Adaptive Cognitive Systems Laboratory · ISU
A data-driven approach to designing a community-focused indoor heat emergency alert system for vulnerable residents.
This page summarizes the CommHEAT research program as described on the ACSL project page. For the full project site, visit commheat.org.
Extreme heat is the deadliest type of weather in the United States and disproportionately affects vulnerable populations. Often called the “silent killer” by health experts because of its gradual and invisible nature, extreme heat is especially dangerous for the elderly and low-income residents who are less likely to have centralized or adequate home cooling.
The 4th U.S. National Climate Assessment predicts that extreme heat events will increase markedly, with significant threats to human health. Lack of central air-conditioning and urban heat island effects—driven by urban density and limited tree canopy—can create dangerous indoor conditions, often worsened in low-income neighborhoods.
The overarching goal is to develop a community-focused, microclimate-informed indoor heat emergency alert (CommHEAT) system that strengthens and personalizes community heat-related emergency management. The framework combines data from residents and community partners in the Capitol East neighborhood of Des Moines with human behavior change theory and scientific machine learning (SciML) to better predict heat flux and human response—organized around five integrated objectives.
The approach is novel in its use of empirical data and participatory modeling with vulnerable residents and stakeholders to iteratively co-design information technology for public health.
CommHEAT develops and evaluates a framework for engaging community members and civic officials in co-developing specific, personalized responses to mitigate extreme heat, with emphasis on vulnerable populations.
Using a behavior change theory lens, the team collects data on current adaptation strategies during heat events and perceptions of heat health warning systems (HHWS) from residents and partners to define adaptation ranges and triggers. Modeled human behavior is integrated with physics-informed SciML models.
Data-driven SciML models aim to tailor alerts to specific people, situations, and events—including locations or buildings at elevated risk under current environmental conditions.
Individualized alerts are intended to support better decision-making, actionable distribution of temporary cooling resources, and reduced vulnerability in indoor and near-building spaces. The work aligns with the City of Des Moines climate action and adaptation plan, ADAPT DSM.
Tian Yao — Ph.D. student in Human–Computer Interaction, contributing to CommHEAT through the Adaptive Cognitive Systems Laboratory, Iowa State University.