Predictive Modeling of Work-Rest Schedule for Agricultural Workers Using Heat Stress and Physiological Data

Area of Science:

• Occupational health and safety
• Environmental physiology
• Agricultural science

Background:

• Heat stress poses significant risks in agricultural settings, impacting worker productivity and safety.
• Existing heat stress management strategies often lack practical, individualized tools for real-time application.
• The agricultural sector faces challenges in mitigating heat-related occupational hazards.

Purpose of the Study:

• To develop and validate predictive tools for optimizing work-rest schedules in hot agricultural environments.
• To provide supervisors with practical methods for assessing heat-related risk and managing worker fatigue.
• To enhance heat stress management policies and worker scheduling through field-tested models.

Main Methods:

• Utilized routinely measured inputs including wet-bulb globe temperature (WBGT), heart-rate metrics, age, and mechanization status.
• Developed predictive models to estimate safe continuous work durations and necessary recovery periods for individual workers.
• Field-tested the models in various agricultural settings, including smallholder and mechanized operations.

Main Results:

• The study successfully developed practical, field-tested predictive tools for work-rest scheduling in hot agricultural settings.
• The models accurately estimate safe work durations and recovery periods based on individual worker data and environmental conditions.
• The tools demonstrated applicability for both smallholder and mechanized agricultural operations.

Conclusions:

• The developed predictive tools offer a practical solution for on-site heat stress management in agriculture.
• These tools can effectively reduce heat-related fatigue, minimize injury risk, and maintain worker productivity.
• Integration into supervisor checklists, mobile apps, or wearable sensors can immediately improve heat stress management policies and worker scheduling.