Spatiotemporal Air Quality Analysis and Prediction in Franklin County, Ohio: A Google Earth Engine-Based GIS, Remote Sensing, and Machine Learning Approach
Abstract
This study uses Google Earth Engine (GEE), remote sensing, and machine learning to analyze and predict air quality in Franklin County, Ohio. Satellite data from Sentinel-5P and MODIS were combined with ground-based measurements and meteorological data to map spatiotemporal patterns of pollutants like PM2.5 and NOâ‚‚. Machine learning models, including Random Forest, achieved high accuracy in predicting pollutant levels and identifying key factors such as traffic density and land use. The results revealed seasonal trends and pollution hotspots, offering actionable insights for air quality management and demonstrating the potential of GEE-based frameworks for scalable environmental monitoring.
Status
Graduate
Department
Geography
College
College of Arts and Sciences
Campus
Athens
Faculty Mentor
Sinha, Gaurav
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Spatiotemporal Air Quality Analysis and Prediction in Franklin County, Ohio: A Google Earth Engine-Based GIS, Remote Sensing, and Machine Learning Approach
This study uses Google Earth Engine (GEE), remote sensing, and machine learning to analyze and predict air quality in Franklin County, Ohio. Satellite data from Sentinel-5P and MODIS were combined with ground-based measurements and meteorological data to map spatiotemporal patterns of pollutants like PM2.5 and NOâ‚‚. Machine learning models, including Random Forest, achieved high accuracy in predicting pollutant levels and identifying key factors such as traffic density and land use. The results revealed seasonal trends and pollution hotspots, offering actionable insights for air quality management and demonstrating the potential of GEE-based frameworks for scalable environmental monitoring.