ENVISION-AI – ENVirOnmental ModellIng, predictIon & forecaSting with AI
Faculty Mentor
Dr. Felix Hamza-Lup
Location
Savannah Ballroom
Type of Research
Proposed
Session Format
Poster Presentation
College
Allen E. Paulson College of Engineering & Computing
Department
Computer Science
Abstract
This project applies advanced artificial intelligence (AI) techniques to model, predict, and forecast fine particulate air pollution (PM2.5), a critical environmental and public health challenge. Emissions from traffic exhaust, wildfires, and industrial activities produce complex, dynamic mixtures of airborne pollutants, among which PM2.5—particles with diameters of 2.5 micrometers or smaller—poses severe risks due to its ability to penetrate deep into the respiratory system and enter the bloodstream. Chronic and acute exposure to PM2.5 is strongly associated with cardiovascular disease, respiratory illness, and premature mortality. To address these challenges, the project will develop AI-driven, data-centric models that integrate large- scale, heterogeneous sensor data from ground-based monitoring networks and related environmental sources. These models will capture fine-grained spatiotemporal emission dynamics, identify nonlinear interactions among pollutant sources and atmospheric conditions, and adapt to evolving environmental patterns. By leveraging machine learning for pattern discovery, prediction, and uncertainty quantification, the system will enable high-accuracy forecasting, real-time anomaly detection, and early-warning capabilities for extreme pollution events. The outcomes of this research will support regulatory compliance, inform evidence-based policy decisions, and enable proactive environmental management strategies, ultimately improving air quality monitoring, public health protection, and community resilience
Program Description
.
Start Date
4-21-2026 10:00 AM
End Date
4-21-2026 12:00 PM
Recommended Citation
Cole, Mckinsey D.; Pham, Windy N.; Pham, Bao Q.; and Zittrouer, Coleman C., "ENVISION-AI – ENVirOnmental ModellIng, predictIon & forecaSting with AI" (2026). GS4 Student Scholars Symposium. 12.
https://digitalcommons.georgiasouthern.edu/research_symposium/2026A/2026A/12
ENVISION-AI – ENVirOnmental ModellIng, predictIon & forecaSting with AI
Savannah Ballroom
This project applies advanced artificial intelligence (AI) techniques to model, predict, and forecast fine particulate air pollution (PM2.5), a critical environmental and public health challenge. Emissions from traffic exhaust, wildfires, and industrial activities produce complex, dynamic mixtures of airborne pollutants, among which PM2.5—particles with diameters of 2.5 micrometers or smaller—poses severe risks due to its ability to penetrate deep into the respiratory system and enter the bloodstream. Chronic and acute exposure to PM2.5 is strongly associated with cardiovascular disease, respiratory illness, and premature mortality. To address these challenges, the project will develop AI-driven, data-centric models that integrate large- scale, heterogeneous sensor data from ground-based monitoring networks and related environmental sources. These models will capture fine-grained spatiotemporal emission dynamics, identify nonlinear interactions among pollutant sources and atmospheric conditions, and adapt to evolving environmental patterns. By leveraging machine learning for pattern discovery, prediction, and uncertainty quantification, the system will enable high-accuracy forecasting, real-time anomaly detection, and early-warning capabilities for extreme pollution events. The outcomes of this research will support regulatory compliance, inform evidence-based policy decisions, and enable proactive environmental management strategies, ultimately improving air quality monitoring, public health protection, and community resilience
