Source Term Estimation for Puff Releases Using Machine Learning: A Case Study

Reliable source term prediction for hazardous pollutant puffs in urban microenvironments is challenging, especially for risk management under strict time constraints. Puff movement is highly stochastic due to atmospheric turbulence, intensified by complex urban canopies. This complexity, combined wi...

Full description

Saved in:
Bibliographic Details
Main Authors: John Bartzis, Spyros Andronopoulos, Ioannis Sakellaris
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/16/6/697
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849467523193372672
author John Bartzis
Spyros Andronopoulos
Ioannis Sakellaris
author_facet John Bartzis
Spyros Andronopoulos
Ioannis Sakellaris
author_sort John Bartzis
collection DOAJ
description Reliable source term prediction for hazardous pollutant puffs in urban microenvironments is challenging, especially for risk management under strict time constraints. Puff movement is highly stochastic due to atmospheric turbulence, intensified by complex urban canopies. This complexity, combined with time limitations, makes advanced computational modeling impractical. A more efficient approach is leveraging past and present data using Machine Learning (ML) techniques. This study proposes an ML-based method, enriched with simplified physical modeling, for source term estimation of unforeseen hazardous air releases in monitored urban areas. The Random Forest Regression, commonly used in meteorology and air quality studies, has been selected. A novel variable selection method is introduced, including the following: (a) a model-derived Exposure Burden Index (EBI) reflecting plume–morphology interactions; (b) a plume travel time indicator; (c) the standard deviation of input variables capturing stochastic behavior; and (d) the total dosage-to-mass released ratio at sensor locations as the target variable. The case study examines JU2003 field experiments involving SF<sub>6</sub> puffs released at street level in Oklahoma City’s urban core, a challenging scenario due to the limited number of sensors and historical data. Results demonstrate the approach’s effectiveness, offering a promising, realistic alternative to traditional computationally intensive methods.
format Article
id doaj-art-e0ef7d400e064a68b989e9eee733419e
institution Kabale University
issn 2073-4433
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-e0ef7d400e064a68b989e9eee733419e2025-08-20T03:26:10ZengMDPI AGAtmosphere2073-44332025-06-0116669710.3390/atmos16060697Source Term Estimation for Puff Releases Using Machine Learning: A Case StudyJohn Bartzis0Spyros Andronopoulos1Ioannis Sakellaris2Department of Mechanical Engineering, University of Western Macedonia, Active Urban Planning Zone (ZEP), 50100 Kozani, GreeceEnvironmental Research Laboratory, Institute of Nuclear & Radiological Sciences & Technology, Energy & Safety, National Centre for Scientific Research “Demokritos”, 15341 Athens, GreeceAtmospheric Chemistry & Innovative Technologies Laboratory (AirTech Lab), Institute of Nuclear & Radiological Sciences & Technology, Energy & Safety, National Centre for Scientific Research “Demokritos”, 15341 Athens, GreeceReliable source term prediction for hazardous pollutant puffs in urban microenvironments is challenging, especially for risk management under strict time constraints. Puff movement is highly stochastic due to atmospheric turbulence, intensified by complex urban canopies. This complexity, combined with time limitations, makes advanced computational modeling impractical. A more efficient approach is leveraging past and present data using Machine Learning (ML) techniques. This study proposes an ML-based method, enriched with simplified physical modeling, for source term estimation of unforeseen hazardous air releases in monitored urban areas. The Random Forest Regression, commonly used in meteorology and air quality studies, has been selected. A novel variable selection method is introduced, including the following: (a) a model-derived Exposure Burden Index (EBI) reflecting plume–morphology interactions; (b) a plume travel time indicator; (c) the standard deviation of input variables capturing stochastic behavior; and (d) the total dosage-to-mass released ratio at sensor locations as the target variable. The case study examines JU2003 field experiments involving SF<sub>6</sub> puffs released at street level in Oklahoma City’s urban core, a challenging scenario due to the limited number of sensors and historical data. Results demonstrate the approach’s effectiveness, offering a promising, realistic alternative to traditional computationally intensive methods.https://www.mdpi.com/2073-4433/16/6/697hazardous pollutant puffssource term estimationurban microenvironment
spellingShingle John Bartzis
Spyros Andronopoulos
Ioannis Sakellaris
Source Term Estimation for Puff Releases Using Machine Learning: A Case Study
Atmosphere
hazardous pollutant puffs
source term estimation
urban microenvironment
title Source Term Estimation for Puff Releases Using Machine Learning: A Case Study
title_full Source Term Estimation for Puff Releases Using Machine Learning: A Case Study
title_fullStr Source Term Estimation for Puff Releases Using Machine Learning: A Case Study
title_full_unstemmed Source Term Estimation for Puff Releases Using Machine Learning: A Case Study
title_short Source Term Estimation for Puff Releases Using Machine Learning: A Case Study
title_sort source term estimation for puff releases using machine learning a case study
topic hazardous pollutant puffs
source term estimation
urban microenvironment
url https://www.mdpi.com/2073-4433/16/6/697
work_keys_str_mv AT johnbartzis sourcetermestimationforpuffreleasesusingmachinelearningacasestudy
AT spyrosandronopoulos sourcetermestimationforpuffreleasesusingmachinelearningacasestudy
AT ioannissakellaris sourcetermestimationforpuffreleasesusingmachinelearningacasestudy