Cargando…

Machine learning-based ozone and PM2.5 forecasting: Application to multiple AQS sites in the Pacific Northwest

Air quality in the Pacific Northwest (PNW) of the U.S has generally been good in recent years, but unhealthy events were observed due to wildfires in summer or wood burning in winter. The current air quality forecasting system, which uses chemical transport models (CTMs), has had difficulty forecast...

Descripción completa

Detalles Bibliográficos
Autores principales: Fan, Kai, Dhammapala, Ranil, Harrington, Kyle, Lamb, Brian, Lee, Yunha
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9999009/
https://www.ncbi.nlm.nih.gov/pubmed/36910164
http://dx.doi.org/10.3389/fdata.2023.1124148
_version_ 1784903580044492800
author Fan, Kai
Dhammapala, Ranil
Harrington, Kyle
Lamb, Brian
Lee, Yunha
author_facet Fan, Kai
Dhammapala, Ranil
Harrington, Kyle
Lamb, Brian
Lee, Yunha
author_sort Fan, Kai
collection PubMed
description Air quality in the Pacific Northwest (PNW) of the U.S has generally been good in recent years, but unhealthy events were observed due to wildfires in summer or wood burning in winter. The current air quality forecasting system, which uses chemical transport models (CTMs), has had difficulty forecasting these unhealthy air quality events in the PNW. We developed a machine learning (ML) based forecasting system, which consists of two components, ML1 (random forecast classifiers and multiple linear regression models) and ML2 (two-phase random forest regression model). Our previous study showed that the ML system provides reliable forecasts of O(3) at a single monitoring site in Kennewick, WA. In this paper, we expand the ML forecasting system to predict both O(3) in the wildfire season and PM2.5 in wildfire and cold seasons at all available monitoring sites in the PNW during 2017–2020, and evaluate our ML forecasts against the existing operational CTM-based forecasts. For O(3), both ML1 and ML2 are used to achieve the best forecasts, which was the case in our previous study: ML2 performs better overall (R(2) = 0.79), especially for low-O(3) events, while ML1 correctly captures more high-O(3) events. Compared to the CTM-based forecast, our O(3) ML forecasts reduce the normalized mean bias (NMB) from 7.6 to 2.6% and normalized mean error (NME) from 18 to 12% when evaluating against the observation. For PM2.5, ML2 performs the best and thus is used for the final forecasts. Compared to the CTM-based PM2.5, ML2 clearly improves PM2.5 forecasts for both wildfire season (May to September) and cold season (November to February): ML2 reduces NMB (−27 to 7.9% for wildfire season; 3.4 to 2.2% for cold season) and NME (59 to 41% for wildfires season; 67 to 28% for cold season) significantly and captures more high-PM2.5 events correctly. Our ML air quality forecast system requires fewer computing resources and fewer input datasets, yet it provides more reliable forecasts than (if not, comparable to) the CTM-based forecast. It demonstrates that our ML system is a low-cost, reliable air quality forecasting system that can support regional/local air quality management.
format Online
Article
Text
id pubmed-9999009
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-99990092023-03-11 Machine learning-based ozone and PM2.5 forecasting: Application to multiple AQS sites in the Pacific Northwest Fan, Kai Dhammapala, Ranil Harrington, Kyle Lamb, Brian Lee, Yunha Front Big Data Big Data Air quality in the Pacific Northwest (PNW) of the U.S has generally been good in recent years, but unhealthy events were observed due to wildfires in summer or wood burning in winter. The current air quality forecasting system, which uses chemical transport models (CTMs), has had difficulty forecasting these unhealthy air quality events in the PNW. We developed a machine learning (ML) based forecasting system, which consists of two components, ML1 (random forecast classifiers and multiple linear regression models) and ML2 (two-phase random forest regression model). Our previous study showed that the ML system provides reliable forecasts of O(3) at a single monitoring site in Kennewick, WA. In this paper, we expand the ML forecasting system to predict both O(3) in the wildfire season and PM2.5 in wildfire and cold seasons at all available monitoring sites in the PNW during 2017–2020, and evaluate our ML forecasts against the existing operational CTM-based forecasts. For O(3), both ML1 and ML2 are used to achieve the best forecasts, which was the case in our previous study: ML2 performs better overall (R(2) = 0.79), especially for low-O(3) events, while ML1 correctly captures more high-O(3) events. Compared to the CTM-based forecast, our O(3) ML forecasts reduce the normalized mean bias (NMB) from 7.6 to 2.6% and normalized mean error (NME) from 18 to 12% when evaluating against the observation. For PM2.5, ML2 performs the best and thus is used for the final forecasts. Compared to the CTM-based PM2.5, ML2 clearly improves PM2.5 forecasts for both wildfire season (May to September) and cold season (November to February): ML2 reduces NMB (−27 to 7.9% for wildfire season; 3.4 to 2.2% for cold season) and NME (59 to 41% for wildfires season; 67 to 28% for cold season) significantly and captures more high-PM2.5 events correctly. Our ML air quality forecast system requires fewer computing resources and fewer input datasets, yet it provides more reliable forecasts than (if not, comparable to) the CTM-based forecast. It demonstrates that our ML system is a low-cost, reliable air quality forecasting system that can support regional/local air quality management. Frontiers Media S.A. 2023-02-24 /pmc/articles/PMC9999009/ /pubmed/36910164 http://dx.doi.org/10.3389/fdata.2023.1124148 Text en Copyright © 2023 Fan, Dhammapala, Harrington, Lamb and Lee. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Big Data
Fan, Kai
Dhammapala, Ranil
Harrington, Kyle
Lamb, Brian
Lee, Yunha
Machine learning-based ozone and PM2.5 forecasting: Application to multiple AQS sites in the Pacific Northwest
title Machine learning-based ozone and PM2.5 forecasting: Application to multiple AQS sites in the Pacific Northwest
title_full Machine learning-based ozone and PM2.5 forecasting: Application to multiple AQS sites in the Pacific Northwest
title_fullStr Machine learning-based ozone and PM2.5 forecasting: Application to multiple AQS sites in the Pacific Northwest
title_full_unstemmed Machine learning-based ozone and PM2.5 forecasting: Application to multiple AQS sites in the Pacific Northwest
title_short Machine learning-based ozone and PM2.5 forecasting: Application to multiple AQS sites in the Pacific Northwest
title_sort machine learning-based ozone and pm2.5 forecasting: application to multiple aqs sites in the pacific northwest
topic Big Data
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9999009/
https://www.ncbi.nlm.nih.gov/pubmed/36910164
http://dx.doi.org/10.3389/fdata.2023.1124148
work_keys_str_mv AT fankai machinelearningbasedozoneandpm25forecastingapplicationtomultipleaqssitesinthepacificnorthwest
AT dhammapalaranil machinelearningbasedozoneandpm25forecastingapplicationtomultipleaqssitesinthepacificnorthwest
AT harringtonkyle machinelearningbasedozoneandpm25forecastingapplicationtomultipleaqssitesinthepacificnorthwest
AT lambbrian machinelearningbasedozoneandpm25forecastingapplicationtomultipleaqssitesinthepacificnorthwest
AT leeyunha machinelearningbasedozoneandpm25forecastingapplicationtomultipleaqssitesinthepacificnorthwest