{"id":{"repo_id":"cornell","oai_identifier":"oai:ecommons.cornell.edu:1813/120632"},"canonical_url":"https://search.dev.ndltd.org/etd/cornell/oai:ecommons.cornell.edu:1813/120632","repository":{"repo_id":"cornell","name":"Cornell University","base_url":"https://ecommons.cornell.edu/server/oai/request"},"display":{"title":"AI-Based Framework for Identifying Wood Burning Appliances through Chimney Recognition","abstract":"Estimating the distribution of wood stove appliances is essential for fine-scale air quality management but remains limited by the coarse spatial resolution of survey-based inventories such as the U.S. National Emissions Inventory (NEI). To address this limitation, we proposed a novel computer vision framework that leverages visible chimney features as proxies for wood stove usage. Using data from drones, vehicle-based videos across urban and rural areas, we trained object detection models (YOLOv11) and integrated them with Vision Language Models (VLMs) for semantic verification. This two-stage pipeline substantially improves detection accuracy over YOLO alone. In the urban Fall Creek neighborhood, the YOLO+VLMs approach achieved an F1-score of 61.4%, compared to 29.3% using YOLO alone. In rural video data, the framework reached 74.5%, up from 17.5%. These results demonstrate the viability of context-informed, multimodal models in identifying distributed emission sources. The proposed method is scalable and adaptable, offering a promising tool for real-time residential wood combustion mapping and environmental policy development.","abstract_html":"Estimating the distribution of wood stove appliances is essential for fine-scale air quality management but remains limited by the coarse spatial resolution of survey-based inventories such as the U.S. National Emissions Inventory (NEI). To address this limitation, we proposed a novel computer vision framework that leverages visible chimney features as proxies for wood stove usage. Using data from drones, vehicle-based videos across urban and rural areas, we trained object detection models (YOLOv11) and integrated them with Vision Language Models (VLMs) for semantic verification. This two-stage pipeline substantially improves detection accuracy over YOLO alone. In the urban Fall Creek neighborhood, the YOLO+VLMs approach achieved an F1-score of 61.4%, compared to 29.3% using YOLO alone. In rural video data, the framework reached 74.5%, up from 17.5%. These results demonstrate the viability of context-informed, multimodal models in identifying distributed emission sources. The proposed method is scalable and adaptable, offering a promising tool for real-time residential wood combustion mapping and environmental policy development.","abstract_has_math":false,"creators":["Huang, Hongpufan"],"institution":"Cornell University","degree_name":"M.S., Mechanical Engineering","degree_level":"Master of Science","degree_discipline":"Mechanical Engineering","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":["Li, Qi"],"year":2025,"date_issued":"2025-08","date_published":"2025-08","updated_at":"2026-07-24T01:49:00Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/f8gz-c457"],"render_values":[{"text":"https://doi.org/10.7298/f8gz-c457","href":"https://doi.org/10.7298/f8gz-c457","code":true}]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 12576","ProQuest Publication ID: 32171161"],"render_values":[{"text":"ProQuest Submission ID: 12576","href":null,"code":true},{"text":"ProQuest Publication ID: 32171161","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/1813/120632","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Li, Qi"]},{"key":"dc:creator","label":"Author","values":["Huang, Hongpufan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-04-02T18:33:19Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-04-02T18:33:19Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-08"]},{"key":"dc:type","label":"Dc Type","values":["dissertation or thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mechanical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master of Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S., Mechanical Engineering"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Cornell University"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/f8gz-c457"]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 12576","ProQuest Publication ID: 32171161"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1813/120632"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["52 pages"]},{"key":"dc:description.abstract","label":"Abstract","values":["Estimating the distribution of wood stove appliances is essential for fine-scale air quality management but remains limited by the coarse spatial resolution of survey-based inventories such as the U.S. National Emissions Inventory (NEI). To address this limitation, we proposed a novel computer vision framework that leverages visible chimney features as proxies for wood stove usage. Using data from drones, vehicle-based videos across urban and rural areas, we trained object detection models (YOLOv11) and integrated them with Vision Language Models (VLMs) for semantic verification. This two-stage pipeline substantially improves detection accuracy over YOLO alone. In the urban Fall Creek neighborhood, the YOLO+VLMs approach achieved an F1-score of 61.4%, compared to 29.3% using YOLO alone. In rural video data, the framework reached 74.5%, up from 17.5%. These results demonstrate the viability of context-informed, multimodal models in identifying distributed emission sources. The proposed method is scalable and adaptable, offering a promising tool for real-time residential wood combustion mapping and environmental policy development."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["AI-Based Framework for Identifying Wood Burning Appliances through Chimney Recognition"]}]}],"canonical_facts":{"dc:contributor.committeemember":["Li, Qi"],"dc:creator":["Huang, Hongpufan"],"dc:date.accessioned":["2026-04-02T18:33:19Z"],"dc:date.available":["2026-04-02T18:33:19Z"],"dc:date.issued":["2025-08"],"dc:description":["52 pages"],"dc:description.abstract":["Estimating the distribution of wood stove appliances is essential for fine-scale air quality management but remains limited by the coarse spatial resolution of survey-based inventories such as the U.S. National Emissions Inventory (NEI). To address this limitation, we proposed a novel computer vision framework that leverages visible chimney features as proxies for wood stove usage. Using data from drones, vehicle-based videos across urban and rural areas, we trained object detection models (YOLOv11) and integrated them with Vision Language Models (VLMs) for semantic verification. This two-stage pipeline substantially improves detection accuracy over YOLO alone. In the urban Fall Creek neighborhood, the YOLO+VLMs approach achieved an F1-score of 61.4%, compared to 29.3% using YOLO alone. In rural video data, the framework reached 74.5%, up from 17.5%. These results demonstrate the viability of context-informed, multimodal models in identifying distributed emission sources. The proposed method is scalable and adaptable, offering a promising tool for real-time residential wood combustion mapping and environmental policy development."],"dc:format.mimetype":["application/pdf"],"dc:identifier.doi":["https://doi.org/10.7298/f8gz-c457"],"dc:identifier.other":["ProQuest Submission ID: 12576","ProQuest Publication ID: 32171161"],"dc:identifier.uri":["https://hdl.handle.net/1813/120632"],"dc:language.iso":["en"],"dc:title":["AI-Based Framework for Identifying Wood Burning Appliances through Chimney Recognition"],"dc:type":["dissertation or thesis"],"thesis:degree_discipline":["Mechanical Engineering"],"thesis:degree_level":["Master of Science"],"thesis:degree_name":["M.S., Mechanical Engineering"],"thesis:institution_name":["Cornell University"]},"updated_at":"2026-07-24T01:49:00Z"}