Improving the construction and prediction strategy of the Air Quality Health Index (AQHI) using machine learning: A case study in Guangzhou, China DOI Creative Commons
Lei Zhang, Yuan Yuan Chen,

Hang Dong

et al.

Ecotoxicology and Environmental Safety, Journal Year: 2024, Volume and Issue: 287, P. 117287 - 117287

Published: Nov. 1, 2024

Effectively capturing the risk of air pollution and informing residents is vital to public health. The widely used Air Quality Index (AQI) has been criticized for failing accurately represent non-threshold linear relationship between health outcomes. Although Health (AQHI) was developed address these limitations, it lacks comprehensive construction criteria. This work proposed a novel prediction strategy AQHI using machine learning methods. Our RF-Alasso-QGC method integrated Random Forest (RF), Adaptive Lasso (Alasso), Quantile-based G-Computation (QGC) effective pollutant selection construction. RF-Alasso excluded CO, while identified PM10, PM2.5, NO2, SO2, O3 as major contributors mortality. QGC controlled additive synergistic effects among pollutants. Compared Standard-AQHI, new RF-Alasso-QGC-AQHI demonstrated stronger correlation with outcomes, an interquartile (IQR) increase associated 1.80 % (1.44 %, 2.17 %) in total mortality, best goodness fit. Additionally, hybrid Auto Regressive Moving Average-Long Short Term Memory (ARIMA-LSTM) successfully forecast AQHI, achieving coefficient determination (R²) 0.961. that improved more efficiently communicate provide early warnings risks multiple

Language: Английский

A Comprehensive Analysis of Removal of Hazardous Dust Particulates from Chemical and Process Industries Off Gases by Advanced Wet Scrubbing Techniques- A Review DOI
Subhrajit Mukherjee, Hammad Siddiqi, Payal Maiti

et al.

Journal of Loss Prevention in the Process Industries, Journal Year: 2024, Volume and Issue: 91, P. 105406 - 105406

Published: Aug. 14, 2024

Language: Английский

Citations

5
Temporal dynamics of PM2.5 induced cell death: Emphasizing inflammation as key mediator in the late stages of prolonged myocardial toxicity DOI
Bhavana Sivakumar,

Gino A. Kurian

Experimental Cell Research, Journal Year: 2025, Volume and Issue: 445(1), P. 114423 - 114423

Published: Jan. 14, 2025

Language: Английский

Citations

0
Attenuation of PM2.5-Induced Lung Injury by 4-Phenylbutyric Acid: Maintenance of [Ca2+]i Stability between Endoplasmic Reticulum and Mitochondria DOI Creative Commons
Zhenhua Ma, Xiaohui Du,

Yize Sun

et al.

Biomolecules, Journal Year: 2024, Volume and Issue: 14(9), P. 1135 - 1135

Published: Sept. 8, 2024

Fine particulate matter (PM2.5) is a significant cause of respiratory diseases and associated cellular damage. The mechanisms behind this damage have not been fully explained. This study investigated two types (inflammation pyroptosis) induced by PM2.5, focusing on their relationship with organelles (the endoplasmic reticulum mitochondria). Animal models demonstrated that PM2.5 induces excessive stress (ER stress), which lung in rats. was confirmed pretreatment an ER inhibitor (4-Phenylbutyric acid, 4-PBA). We found that, vitro, the intracellular Ca2+ ([Ca2+]i) dysregulation rat alveolar macrophages stress. Changes mitochondria-associated membranes (MAMs) result abnormal mitochondrial function. further massive expression NLRP3 GSDMD-N, detrimental to cell survival. In conclusion, our findings provide valuable insights into between [Ca2+]i dysregulation, damage, inflammation pyroptosis under PM2.5-induced conditions. Their interactions ultimately impact health.

Language: Английский

Citations

3
Improving the construction and prediction strategy of the Air Quality Health Index (AQHI) using machine learning: A case study in Guangzhou, China DOI Creative Commons
Lei Zhang, Yuan Yuan Chen,

Hang Dong

et al.

Ecotoxicology and Environmental Safety, Journal Year: 2024, Volume and Issue: 287, P. 117287 - 117287

Published: Nov. 1, 2024

Effectively capturing the risk of air pollution and informing residents is vital to public health. The widely used Air Quality Index (AQI) has been criticized for failing accurately represent non-threshold linear relationship between health outcomes. Although Health (AQHI) was developed address these limitations, it lacks comprehensive construction criteria. This work proposed a novel prediction strategy AQHI using machine learning methods. Our RF-Alasso-QGC method integrated Random Forest (RF), Adaptive Lasso (Alasso), Quantile-based G-Computation (QGC) effective pollutant selection construction. RF-Alasso excluded CO, while identified PM10, PM2.5, NO2, SO2, O3 as major contributors mortality. QGC controlled additive synergistic effects among pollutants. Compared Standard-AQHI, new RF-Alasso-QGC-AQHI demonstrated stronger correlation with outcomes, an interquartile (IQR) increase associated 1.80 % (1.44 %, 2.17 %) in total mortality, best goodness fit. Additionally, hybrid Auto Regressive Moving Average-Long Short Term Memory (ARIMA-LSTM) successfully forecast AQHI, achieving coefficient determination (R²) 0.961. that improved more efficiently communicate provide early warnings risks multiple

Language: Английский

Citations

0