Using machine learning for air quality prediction and sustainable urban planning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27230%2F25%3A10259457" target="_blank" >RIV/61989100:27230/25:10259457 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S2666188825005453?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S2666188825005453?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.sftr.2025.100981" target="_blank" >10.1016/j.sftr.2025.100981</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Using machine learning for air quality prediction and sustainable urban planning

Popis výsledku v původním jazyce

Air pollution has become a very serious issue worldwide, as evidenced by increasing PM2.5 levels. It is not just unhealthy to breathe in that polluted air, but it also causes respiratory problems, heart diseases, and lung cancer. There are many contributors to this environmental issue, including industrial growth, expansion of urban areas, agriculture, and burning of fossil fuels. All these sources emit harmful substances into the atmosphere and deteriorate air quality. Accurate and reliable tracking and prediction of air quality is very important for protecting public health, and it also aligns with Sustainable Development Goal (SDG) of &quot;Good Health and WellBeing&quot;, which aims to ensure good health for all. With the latest developments in artificial intelligence, machine learning has emerged as a valuable tool for air quality forecasting. This research investigates an innovative approach to predict the levels of air pollutants in Lahore, Pakistan, using data from January 2003 to December 2022, covering eight pollutants and four weather-related factors. The study uses several time-series models: SARIMA, seasonal autoregressive integrated moving-average with exogenous, Long short-term memory or LSTMS, and non-linear autoregressive. Two different evaluation performance criteria are deployed to evaluate these models: Root mean squared error (RMSE) and DTW for their overall performance metric. Results indicate that NAR has performed better than others with a minimum RMSE of 23.52 and a DTW of 5023. Results indicate a projected % increase in AQI by 13 % for 2030 from the base year 2022. The study provides important information regarding future trends in air quality. It offers different strategies for pollution mitigation that regulators can adopt with the support of strategic planning and policymaking in line with SDGs&apos; objectives.

Název v anglickém jazyce

Using machine learning for air quality prediction and sustainable urban planning

Popis výsledku anglicky

Air pollution has become a very serious issue worldwide, as evidenced by increasing PM2.5 levels. It is not just unhealthy to breathe in that polluted air, but it also causes respiratory problems, heart diseases, and lung cancer. There are many contributors to this environmental issue, including industrial growth, expansion of urban areas, agriculture, and burning of fossil fuels. All these sources emit harmful substances into the atmosphere and deteriorate air quality. Accurate and reliable tracking and prediction of air quality is very important for protecting public health, and it also aligns with Sustainable Development Goal (SDG) of &quot;Good Health and WellBeing&quot;, which aims to ensure good health for all. With the latest developments in artificial intelligence, machine learning has emerged as a valuable tool for air quality forecasting. This research investigates an innovative approach to predict the levels of air pollutants in Lahore, Pakistan, using data from January 2003 to December 2022, covering eight pollutants and four weather-related factors. The study uses several time-series models: SARIMA, seasonal autoregressive integrated moving-average with exogenous, Long short-term memory or LSTMS, and non-linear autoregressive. Two different evaluation performance criteria are deployed to evaluate these models: Root mean squared error (RMSE) and DTW for their overall performance metric. Results indicate that NAR has performed better than others with a minimum RMSE of 23.52 and a DTW of 5023. Results indicate a projected % increase in AQI by 13 % for 2030 from the base year 2022. The study provides important information regarding future trends in air quality. It offers different strategies for pollution mitigation that regulators can adopt with the support of strategic planning and policymaking in line with SDGs&apos; objectives.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10510 - Climatic research

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Sustainable Futures

ISSN

2666-1888

e-ISSN

—

Svazek periodika

10

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

13

Strana od-do

nestránkováno

Kód UT WoS článku

001530522000001

EID výsledku v databázi Scopus

—