dc.contributor.author |
Waseem, KH
|
|
dc.contributor.author |
Mushtaq, H
|
|
dc.contributor.author |
Abid, F
|
|
dc.contributor.author |
Abu-Mahfouz, Adnan MI
|
|
dc.contributor.author |
Shaikh, A
|
|
dc.contributor.author |
Turan, M
|
|
dc.contributor.author |
Rasheed, J
|
|
dc.date.accessioned |
2023-02-26T08:18:25Z |
|
dc.date.available |
2023-02-26T08:18:25Z |
|
dc.date.issued |
2022-10 |
|
dc.identifier.citation |
Waseem, K., Mushtaq, H., Abid, F., Abu-Mahfouz, A.M., Shaikh, A., Turan, M. & Rasheed, J. 2022. Forecasting of air quality using an optimized recurrent neural network. <i>Processes, 10(10).</i> http://hdl.handle.net/10204/12616 |
en_ZA |
dc.identifier.issn |
2227-9717 |
|
dc.identifier.uri |
https://doi.org/10.3390/pr10102117
|
|
dc.identifier.uri |
http://hdl.handle.net/10204/12616
|
|
dc.description.abstract |
Clean air is necessary for leading a healthy life. Many respiratory illnesses have their root in the poor quality of air across regions. Due to the tremendous impact of air quality on people’s lives, it is essential to devise a mechanism through which air pollutants (PM2.5, NOx, COx, SOx) can be forecasted. However, forecasting air quality and its pollutants is complicated as air quality depends on several factors such as weather, vehicular, and power plant emissions. This aim of this research was to find the impact of weather on PM2.5 concentrations and to forecast the daily and hourly PM2.5 concentration for the next 30 days and 72 h in Pakistan. This forecasting was done through state-of-the-art deep learning and machine learning models such as FbProphet, LSTM, and LSTM encoder–decoder. This research also successfully forecasted the proposed daily and hourly PM2.5 concentration. The LSTM encoder–decoder had the best performance and successfully forecasted PM2.5 concentration with a mean absolute percentage error (MAPE) of 28.2%, 15.07%, and 42.1% daily, and 11.75%, 9.5%, and 7.4% hourly for different cities in Pakistan. This research proves that a data-driven approach is essential for resolving air pollution in Pakistan. |
en_US |
dc.format |
Fulltext |
en_US |
dc.language.iso |
en |
en_US |
dc.relation.uri |
https://www.mdpi.com/2227-9717/10/10/2117/htm |
en_US |
dc.source |
Processes, 10(10) |
en_US |
dc.subject |
Air quality |
en_US |
dc.subject |
Fb Prophet |
en_US |
dc.subject |
Forecasting |
en_US |
dc.subject |
Neural network |
en_US |
dc.subject |
PM2.5 |
en_US |
dc.subject |
Time series models |
en_US |
dc.title |
Forecasting of air quality using an optimized recurrent neural network |
en_US |
dc.type |
Article |
en_US |
dc.description.pages |
21 |
en_US |
dc.description.note |
Copyright: © 2022 by the author. 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/). |
en_US |
dc.description.cluster |
Next Generation Enterprises & Institutions |
en_US |
dc.description.impactarea |
EDT4IR Management |
en_US |
dc.identifier.apacitation |
Waseem, K., Mushtaq, H., Abid, F., Abu-Mahfouz, A. M., Shaikh, A., Turan, M., & Rasheed, J. (2022). Forecasting of air quality using an optimized recurrent neural network. <i>Processes, 10(10)</i>, http://hdl.handle.net/10204/12616 |
en_ZA |
dc.identifier.chicagocitation |
Waseem, KH, H Mushtaq, F Abid, Adnan MI Abu-Mahfouz, A Shaikh, M Turan, and J Rasheed "Forecasting of air quality using an optimized recurrent neural network." <i>Processes, 10(10)</i> (2022) http://hdl.handle.net/10204/12616 |
en_ZA |
dc.identifier.vancouvercitation |
Waseem K, Mushtaq H, Abid F, Abu-Mahfouz AM, Shaikh A, Turan M, et al. Forecasting of air quality using an optimized recurrent neural network. Processes, 10(10). 2022; http://hdl.handle.net/10204/12616. |
en_ZA |
dc.identifier.ris |
TY - Article
AU - Waseem, KH
AU - Mushtaq, H
AU - Abid, F
AU - Abu-Mahfouz, Adnan MI
AU - Shaikh, A
AU - Turan, M
AU - Rasheed, J
AB - Clean air is necessary for leading a healthy life. Many respiratory illnesses have their root in the poor quality of air across regions. Due to the tremendous impact of air quality on people’s lives, it is essential to devise a mechanism through which air pollutants (PM2.5, NOx, COx, SOx) can be forecasted. However, forecasting air quality and its pollutants is complicated as air quality depends on several factors such as weather, vehicular, and power plant emissions. This aim of this research was to find the impact of weather on PM2.5 concentrations and to forecast the daily and hourly PM2.5 concentration for the next 30 days and 72 h in Pakistan. This forecasting was done through state-of-the-art deep learning and machine learning models such as FbProphet, LSTM, and LSTM encoder–decoder. This research also successfully forecasted the proposed daily and hourly PM2.5 concentration. The LSTM encoder–decoder had the best performance and successfully forecasted PM2.5 concentration with a mean absolute percentage error (MAPE) of 28.2%, 15.07%, and 42.1% daily, and 11.75%, 9.5%, and 7.4% hourly for different cities in Pakistan. This research proves that a data-driven approach is essential for resolving air pollution in Pakistan.
DA - 2022-10
DB - ResearchSpace
DP - CSIR
J1 - Processes, 10(10)
KW - Air quality
KW - Fb Prophet
KW - Forecasting
KW - Neural network
KW - PM2.5
KW - Time series models
LK - https://researchspace.csir.co.za
PY - 2022
SM - 2227-9717
T1 - Forecasting of air quality using an optimized recurrent neural network
TI - Forecasting of air quality using an optimized recurrent neural network
UR - http://hdl.handle.net/10204/12616
ER -
|
en_ZA |
dc.identifier.worklist |
26508 |
en_US |