Designing AI-Based air pollution early warning for low resource high vulnerability settings: insights from an adapted Technology Acceptance Model in Ulaanbaatar, Mongolia
1
School of Public Health Science, University of Waterloo Climate Institute, Waterloo, Canada
Popul. Med. 2026;8(Supplement Supplement 1):A3788
ABSTRACT
INTRODUCTION:
Real time monitoring and machine learning based early warning systems are increasingly used to support public health responses to air pollution. However, there is limited evidence on how such systems should be designed for residents in high risk low resource settings. This study uses a Technology Acceptance Model to generate design recommendations for a proposed real time monitoring and early warning system for air pollution in Ulaanbaatar, Mongolia.1
METHODS:
We conducted 25 semi structured interviews with adult residents across Ulaanbaatar who varied in age, health concerns and digital experience. Participants were introduced to a concept for a real time monitoring and early warning system and asked to reflect on perceived usefulness, ease of use, trust and broader contextual factors.
RESULTS:
Perceived usefulness and ease of use were important for engagement, but participants evaluated the system through three interrelated design domains. First, digital plurality highlighted the need for flexible access across devices and platforms, reflecting shared phones, variable connectivity and diverse digital practices. Second, credibility centred on trust in the institutions behind the system, transparency in how alerts are generated and clarity in the presentation of local air quality data. Third, contextual vulnerability underscored how health worries, financial constraints and existing stress shaped the ways people could act on warnings. User archetypes, ranging from digitally fluent caregivers to individuals facing structural barriers, illustrated how these domains translate into distinct design needs in low resource settings.
CONCLUSIONS:
Technology acceptance for air pollution early warning in low resource high vulnerability settings depends on design choices that support digital plurality, strengthen credibility and respond to contextual vulnerability. Design and deployment strategies should be grounded in qualitative engagement with residents to ensure technologies are usable, trustworthy and realistically actionable for communities living with heightened risk.
Real time monitoring and machine learning based early warning systems are increasingly used to support public health responses to air pollution. However, there is limited evidence on how such systems should be designed for residents in high risk low resource settings. This study uses a Technology Acceptance Model to generate design recommendations for a proposed real time monitoring and early warning system for air pollution in Ulaanbaatar, Mongolia.1
METHODS:
We conducted 25 semi structured interviews with adult residents across Ulaanbaatar who varied in age, health concerns and digital experience. Participants were introduced to a concept for a real time monitoring and early warning system and asked to reflect on perceived usefulness, ease of use, trust and broader contextual factors.
RESULTS:
Perceived usefulness and ease of use were important for engagement, but participants evaluated the system through three interrelated design domains. First, digital plurality highlighted the need for flexible access across devices and platforms, reflecting shared phones, variable connectivity and diverse digital practices. Second, credibility centred on trust in the institutions behind the system, transparency in how alerts are generated and clarity in the presentation of local air quality data. Third, contextual vulnerability underscored how health worries, financial constraints and existing stress shaped the ways people could act on warnings. User archetypes, ranging from digitally fluent caregivers to individuals facing structural barriers, illustrated how these domains translate into distinct design needs in low resource settings.
CONCLUSIONS:
Technology acceptance for air pollution early warning in low resource high vulnerability settings depends on design choices that support digital plurality, strengthen credibility and respond to contextual vulnerability. Design and deployment strategies should be grounded in qualitative engagement with residents to ensure technologies are usable, trustworthy and realistically actionable for communities living with heightened risk.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
