Forecasting Occupational Survivability of Rickshaw Pullers in a Changing Climate with Wearable Data

2025-10-29

AI Summary

This study investigates occupational health risks among Dhaka’s cycle-rickshaw pullers under climate change, focusing on physiological strain induced by extreme heat. Method: Using wearable sensors, we collected real-time physiological data—including skin temperature, heart rate variability, and skin conductance—integrated with meteorological observations to develop a Linear Gaussian Bayesian Network (LGBN) for predicting heat stress responses. We further coupled this with CMIP6 climate projections to quantify future thermal exposure trends. Contribution/Results: We innovatively fused short-term physiological monitoring with long-term climate modeling, proposing—for the first time—a dynamic survival threshold warning system based on WBGT and skin temperature. The model achieves low prediction error (NMAE: 0.47–0.82). Results indicate that 32% of pullers currently face high heat risk—projected to rise to 37% during 2026–2030—with mean per-trip heat exposure nearing 12 minutes. Findings provide empirical evidence and actionable intervention pathways for climate adaptation among low-income outdoor workers.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Cycle rickshaw pullers are highly vulnerable to extreme heat, yet little is known about how their physiological biomarkers respond under such conditions. This study collected real-time weather and physiological data using wearable sensors from 100 rickshaw pullers in Dhaka, Bangladesh. In addition, interviews with 12 pullers explored their knowledge, perceptions, and experiences related to climate change. We developed a Linear Gaussian Bayesian Network (LGBN) regression model to predict key physiological biomarkers based on activity, weather, and demographic features. The model achieved normalized mean absolute error values of 0.82, 0.47, 0.65, and 0.67 for skin temperature, relative cardiac cost, skin conductance response, and skin conductance level, respectively. Using projections from 18 CMIP6 climate models, we layered the LGBN on future climate forecasts to analyze survivability for current (2023-2025) and future years (2026-2100). Based on thresholds of WBGT above 31.1°C and skin temperature above 35°C, 32% of rickshaw pullers already face high heat exposure risk. By 2026-2030, this percentage may rise to 37% with average exposure lasting nearly 12 minutes, or about two-thirds of the trip duration. A thematic analysis of interviews complements these findings, showing that rickshaw pullers recognize their increasing climate vulnerability and express concern about its effects on health and occupational survivability.

Problem

• Predicting physiological responses of rickshaw pullers to extreme heat using wearable sensors
• Assessing current and future heat exposure risks for occupational survivability
• Modeling climate change impacts on vulnerable outdoor workers' health safety

Innovation

• Used wearable sensors to collect physiological data
• Developed LGBN model to predict biomarkers
• Applied climate projections to assess future survivability