TY - JOUR
T1 - Data-Driven PM2.5 Exposure Prediction in Wildfire-Prone Regions and Respiratory Disease Mortality Risk Assessment
AU - Khanmohammadi, Sadegh
AU - Arashpour, Mehrdad
AU - Bazli, Milad
AU - Farzanehfar, Parisa
PY - 2024/8/7
Y1 - 2024/8/7
N2 - Wildfires generate substantial smoke containing fine particulate matter (PM2.5) that adversely impacts health. This study develops machine learning models integrating pre-wildfire factors like weather and fuel conditions with post-wildfire health impacts to provide a holistic understanding of smoke exposure risks. Various data-driven models including Support Vector Regression, Multi-layer Perceptron, and three tree-based ensemble algorithms (Random Forest, Extreme Gradient Boosting (XGBoost), and Natural Gradient Boosting (NGBoost)) are evaluated in this study. Ensemble models effectively predict PM2.5 levels based on temperature, humidity, wind, and fuel moisture, revealing the significant roles of radiation, temperature, and moisture. Further modelling links smoke exposure to deaths from chronic obstructive pulmonary disease (COPD) and lung cancer using age, sex, and pollution type as inputs. Ambient pollution is the primary driver of COPD mortality, while age has a greater influence on lung cancer deaths. This research advances atmospheric and health impact understanding, aiding forest fire prevention and management.
AB - Wildfires generate substantial smoke containing fine particulate matter (PM2.5) that adversely impacts health. This study develops machine learning models integrating pre-wildfire factors like weather and fuel conditions with post-wildfire health impacts to provide a holistic understanding of smoke exposure risks. Various data-driven models including Support Vector Regression, Multi-layer Perceptron, and three tree-based ensemble algorithms (Random Forest, Extreme Gradient Boosting (XGBoost), and Natural Gradient Boosting (NGBoost)) are evaluated in this study. Ensemble models effectively predict PM2.5 levels based on temperature, humidity, wind, and fuel moisture, revealing the significant roles of radiation, temperature, and moisture. Further modelling links smoke exposure to deaths from chronic obstructive pulmonary disease (COPD) and lung cancer using age, sex, and pollution type as inputs. Ambient pollution is the primary driver of COPD mortality, while age has a greater influence on lung cancer deaths. This research advances atmospheric and health impact understanding, aiding forest fire prevention and management.
KW - air pollution
KW - artificial intelligence
KW - bronchus
KW - chronic obstructive pulmonary disease (COPD)
KW - lung cancer (TB&L)
KW - machine learning
KW - tracheal
KW - wildfires
UR - http://www.scopus.com/inward/record.url?scp=85202628998&partnerID=8YFLogxK
U2 - 10.3390/fire7080277
DO - 10.3390/fire7080277
M3 - Article
AN - SCOPUS:85202628998
SN - 2571-6255
VL - 7
SP - 1
EP - 17
JO - Fire
JF - Fire
IS - 8
M1 - 277
ER -