[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127281-en":3,"doc-seo-127281-105":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},127281,2336475104362,"Eden","https://ap-avatar.wpscdn.com/avatar/22000c4c46a41b752dd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786595829695023868",8,"Research & Report","Automated Solar PV Analysis with Machine Learning and Computer Vision - Dataset and Methodology - thesis","Solar power is critical under climate change, yet maintaining rapidly expanding solar photovoltaic installations is costly and slow when panels are manually inspected for defects or obstructions. This thesis introduces the De-Solar dataset for solar PV obstruction, develops SolarFormer++, a machine learning and computer vision system building on SolarFormer, and presents De-Solar v2.0, a multimodal dataset combining multispectral remote-sensing imagery with environmental factors and related data for improved analysis.","University of Arkansas, Fayetteville  \nScholarWorks@UARK  \n\n| Electrical Engineering and Computer Science Undergraduate Honors Theses | Electrical Engineering and Computer Science |\n| --- | --- |\n| 5-2025\u003Cbr>Automated Solar PV Analysis with Machine Learning and Computer Vision: Dataset and Methodology\u003Cbr>Malachi Massey\u003Cbr>University of Arkansas, Fayetteville, [malachi.massey.dev@gmail.com](malachi.massey.dev@gmail.com)\u003Cbr>Follow this and additional works at: [https://scholarworks.uark.edu/elcsuht](https://scholarworks.uark.edu/elcsuht)\u003Cbr> Part of the Artificial Intelligence and Robotics Commons\u003Cbr>Click here to let us know how this document benefits you. |  |\n\nCitation  \nMassey, M. (2025) . Automated Solar PV Analysis with Machine Learning and Computer Vision: Dataset and Methodology. Electrical Engineering and Computer Science Undergraduate Honors Theses Retrieved from [https://scholarworks.uark.edu/elcsuht/20](https://scholarworks.uark.edu/elcsuht/20)  \nThis Thesis is brought to you for free and open access by the Electrical Engineering and Computer Science at ScholarWorks@UARK. It has been accepted for inclusion in Electrical Engineering and Computer Science Undergraduate Honors Theses by an authorized administrator of ScholarWorks@UARK. For more information, please contact [uarepos@uark.edu](uarepos@uark.edu).  \nAutomated Solar PV Analysis with Machine Learning and Computer Vision:  \nDataset and Methodology  \nAutomated Solar PV Analysis with Machine Learning and Computer Vision:  \nDataset and Methodology  \nA thesis submitted in partial fulfillment of the requirements for the Engineering Honors Program with the degree of Bachelor of Science in Computer Science  \nBy  \nMalachi Massey  \nApril 2025  \nUniversity of Arkansas  \nThesis Committee  \nDr. Thi Hoang Ngan Le, Ph.D, Committee Chair  \nDr. John Michael Gauch, Ph.D, Committee Member  \nDr. Roy McCann, Ph.D, Committee Member  \nAbstract  \nSolar power is a vital resource in a world being threatened with the everevolving impacts of climate change. A combination of new and developing technologies have allowed solar photovoltaic installation to increase at an exponential rate. With this rapid and unprecedented growth comes the task of maintaining tens of thousands of square miles of solar photovoltaic panels. Manually observing and testing solar PV panels for defects or obstructions is costly and time-consuming, distracting valuable resources from the continued installation of new units. This research aims to (i) firstly, introduce a novel dataset on solar PV obstruction, named De-Solar dataset; (ii) secondly, develop a machine learning and computer vision system, SolarFormer++, which is an improvement of SolarFormer [1]; and (iii) finally, we present a multimodal dataset, De-Solar v2.0, which incorporates multispectral imagery from remote sensing and environmental factors.  \nACKNOWLEDGEMENTS  \nThank you to Dr. Le for giving me the incredible opportunity to conduct research on something I love and for providing me an encouraging environment in which to do so. Thank you to Esteban who helped and encouraged me every single step of the way, even when nothing was working as expected. I cannot express how amazing it was working with you. Finally, thank you to the University of Arkansas, the Honors College, and the College of Engineering for giving me a place to learn, grow, and laugh. You shall be missed.  \nTABLE OF CONTENTS  \nAbstract ...................................... ii  \nAcknowledgements ................................ iii  \nTable of Contents ................................. iv  \nList [of Figures .................................. vi](of Figures .................................. vi)  \n[List of Tables ................................... viii](List of Tables ................................... viii)  \n[1 Background .................................. 1](1 Background .................................. 1)  \n[1.1 SolarFormer: Introduction ....................... 1](1.1 SolarFormer","cbCaie2bTudfA3CA","https://ap.wps.com/l/cbCaie2bTudfA3CA","pdf",49389489,1,40,"English","en",105,"# Abstract\n# Acknowledgements\n# Table of Contents\n# List of Figures\n# List of Tables\n# 1 Background\n## 1.1 SolarFormer: Introduction\n# 2 SolarFormer: Broader Impacts\n## 2.1 Academic Impacts\n## 2.2 Industry Impacts\n## 2.3 Environmental Impacts\n## 2.4 Political Impacts\n# 3 Recent Developments\n## 3.1 SolarFormer++\n## 3.2 S3Former\n## 3.3 De-Solar Dataset\n# 4 New Contributions\n## 4.1 De-Solar 2.0 Dataset\n# 5 Future Developments\n## 5.1 Multi-banded Extension of SolarFormer++ and S3Former\n## 5.2 Voltage Prediction Extension of SolarFormer++ and S3Former\n# Bibliography","[{\"question\":\"What problem does the thesis address in solar photovoltaic maintenance?\",\"answer\":\"Manually observing and testing solar PV panels for defects or obstructions is costly and time-consuming, which distracts resources from installing new units.\"},{\"question\":\"What datasets are introduced, and what is their purpose?\",\"answer\":\"The thesis introduces the De-Solar dataset for solar PV obstruction and presents De-Solar v2.0, a multimodal dataset that incorporates multispectral imagery and environmental factors.\"},{\"question\":\"What models or systems are developed for analysis?\",\"answer\":\"It develops SolarFormer++, an improved machine learning and computer vision system based on SolarFormer, and also discusses related work such as S3Former.\"}]","Automated Solar PV Analysis with Machine Learning and Computer Vision - Dataset and Methodology - thesis | PDF",1785938084,101,{"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},"automated-solar-pv-analysis-with-machine-learning-and-computer-vision-dataset-and-methodology-thesis","",{"@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/automated-solar-pv-analysis-with-machine-learning-and-computer-vision-dataset-and-methodology-thesis/127281/",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","2026-08-22","2026-08-05",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},"What problem does the thesis address in solar photovoltaic maintenance?","Question",{"text":76,"@type":77},"Manually observing and testing solar PV panels for defects or obstructions is costly and time-consuming, which distracts resources from installing new units.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What datasets are introduced, and what is their purpose?",{"text":81,"@type":77},"The thesis introduces the De-Solar dataset for solar PV obstruction and presents De-Solar v2.0, a multimodal dataset that incorporates multispectral imagery and environmental factors.",{"name":83,"@type":74,"acceptedAnswer":84},"What models or systems are developed for analysis?",{"text":85,"@type":77},"It develops SolarFormer++, an improved machine learning and computer vision system based on SolarFormer, and also discusses related work such as S3Former.","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},[94,98,102,106,111,116,120,123,128,131,135],{"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":21,"slug":119},7,"Healthcare","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":107,"slug":138},19,"General","general"]