A novel CMAQ-CNN hybrid model to forecast hourly surface-ozone concentrations 14 days in advance

Abstract Issues regarding air quality and related health concerns have prompted this study, which develops an accurate and computationally fast, efficient hybrid modeling system that combines numerical modeling and machine learning for forecasting concentrations of surface ozone. Currently available...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Alqamah Sayeed, Yunsoo Choi, Ebrahim Eslami, Jia Jung, Yannic Lops, Ahmed Khan Salman, Jae-Bum Lee, Hyun-Ju Park, Min-Hyeok Choi
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/61a2b4505f114dcaba24ee227ece1377
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:61a2b4505f114dcaba24ee227ece1377
record_format dspace
spelling oai:doaj.org-article:61a2b4505f114dcaba24ee227ece13772021-12-02T14:47:31ZA novel CMAQ-CNN hybrid model to forecast hourly surface-ozone concentrations 14 days in advance10.1038/s41598-021-90446-62045-2322https://doaj.org/article/61a2b4505f114dcaba24ee227ece13772021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-90446-6https://doaj.org/toc/2045-2322Abstract Issues regarding air quality and related health concerns have prompted this study, which develops an accurate and computationally fast, efficient hybrid modeling system that combines numerical modeling and machine learning for forecasting concentrations of surface ozone. Currently available numerical modeling systems for air quality predictions (e.g., CMAQ) can forecast 24 to 48 h in advance. In this study, we develop a modeling system based on a convolutional neural network (CNN) model that is not only fast but covers a temporal period of two weeks with a resolution as small as a single hour for 255 stations. The CNN model uses meteorology from the Weather Research and Forecasting model (processed by the Meteorology-Chemistry Interface Processor), forecasted air quality from the Community Multi-scale Air Quality Model (CMAQ), and previous 24-h concentrations of various measurable air quality parameters as inputs and predicts the following 14-day hourly surface ozone concentrations. The model achieves an average accuracy of 0.91 in terms of the index of agreement for the first day and 0.78 for the fourteenth day, while the average index of agreement for one day ahead prediction from the CMAQ is 0.77. Through this study, we intend to amalgamate the best features of numerical modeling (i.e., fine spatial resolution) and a deep neural network (i.e., computation speed and accuracy) to achieve more accurate spatio-temporal predictions of hourly ozone concentrations. Although the primary purpose of this study is the prediction of hourly ozone concentrations, the system can be extended to various other pollutants.Alqamah SayeedYunsoo ChoiEbrahim EslamiJia JungYannic LopsAhmed Khan SalmanJae-Bum LeeHyun-Ju ParkMin-Hyeok ChoiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Alqamah Sayeed
Yunsoo Choi
Ebrahim Eslami
Jia Jung
Yannic Lops
Ahmed Khan Salman
Jae-Bum Lee
Hyun-Ju Park
Min-Hyeok Choi
A novel CMAQ-CNN hybrid model to forecast hourly surface-ozone concentrations 14 days in advance
description Abstract Issues regarding air quality and related health concerns have prompted this study, which develops an accurate and computationally fast, efficient hybrid modeling system that combines numerical modeling and machine learning for forecasting concentrations of surface ozone. Currently available numerical modeling systems for air quality predictions (e.g., CMAQ) can forecast 24 to 48 h in advance. In this study, we develop a modeling system based on a convolutional neural network (CNN) model that is not only fast but covers a temporal period of two weeks with a resolution as small as a single hour for 255 stations. The CNN model uses meteorology from the Weather Research and Forecasting model (processed by the Meteorology-Chemistry Interface Processor), forecasted air quality from the Community Multi-scale Air Quality Model (CMAQ), and previous 24-h concentrations of various measurable air quality parameters as inputs and predicts the following 14-day hourly surface ozone concentrations. The model achieves an average accuracy of 0.91 in terms of the index of agreement for the first day and 0.78 for the fourteenth day, while the average index of agreement for one day ahead prediction from the CMAQ is 0.77. Through this study, we intend to amalgamate the best features of numerical modeling (i.e., fine spatial resolution) and a deep neural network (i.e., computation speed and accuracy) to achieve more accurate spatio-temporal predictions of hourly ozone concentrations. Although the primary purpose of this study is the prediction of hourly ozone concentrations, the system can be extended to various other pollutants.
format article
author Alqamah Sayeed
Yunsoo Choi
Ebrahim Eslami
Jia Jung
Yannic Lops
Ahmed Khan Salman
Jae-Bum Lee
Hyun-Ju Park
Min-Hyeok Choi
author_facet Alqamah Sayeed
Yunsoo Choi
Ebrahim Eslami
Jia Jung
Yannic Lops
Ahmed Khan Salman
Jae-Bum Lee
Hyun-Ju Park
Min-Hyeok Choi
author_sort Alqamah Sayeed
title A novel CMAQ-CNN hybrid model to forecast hourly surface-ozone concentrations 14 days in advance
title_short A novel CMAQ-CNN hybrid model to forecast hourly surface-ozone concentrations 14 days in advance
title_full A novel CMAQ-CNN hybrid model to forecast hourly surface-ozone concentrations 14 days in advance
title_fullStr A novel CMAQ-CNN hybrid model to forecast hourly surface-ozone concentrations 14 days in advance
title_full_unstemmed A novel CMAQ-CNN hybrid model to forecast hourly surface-ozone concentrations 14 days in advance
title_sort novel cmaq-cnn hybrid model to forecast hourly surface-ozone concentrations 14 days in advance
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/61a2b4505f114dcaba24ee227ece1377
work_keys_str_mv AT alqamahsayeed anovelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT yunsoochoi anovelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT ebrahimeslami anovelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT jiajung anovelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT yanniclops anovelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT ahmedkhansalman anovelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT jaebumlee anovelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT hyunjupark anovelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT minhyeokchoi anovelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT alqamahsayeed novelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT yunsoochoi novelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT ebrahimeslami novelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT jiajung novelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT yanniclops novelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT ahmedkhansalman novelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT jaebumlee novelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT hyunjupark novelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
AT minhyeokchoi novelcmaqcnnhybridmodeltoforecasthourlysurfaceozoneconcentrations14daysinadvance
_version_ 1718389511463895040