The major detrimental health effects of ground-level ozone (GLO) pollution make it imperative that both policy makers and ordinary citizens have access to high accuracy, high-resolution forecasts of their local area. Recently, advancements in computing power have made it possible to apply artificial intelligence (AI) techniques to a variety of big data modelling problems, including GLO forecasting and estimation. Of these AI methods, deep neural networks (DNN) have demonstrated the highest accuracy due to their ability extract non-linear relationships from high dimensional, noisy data inputs.
This research effort uses novel data sources, namely NOAA’s High Resolution Rapid Refresh (HRRR) meteorology model, and a long-short-term-memory (LSTM) neural network to forecast and interpolate ozone values at high spatiotemporal resolution of 1 hour and 3 km. The accuracies of the LSTM models are analyzed using lagged ozone at various forecast horizons and across the varying geographies of eleven ground sensors. I use Denver, Colorado as my study area due to its long-standing GLO pollution problem and relatively high density of EPA ozone monitoring stations.
","abstract_html":"<p>The major detrimental health effects of ground-level ozone (GLO) pollution make it imperative that both policy makers and ordinary citizens have access to high accuracy, high-resolution forecasts of their local area. Recently, advancements in computing power have made it possible to apply artificial intelligence (AI) techniques to a variety of big data modelling problems, including GLO forecasting and estimation. Of these AI methods, deep neural networks (DNN) have demonstrated the highest accuracy due to their ability extract non-linear relationships from high dimensional, noisy data inputs.</p> <p>This research effort uses novel data sources, namely NOAA’s High Resolution Rapid Refresh (HRRR) meteorology model, and a long-short-term-memory (LSTM) neural network to forecast and interpolate ozone values at high spatiotemporal resolution of 1 hour and 3 km. The accuracies of the LSTM models are analyzed using lagged ozone at various forecast horizons and across the varying geographies of eleven ground sensors. I use Denver, Colorado as my study area due to its long-standing GLO pollution problem and relatively high density of EPA ozone monitoring stations.</p>","abstract_has_math":false,"creators":["Keenan, William J."],"institution":null,"degree_name":"M.A. in Geography","degree_level":"Masters Thesis","degree_discipline":null,"degree_department":null,"school":null,"contributors":["Jing Li","Michael Keables","Kris Kuzera"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-06-15T07:00:00Z","date_published":"2024-06-15T07:00:00Z","updated_at":"2026-07-24T02:01:48Z","subjects":["Air pollution","Air quality","Geographic information science (GIS)","Long-short-term-memory (LSTM)","Machine learning","Ozone pollution","Environmental Monitoring","Environmental Sciences","Environmental Studies","Geographic Information Sciences","Geography","Other Geography","Social and Behavioral Sciences"],"languages":["English (eng)"],"rights":["Copyright is held by the author. User is responsible for all copyright compliance.
"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.du.edu/etd/2398","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Jing Li","Michael Keables","Kris Kuzera"]},{"key":"dc:creator","label":"Author","values":["Keenan, William J."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-01-31T08:00:00Z"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.A. in Geography"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Air pollution","Air quality","Geographic information science (GIS)","Long-short-term-memory (LSTM)","Machine learning","Ozone pollution","Environmental Monitoring","Environmental Sciences","Environmental Studies","Geographic Information Sciences","Geography","Other Geography","Social and Behavioral Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English (eng)"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright is held by the author. User is responsible for all copyright compliance.
"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.du.edu/etd/2398"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The major detrimental health effects of ground-level ozone (GLO) pollution make it imperative that both policy makers and ordinary citizens have access to high accuracy, high-resolution forecasts of their local area. Recently, advancements in computing power have made it possible to apply artificial intelligence (AI) techniques to a variety of big data modelling problems, including GLO forecasting and estimation. Of these AI methods, deep neural networks (DNN) have demonstrated the highest accuracy due to their ability extract non-linear relationships from high dimensional, noisy data inputs.
This research effort uses novel data sources, namely NOAA’s High Resolution Rapid Refresh (HRRR) meteorology model, and a long-short-term-memory (LSTM) neural network to forecast and interpolate ozone values at high spatiotemporal resolution of 1 hour and 3 km. The accuracies of the LSTM models are analyzed using lagged ozone at various forecast horizons and across the varying geographies of eleven ground sensors. I use Denver, Colorado as my study area due to its long-standing GLO pollution problem and relatively high density of EPA ozone monitoring stations.
"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["A Geospatial and Machine Learning Framework for Forecasting Ground Level Ozone Pollution"]}]}],"canonical_facts":{"dc:contributor":["Jing Li","Michael Keables","Kris Kuzera"],"dc:creator":["Keenan, William J."],"dc:date.available":["2025-01-31T08:00:00Z"],"dc:description.abstract":["The major detrimental health effects of ground-level ozone (GLO) pollution make it imperative that both policy makers and ordinary citizens have access to high accuracy, high-resolution forecasts of their local area. Recently, advancements in computing power have made it possible to apply artificial intelligence (AI) techniques to a variety of big data modelling problems, including GLO forecasting and estimation. Of these AI methods, deep neural networks (DNN) have demonstrated the highest accuracy due to their ability extract non-linear relationships from high dimensional, noisy data inputs.
This research effort uses novel data sources, namely NOAA’s High Resolution Rapid Refresh (HRRR) meteorology model, and a long-short-term-memory (LSTM) neural network to forecast and interpolate ozone values at high spatiotemporal resolution of 1 hour and 3 km. The accuracies of the LSTM models are analyzed using lagged ozone at various forecast horizons and across the varying geographies of eleven ground sensors. I use Denver, Colorado as my study area due to its long-standing GLO pollution problem and relatively high density of EPA ozone monitoring stations.
"],"dc:format":["application/pdf"],"dc:identifier":["https://digitalcommons.du.edu/etd/2398"],"dc:language":["English (eng)"],"dc:rights":["Copyright is held by the author. User is responsible for all copyright compliance.
"],"dc:subject":["Air pollution","Air quality","Geographic information science (GIS)","Long-short-term-memory (LSTM)","Machine learning","Ozone pollution","Environmental Monitoring","Environmental Sciences","Environmental Studies","Geographic Information Sciences","Geography","Other Geography","Social and Behavioral Sciences"],"dc:title":["A Geospatial and Machine Learning Framework for Forecasting Ground Level Ozone Pollution"],"thesis:degree_level":["Masters Thesis"],"thesis:degree_name":["M.A. in Geography"]},"updated_at":"2026-07-24T02:01:48Z"}