenge the approaches for PM2:5 studies.  \nThis dissertation shows how machine learning methods can be used to address these challenges in three subtopics connected to modeling and estimation for PM2:5 . Satellite-based remote sensing products provide important variables that can be used to study regional and global PM2:5, such as the Aerosol Optical Depth (AOD) . Nevertheless, AOD products in cloudy areas cannot be retrieved, and the quality of AOD data in nearby cloud areas cannot be guaranteed.  \nAccordingly, the 􀀌rst study aims to detect cloud pixels based on remote sensing images. This study investigates the cloud detection with a set of machine learning models on four subsets of 88 Landsat8 images that have been carefully labelled by analysts. Four subsets of trainin","cbCaitN6ldNuf0ko","https://ap.wps.com/l/cbCaitN6ldNuf0ko","pdf",26283449,1,127,"English","en",105,"# Introduction\n## Earth observation and PM2.5 motivation\n# Cloud detection study\n## Machine learning models and training design\n## Comparison with Fmask\n# High temporal resolution PM2.5 modeling\n## Data sources and dataset period\n## Impact of NEXRAD\n# Nationwide PM2.5 estimation\n## GOES-16 AOD, meteorology, and ancillary data\n# Conclusion","[{\"question\":\"Why is cloud handling critical for PM2:5 studies using remote sensing?\",\"answer\":\"AOD products cannot be reliably retrieved in cloudy areas, and the quality near clouds cannot be guaranteed. This directly limits downstream PM2:5 modeling and estimation.\"},{\"question\":\"How was cloud detection performed in the first study?\",\"answer\":\"Cloud pixels were detected using 16 machine learning models trained on four carefully labeled subsets of 88 Landsat 8 images. Model performance was compared against the Fmask algorithm.\"},{\"question\":\"What data were used for the high temporal resolution PM2:5 models and how did radar help?\",\"answer\":\"The models used weather radar data (NEXRAD) plus meteorological inputs from ECMWF and PM2:5 ground observations from 31 sensors across several Dallas-area counties. The version using NEXRAD achieved higher performance (R2 about 0.855 versus about 0.7 without NEXRAD).\"}]","CLOUD DETECTION AND PM2:5 ESTIMATION USING MACHINE LEARNING - Dissertation | PDF",1785809397,320,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"cloud-detection-and-pm25-estimation-using-machine-learning-dissertation","",{"@graph":36,"@context":86},[37,54,69],{"@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/cloud-detection-and-pm25-estimation-using-machine-learning-dissertation/122215/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is cloud handling critical for PM2:5 studies using remote sensing?","Question",{"text":76,"@type":77},"AOD products cannot be reliably retrieved in cloudy areas, and the quality near clouds cannot be guaranteed. This directly limits downstream PM2:5 modeling and estimation.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How was cloud detection performed in the first study?",{"text":81,"@type":77},"Cloud pixels were detected using 16 machine learning models trained on four carefully labeled subsets of 88 Landsat 8 images. Model performance was compared against the Fmask algorithm.",{"name":83,"@type":74,"acceptedAnswer":84},"What data were used for the high temporal resolution PM2:5 models and how did radar help?",{"text":85,"@type":77},"The models used weather radar data (NEXRAD) plus meteorological inputs from ECMWF and PM2:5 ground observations from 31 sensors across several Dallas-area counties. The version using NEXRAD achieved higher performance (R2 about 0.855 versus about 0.7 without NEXRAD).","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]