An Explainable Multi-Modal Deep Learning Framework for Investigating the Influences of Dynamic Environmental Exposure on Momentary Stress.
- 1Institute of Space and Earth Information Science, The Chinese University of Hong Kong, Shatin, Hong Kong Special Administrative Region999077, China.
- 2Department of Geography and Resource Management, The Chinese University of Hong Kong, Shatin, Hong Kong Special Administrative Region999077, China.
Abstract
Urban stressors pose critical public health concerns by adversely affecting residents' mental health. However, past studies have mostly focused on single-modal stressors under static exposure paradigms, with limited exploration of nonlinear environment-stress relationships. This study proposes an explainable multimodal deep learning framework that integrates remote sensing imagery (RSI), street-view imagery (SVI), mobile sensor data, and points of interest (POIs) to accurately predict and explain momentary stress in urban environments. Using 4342 momentary stress records and 125,440 min-level environmental exposure records collected in Hong Kong, we validated the framework, achieving an accuracy of 78.26% and an AUC-ROC of 82.77%. A multilevel gradient-based explainability analysis reveals that (i) environmental exposure within the most recent 25 min exerts the strongest influence on momentary stress and notable spatial heterogeneity exists in stress prediction, highlighting the importance of capturing exposure dynamics; (ii) specific environmental thresholds were identified, including 55 dBA for noise, 25 μg/m3 for PM2.5, 32 °C for temperature, 40%-70% for humidity, and 25% for greenery visibility; and (iii) from an aerial perspective, open spaces consistently suppress stress, while the influence of buildings varies depending on surrounding spatial configuration. This study provides an integrative and explainable tool offering actionable insights for public health interventions.
Related
- Environmental influences on physical activity among young rural women: a qualitative study
- Male reproductive health under environmental, pharmacological, and disease influences: a scoping review
- Exploring Environmental Influences on Mono(2-Ethylhexyl) Phthalate (MEHP) Exposure in Common Bottlenose Dolphins (Tursiops truncatus) in Sarasota Bay, FL, USA.
- Genetic and environmental influences on rotator cuff tears: a population-based twin study
- From Who experiences stress to When It Occurs: Revisiting Lazarus’ transactional model of stress using an ecological momentary assessment framework
BibTeX
@article{wang2026explainable,
title = {{An Explainable Multi-Modal Deep Learning Framework for Investigating the Influences of Dynamic Environmental Exposure on Momentary Stress.}},
author = {Linsen Wang and Mei-Po Kwan and Liuyi Song},
journal = {Environmental science \& technology},
year = {2026},
month = oct,
doi = {10.1021/acs.est.6c09466},
url = {https://europepmc.org/article/MED/42916997},
note = {CC BY},
}
RIS
TY - JOUR
TI - An Explainable Multi-Modal Deep Learning Framework for Investigating the Influences of Dynamic Environmental Exposure on Momentary Stress.
AU - Linsen Wang
AU - Mei-Po Kwan
AU - Liuyi Song
PY - 2026
DA - 2026/10/01
JO - Environmental science & technology
DO - 10.1021/acs.est.6c09466
UR - https://europepmc.org/article/MED/42916997
AB - Urban stressors pose critical public health concerns by adversely affecting residents' mental health. However, past studies have mostly focused on single-modal stressors under static exposure paradigms, with limited exploration of nonlinear environment-stress relationships. This study proposes an explainable multimodal deep learning framework that integrates remote sensing imagery (RSI), street-view imagery (SVI), mobile sensor data, and points of interest (POIs) to accurately predict and explain momentary stress in urban environments. Using 4342 momentary stress records and 125,440 min-level environmental exposure records collected in Hong Kong, we validated the framework, achieving an accuracy of 78.26% and an AUC-ROC of 82.77%. A multilevel gradient-based explainability analysis reveals that (i) environmental exposure within the most recent 25 min exerts the strongest influence on momentary stress and notable spatial heterogeneity exists in stress prediction, highlighting the importance of capturing exposure dynamics; (ii) specific environmental thresholds were identified, including 55 dBA for noise, 25 μg/m3 for PM2.5, 32 °C for temperature, 40%-70% for humidity, and 25% for greenery visibility; and (iii) from an aerial perspective, open spaces consistently suppress stress, while the influence of buildings varies depending on surrounding spatial configuration. This study provides an integrative and explainable tool offering actionable insights for public health interventions.
SN - 0013-936X
SN - 1520-5851
ER -