AI Integrated Environmental Monitoring for Heat Stress Management in Healthcare and Public Spaces

DOI

10.2991/978-94-6239-756-9_27How to use a DOI?

Keywords

AI integration; Environmental monitoring; Heat stress; Healthcare management; Public spaces

Abstract

Extreme heat events are increasing in frequency, intensity, and duration under climate change with a mean global temperature rise of 1.2 ℃ having arisen from increasing greenhouse gas emissions. This effect threatens public health in densely populated regions such as India. In this paper, an AI based environmental monitoring system for the prediction and control of heat stress in healthcare and educational settings is discussed. This study utilized machine learning (Random Forest, Gradient Boosting, CatBoost and SVR) and deep learning (LSTM) models to predict the Heat Index (HI), an apparent (“feels-like”) temperature derived from air temperature and relative humidity, using a five-year high-resolution meteorological dataset from a hospital campus in Gurugram, India, and to analyze the temporal dynamics of heat stress.[16] A multiple correlation analysis showed that the radiation and humidity parameters (especially longwave irradiance, wet bulb temperature, and UVB irradiance) had a significant effect on perceived thermal stress; >43% of observed hours were in categories of “danger” or “extreme caution”. The Random Forest model achieved the highest predictive performance (R² = 0.9993, RMSE = 0.3231), indicating strong nonlinear mapping and good generalization on the test set. The LSTM captured sequential dependencies in the time series (R² = 0.973, RMSE = 1.797) but showed higher error than the tree-based models under the present dataset and training configuration. These predictive outputs are embedded within a proactive heat stress management workflow that includes automated warnings, HVAC operational adjustments, and nature-based cooling measures such as shaded pathways and green roofs. Consistent with prior field evidence, such interventions can reduce heat stress exposure (often reported using WBGT) and improve operational resilience in high risk periods.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Manvendra Deswal
AU  - Rajkumar Balasubramaniam
AU  - Abhinav Raj
AU  - Sadaksh Arora
AU  - Sarthak Belekar
PY  - 2026
DA  - 2026/08/31
TI  - AI Integrated Environmental Monitoring for Heat Stress Management in Healthcare and Public Spaces
BT  - Proceedings of the Conference on Bioengineering for Global Health (SYMRESEARCH 2.0 2025)
PB  - Atlantis Press
SP  - 395
EP  - 413
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6239-756-9_27
DO  - 10.2991/978-94-6239-756-9_27
ID  - Deswal2026
ER  -