Zobraziť v EDS

Evaluating machine learning models for air quality error mapping in Kraków, Poland.

Uložené v:
Podrobná bibliografia
Názov: Evaluating machine learning models for air quality error mapping in Kraków, Poland.
Autori: Zaręba, Mateusz, Cogiel, Szymon, Węglińska, Elżbieta, Danek, Tomasz
Zdroj: Miscellanea Geographica: Regional Studies on Development; Jan2026, Vol. 30 Issue 1, p24-32, 9p
Predmety: MACHINE learning, PARTICULATE matter, CITIES & towns, AIR pollution measurement, ERROR analysis in mathematics, BOX-Jenkins forecasting
Geografický termín: POLAND, KRAKOW (Poland)
Abstrakt: Accurate air quality prediction is essential for sustainable urban development. This study evaluates the performance of machine learning models, including DLinear and XGBoost, in comparison with the traditional Autoregressive Integrated Moving Average (ARIMA) method for predicting fine particulate matter (PM2.5) concentrations in Kraków, Poland. A dense network of low-cost sensors was used to generate high-resolution spatial and temporal data. Prediction errors were analysed using the Getis-Ord Gi* spatial statistics method during both extreme pollution events and low pollution days. The results indicate that DLinear achieved the lowest root mean square error (RMSE = 3.8 µg/m3), followed by XGBoost (RMSE = 6.7 µg/m3) and ARIMA (RMSE = 9.2 µg/m3). The spatial distribution of errors highlights the influence of environmental factors, such as humidity and proximity to water bodies, on model accuracy. These findings show the limitations of current prediction models and emphasize the need for spatially adaptive approaches to improve pollution. [ABSTRACT FROM AUTHOR]
Copyright of Miscellanea Geographica: Regional Studies on Development is the property of Sciendo and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáza: Complementary Index
Popis
Abstrakt:Accurate air quality prediction is essential for sustainable urban development. This study evaluates the performance of machine learning models, including DLinear and XGBoost, in comparison with the traditional Autoregressive Integrated Moving Average (ARIMA) method for predicting fine particulate matter (PM<subscript>2.5</subscript>) concentrations in Kraków, Poland. A dense network of low-cost sensors was used to generate high-resolution spatial and temporal data. Prediction errors were analysed using the Getis-Ord Gi* spatial statistics method during both extreme pollution events and low pollution days. The results indicate that DLinear achieved the lowest root mean square error (RMSE = 3.8 µg/m<sup>3</sup>), followed by XGBoost (RMSE = 6.7 µg/m<sup>3</sup>) and ARIMA (RMSE = 9.2 µg/m<sup>3</sup>). The spatial distribution of errors highlights the influence of environmental factors, such as humidity and proximity to water bodies, on model accuracy. These findings show the limitations of current prediction models and emphasize the need for spatially adaptive approaches to improve pollution. [ABSTRACT FROM AUTHOR]
ISSN:08676046
DOI:10.2478/mgrsd-2025-0026