Enhancing PM2.5 Prediction Using NARX-Based Combined CNN and LSTM Hybrid Model

Ahmed Samy AbdElAziz Moursi; Nawal El-Fishawy; Soufiene Djahel; Marwa A. Shouman

doi:10.3390/s22124418

Enhancing PM2.5 Prediction Using NARX-Based Combined CNN and LSTM Hybrid Model

Ahmed Samy AbdElAziz Moursi, Nawal El-Fishawy, Soufiene Djahel, Marwa A. Shouman

Research output: Contribution to journal › Article › peer-review

19 Citations (Scopus)

68 Downloads (Pure)

Abstract

In a world where humanity’s interests come first, the environment is flooded with pollutants produced by humans’ urgent need for expansion. Air pollution and climate change are side effects of humans’ inconsiderate intervention. Particulate matter of 2.5 µm diameter (PM2.5) infiltrates lungs and hearts, causing many respiratory system diseases. Innovation in air pollution prediction is a must to protect the environment and its habitants, including those of humans. For that purpose, an enhanced method for PM2.5 prediction within the next hour is introduced in this research work using nonlinear autoregression with exogenous input (NARX) model hosting a convolutional neural network (CNN) followed by long short-term memory (LSTM) neural networks. The proposed enhancement was evaluated by several metrics such as index of agreement (IA) and normalized root mean square error (NRMSE). The results indicated that the CNN–LSTM/NARX hybrid model has the lowest NRMSE and the best IA, surpassing the state-of-the-art proposed hybrid deep-learning algorithms.

Original language	English
Article number	4418
Number of pages	31
Journal	Sensors
Volume	22
Issue number	12
DOIs	https://doi.org/10.3390/s22124418
Publication status	Published - 11 Jun 2022
Externally published	Yes

Bibliographical note

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/)

Funder

The researcher Ahmed Moursi is funded by a full Newton–Mosharafa scholarship from the Ministry of Higher Education of the Arab Republic of Egypt.

Keywords

CNN–LSTM
NARX neural network
PM2.5
air quality prediction
machine learning

ASJC Scopus subject areas

Analytical Chemistry
Information Systems
Instrumentation
Atomic and Molecular Physics, and Optics
Electrical and Electronic Engineering
Biochemistry

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3390/s22124418Licence: CC BY

PublishedFinal published version, 2.24 MBLicence: CC BY
sensors-22-04418-v2Final published version, 12 MBLicence: CC BY

Cite this

@article{772ab7c868c943ac9324ec282e5e22b6,

title = "Enhancing PM2.5 Prediction Using NARX-Based Combined CNN and LSTM Hybrid Model",

abstract = "In a world where humanity{\textquoteright}s interests come first, the environment is flooded with pollutants produced by humans{\textquoteright} urgent need for expansion. Air pollution and climate change are side effects of humans{\textquoteright} inconsiderate intervention. Particulate matter of 2.5 µm diameter (PM2.5) infiltrates lungs and hearts, causing many respiratory system diseases. Innovation in air pollution prediction is a must to protect the environment and its habitants, including those of humans. For that purpose, an enhanced method for PM2.5 prediction within the next hour is introduced in this research work using nonlinear autoregression with exogenous input (NARX) model hosting a convolutional neural network (CNN) followed by long short-term memory (LSTM) neural networks. The proposed enhancement was evaluated by several metrics such as index of agreement (IA) and normalized root mean square error (NRMSE). The results indicated that the CNN–LSTM/NARX hybrid model has the lowest NRMSE and the best IA, surpassing the state-of-the-art proposed hybrid deep-learning algorithms.",

keywords = "CNN–LSTM, NARX neural network, PM2.5, air quality prediction, machine learning",

author = "Moursi, {Ahmed Samy AbdElAziz} and Nawal El-Fishawy and Soufiene Djahel and Shouman, {Marwa A.}",

note = "{\textcopyright} 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/)",

year = "2022",

month = jun,

day = "11",

doi = "10.3390/s22124418",

language = "English",

volume = "22",

journal = "Sensors",

issn = "1424-3210",

publisher = "MDPI",

number = "12",

}

TY - JOUR

T1 - Enhancing PM2.5 Prediction Using NARX-Based Combined CNN and LSTM Hybrid Model

AU - Moursi, Ahmed Samy AbdElAziz

AU - El-Fishawy, Nawal

AU - Djahel, Soufiene

AU - Shouman, Marwa A.

N1 - © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/)

PY - 2022/6/11

Y1 - 2022/6/11

N2 - In a world where humanity’s interests come first, the environment is flooded with pollutants produced by humans’ urgent need for expansion. Air pollution and climate change are side effects of humans’ inconsiderate intervention. Particulate matter of 2.5 µm diameter (PM2.5) infiltrates lungs and hearts, causing many respiratory system diseases. Innovation in air pollution prediction is a must to protect the environment and its habitants, including those of humans. For that purpose, an enhanced method for PM2.5 prediction within the next hour is introduced in this research work using nonlinear autoregression with exogenous input (NARX) model hosting a convolutional neural network (CNN) followed by long short-term memory (LSTM) neural networks. The proposed enhancement was evaluated by several metrics such as index of agreement (IA) and normalized root mean square error (NRMSE). The results indicated that the CNN–LSTM/NARX hybrid model has the lowest NRMSE and the best IA, surpassing the state-of-the-art proposed hybrid deep-learning algorithms.

AB - In a world where humanity’s interests come first, the environment is flooded with pollutants produced by humans’ urgent need for expansion. Air pollution and climate change are side effects of humans’ inconsiderate intervention. Particulate matter of 2.5 µm diameter (PM2.5) infiltrates lungs and hearts, causing many respiratory system diseases. Innovation in air pollution prediction is a must to protect the environment and its habitants, including those of humans. For that purpose, an enhanced method for PM2.5 prediction within the next hour is introduced in this research work using nonlinear autoregression with exogenous input (NARX) model hosting a convolutional neural network (CNN) followed by long short-term memory (LSTM) neural networks. The proposed enhancement was evaluated by several metrics such as index of agreement (IA) and normalized root mean square error (NRMSE). The results indicated that the CNN–LSTM/NARX hybrid model has the lowest NRMSE and the best IA, surpassing the state-of-the-art proposed hybrid deep-learning algorithms.

KW - CNN–LSTM

KW - NARX neural network

KW - PM2.5

KW - air quality prediction

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85131697353&partnerID=8YFLogxK

U2 - 10.3390/s22124418

DO - 10.3390/s22124418

M3 - Article

SN - 1424-3210

VL - 22

JO - Sensors

JF - Sensors

IS - 12

M1 - 4418

ER -

Enhancing PM2.5 Prediction Using NARX-Based Combined CNN and LSTM Hybrid Model

Abstract

Bibliographical note

Funder

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

AI- enabled air quality monitoring system on the edge for more sustainable cities

Cite this

Enhancing PM2.5 Prediction Using NARX-Based Combined CNN and LSTM Hybrid Model

Abstract

Bibliographical note

Funder

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Projects

AI- enabled air quality monitoring system on the edge for more sustainable cities

Cite this