jailcd2024037: Toward Sustainable AI for Indoor Air Quality Management: A Case Study on PM2.5 Analysis at Chiang Mai International Airport

Abstract

This case study systematically investigates the application of Sustainable Artificial Intelligence (AI) methodologies in analyzing multi-modal data, specifically focusing on an extensive outdoor and indoor particulate matter (PM) sensor network at Chiang Mai International Airport. Aligned with the shared principles of Sustainable AI and low-carbon design, the study provides detailed insights into PM distribution within the airport's domestic terminal, a critical consideration for more than 4 million primary and secondary users. The research aims to contribute to the strategic development of low-carbon design, emphasizing energy efficiency and smart infrastructure. The study's nuanced understanding of particulate matter dynamics informs the data-driven decision-making processes related to sustainable architectural and environmental design practices. Moreover, by leveraging the accumulated data on indoor air quality, the study seeks to influence policy formulation, advocating for measures that prioritize air quality while aligning with the broader goal of promoting energy-efficient operations within the airport environment. By illustrating Sustainable AI as a practical model, the case study offers insights into integrating environmentally responsible solutions as technology-driven for indoor air quality management within broader sustainability frameworks.