[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120254-en":3,"doc-seo-120254-105":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":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},120254,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Pixel-Wise Machine Learning and Deep Learning Methods Implementation on Multi-Class Wildfire Mapping - Capstone","Wildfires are destructive natural hazards, and their increasing frequency and intensity make accurate mapping essential for hazard management. This capstone applies pixel-wise machine learning and deep learning for multi-class wildfire mapping using two California wildfire events. Machine learning models include Random Forest, eXtreme Gradient Boosting, and Support Vector Machine, while the deep learning approach uses U-Net. Results show U-Net achieves the strongest classification, though SVM performs best among machine learning methods. The study concludes that AI improves accuracy and efficiency and identifies opportunities for model tuning and better hand-labeled masks.","Northern Illinois University  \nHuskie Commons  \n\n| Honors Capstones | Undergraduate Research & Artistry |\n| --- | --- |\n| Spring 5-7-2023\u003Cbr>Pixel-Wise Machine Learning and Deep Learning Methods Implementation on Multi-Class Wildfire Mapping\u003Cbr>Mingda Wu\u003Cbr>Northern Illinois University\u003Cbr>Follow this and additional works at: [https://huskiecommons.lib.niu.edu/studentengagement](https://huskiecommons.lib.niu.edu/studentengagement)honorscapstones\u003Cbr> Part of the Environmental Monitoring Commons |  |\n\nRecommended Citation  \nWu, Mingda, \"Pixel-Wise Machine Learning and Deep Learning Methods Implementation on Multi-Class Wildfire Mapping\" (2023) . Honors Capstones. 1464.  \n[https://huskiecommons.lib.niu.edu/studentengagement-honorscapstones/1464](https://huskiecommons.lib.niu.edu/studentengagement-honorscapstones/1464)  \nThis Student Project is brought to you for free and open access by the Undergraduate Research & Artistry at Huskie Commons. It has been accepted for inclusion in Honors Capstones by an authorized administrator of Huskie Commons. For more information, please contact [jschumacher@niu.edu](jschumacher@niu.edu).  \nWu 1  \nNORTHERN ILLINOIS UNIVERSITY  \nPixel-Wise Machine Learning and Deep Learning Methods Implementation  \non Multi-Class Wildfire Mapping  \nA Capstone Submitted to the  \nUniversity Honors Program  \nIn Partial Fulfillment of the  \nRequirements of the Baccalaureate Degree  \nWith Honors  \nDepartment Of  \nEarth, Atmosphere and Environment  \nBy  \nMingda Wu  \nDeKalb, Illinois  \nMay 13 , 2023  \nWu 3  \nAbstract  \nWildfires are destructive natural hazards. Artificial Intelligence (AI) has been a trendy topic in recent years due to its powerful applicability. This study focuses on the use of artificial intelligence (AI) in hazard management, specifically in the field of wildfire mapping. Machine learning and Deep learning are two subsets ofAI. This study applied pixel-wise machine learning and deep learning methods to do multi-class mapping on two wildfire events in California, USA. The purpose of this research is to demonstrate the usefulness and advantages of using AI in the field of hazard management. The machine learning methods selected are Random Forest, eXtreme Gradient Boosting and Support Vector Machine. The deep learning method used is UNet. The results indicate that U-Net did the best job at classifying wildfire events, while SVM had the best performance among machine learning algorithms. U-Net is, however, the most timeconsuming model due to the nature of deep learning. There are some aspects of this study that can be improved. The models may be tuned to have better performances. And it will be better to use hand-labeled masks to make the deep learning model more useful in more complex conditions. This research emphasizes that the use of AI in hazard management can improve the accuracy and efficiency of wildfire mapping. It also highlights the potential for AI to be applied in other fields of hazard management. Overall, the study demonstrates the usefulness and advantages of using AI in wildfire mapping and provides insights into how this technology can be further optimized for hazard management.  \nKeywords: Wildfires, Multiclass classification, Multiclass semantic segmentation, AI, Machine learning, Deep learning, U-Net, Pixel-wise, California, Remote sensing  \nWu 4  \n1. Introduction and Background  \nWildfires are destructive natural hazards that can cause great damage to the environment and human society, and they are becoming more frequent and intense due to climate change, and California is one of the most affected regions. These natural disasters pose a significant threat to the environment, infrastructure, and human life. In recent years, Artificial Intelligence (AI) has become a popular tool to tackle complex problems in various fields, including disaster management. Machine learning, a subset of AI, has shown promise in addressing the challenges of wildfire management. Machine learning requires s","cbCaitQTxrfEUspO","https://ap.wps.com/l/cbCaitQTxrfEUspO","pdf",1411960,1,20,"English","en",105,"# 1. Introduction and Background\n# 2. Dataset and Methodology\n# 3. Results and Evaluation\n# 4. Discussion and Future Work\n# References","[{\"question\":\"Which models are used for multi-class wildfire mapping in this study?\",\"answer\":\"The study uses Random Forest, eXtreme Gradient Boosting, and Support Vector Machine for machine learning, and U-Net for deep learning.\"},{\"question\":\"What datasets and data source support the experiments?\",\"answer\":\"The experiments use satellite images from Sentinel 2 MSI Level 2A, including atmospheric correction and multiple resolution options.\"},{\"question\":\"How do the results compare between U-Net and the machine learning baselines?\",\"answer\":\"U-Net performs best overall for classifying wildfire events, while SVM shows the best performance among the machine learning algorithms. U-Net is also the most time-consuming due to deep learning.\"}]","Pixel-Wise Machine Learning and Deep Learning Methods Implementation on Multi-Class Wildfire Mapping - Capstone | PDF",1785729057,50,{"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},"pixel-wise-machine-learning-and-deep-learning-methods-implementation-on-multi-class-wildfire-mapping-capstone","",{"@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/pixel-wise-machine-learning-and-deep-learning-methods-implementation-on-multi-class-wildfire-mapping-capstone/120254/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Which models are used for multi-class wildfire mapping in this study?","Question",{"text":75,"@type":76},"The study uses Random Forest, eXtreme Gradient Boosting, and Support Vector Machine for machine learning, and U-Net for deep learning.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What datasets and data source support the experiments?",{"text":80,"@type":76},"The experiments use satellite images from Sentinel 2 MSI Level 2A, including atmospheric correction and multiple resolution options.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the results compare between U-Net and the machine learning baselines?",{"text":84,"@type":76},"U-Net performs best overall for classifying wildfire events, while SVM shows the best performance among the machine learning algorithms. U-Net is also the most time-consuming due to deep learning.","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},[93,97,101,105,110,114,119,122,126,129,133],{"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":29,"slug":113},6,"Technology","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":21,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":21,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]