Enhancing Air-Quality Predictions on University Campuses: A Machine-Learning Approach to PM2.5 Forecasting at the University of Petroșani

Fabian Arun Panaite, Cosmin Rus, Monica Leba (), Andreea Cristina Ionica () and Michael Windisch
Additional contact information
Fabian Arun Panaite: Department of System Control and Computer Engineering, University of Petrosani, 332006 Petrosani, Romania
Cosmin Rus: Department of System Control and Computer Engineering, University of Petrosani, 332006 Petrosani, Romania
Monica Leba: Department of System Control and Computer Engineering, University of Petrosani, 332006 Petrosani, Romania
Andreea Cristina Ionica: Department of Management and Industrial Engineering, University of Petrosani, 332006 Petrosani, Romania
Michael Windisch: Faculty Electronic Engineering & Entrepreneurship, University of Applied Sciences Technikum Wien, 1200 Vienna, Austria

Sustainability, 2024, vol. 16, issue 17, 1-20

Abstract: This study focuses on predicting PM2.5 levels at the University of Petroșani by employing advanced machine-learning techniques to analyze a dataset that encapsulates a wide array of air pollutants and meteorological factors. Utilizing data from Internet of Things (IoT) sensors and established environmental monitoring stations, the research leverages Random Forest, Gradient Boosting Machines, and Support Vector Regression models to forecast air quality, emphasizing the complex interplay between various pollutants. The models demonstrate varying degrees of accuracy, with the Random Forest model achieving the highest predictive power, indicated by an R 2 score of 0.82764. Our findings highlight the significant impact of specific pollutants such as NO, NO 2 , and CO on PM2.5 levels, suggesting targeted mitigation strategies could enhance local air quality. Additionally, the study explores the role of temporal dynamics in pollution trends, employing time-series analysis to further refine the predictive accuracy. This research contributes to the field of environmental science by providing a nuanced understanding of air-quality fluctuations in a university setting and offering a replicable model for similar environments seeking to reduce airborne pollutants and protect public health.

Keywords: campus air quality; sustainable campus; air monitoring; pollutant analysis; predictive analytics (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/16/17/7854/pdf (application/pdf)
https://www.mdpi.com/2071-1050/16/17/7854/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:16:y:2024:i:17:p:7854-:d:1474365

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().