Skip to main navigation Skip to search Skip to main content

Modelling and predicting classroom indoor air quality using machine learning algorithms

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

Abstract

Air quality in schools can significantly impact students’ health and academic performance. This research collected air quality data from two schools to develop predictive models for indoor air quality (IAQ). Artificial Neural Networks (ANNs) were used to simulate the influence of outdoor air pollution and classroom activities on IAQ, while Long Short-Term Memory (LSTM) models predicted real-time IAQ. Comparative analysis shows IAQ issues are localised, requiring model adjustment specific to school environments. Findings provide insights into IAQ management, helping schools maintain healthier learning environments.

Original languageEnglish
Title of host publicationProceedings of Building Simulation 2025
Subtitle of host publication19th Conference of IBPSA
EditorsQuentin Jackson, Priya Gandhi, Nicki Parker, Marie karekla, PC Thomas, Chirag Deb, Ozgur Gocer, Jungsoo Kim, Veronica Garcia, Rebecca Powles
PublisherInternational Building Performance Simulation Association
Pages1-6
Number of pages6
ISBN (Electronic)9781775052043
DOIs
Publication statusPublished - 2025
Event19th IBPSA Conference on Building Simulation, BS 2025 - Brisbane, Australia
Duration: 24 Aug 202527 Aug 2025

Publication series

NameBuilding Simulation Conference Proceedings
Volume19
ISSN (Print)2522-2708

Conference

Conference19th IBPSA Conference on Building Simulation, BS 2025
Country/TerritoryAustralia
CityBrisbane
Period24/08/2527/08/25

Fingerprint

Dive into the research topics of 'Modelling and predicting classroom indoor air quality using machine learning algorithms'. Together they form a unique fingerprint.

Cite this