Integrated Remote-Sensing and Environmental Data Analytics for Predictive Heat-Stress Risk Assessment and Digital Health Monitoring in South Africa

This paper presents a framework and a preliminary computational demonstration for predictive heat-stress risk assessment and digital health monitoring in South Africa. Heat-stress risk is increasing under climate change, yet location-specific early-warning tools remain scarce, and South Africa's first national climate and health surveillance platform is, in its present phase, oriented towards surveillance and visualisation. The paper specifies a data-integration procedure that combines ERA5/ERA5-Land reanalysis, ERA5-HEAT-derived Universal Thermal Climate Index data and MODIS land-surface temperature for six representative cities (Johannesburg, Pretoria, Cape Town, Durban, Bloemfontein and Polokwane), specifies the training and comparison of four supervised classifiers (Logistic Regression, Random Forest, XGBoost and Support Vector Machine), and proposes a five-layer digital-health early-warning architecture that maps risk categories to public-health messages. Because authenticated Copernicus and NASA Earthdata access was unavailable, the machine-learning stage is specified but not executed, and no predictive performance is reported. A demonstration using published climate normals and the National Weather Service Heat Index places Bloemfontein in the Extreme Caution band, Pretoria, Durban, Polokwane and Johannesburg in the Caution band, and Cape Town just below Caution. A humidity-sensitivity analysis shows that the categories for Johannesburg and Durban depend on estimated humidity, and a scenario analysis shows that Johannesburg's record-heat days reach the Danger band, whereas its monthly normal remains at the Caution threshold. These findings support the development of day-resolved, location-specific prediction that uses quality-controlled humidity inputs.

Authors

Publication Details

Journal
ABUAD Journal of Engineering Research and Development (AJERD)
Published
2026-11-15
DOI
https://doi.org/10.53982/ajerd.2026.0903.26-j
Primary Topic
Climate Change and Health Impacts
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Integrated Remote-Sensing and Environmental Data Analytics for Predictive Heat-Stress Risk Assessment and Digital Health Monitoring in South Africa

Segun Akinola
ABUAD Journal of Engineering Research and Development (AJERD)
Climate Change and Health Impacts
article

Integrated Remote-Sensing and Environmental Data Analytics for Predictive Heat-Stress Risk Assessment and Digital Health Monitoring in South Africa

Segun Akinola
article en

Abstract

This paper presents a framework and a preliminary computational demonstration for predictive heat-stress risk assessment and digital health monitoring in South Africa. Heat-stress risk is increasing under climate change, yet location-specific early-warning tools remain scarce, and South Africa's first national climate and health surveillance platform is, in its present phase, oriented towards surveillance and visualisation. The paper specifies a data-integration procedure that combines ERA5/ERA5-Land reanalysis, ERA5-HEAT-derived Universal Thermal Climate Index data and MODIS land-surface temperature for six representative cities (Johannesburg, Pretoria, Cape Town, Durban, Bloemfontein and Polokwane), specifies the training and comparison of four supervised classifiers (Logistic Regression, Random Forest, XGBoost and Support Vector Machine), and proposes a five-layer digital-health early-warning architecture that maps risk categories to public-health messages. Because authenticated Copernicus and NASA Earthdata access was unavailable, the machine-learning stage is specified but not executed, and no predictive performance is reported. A demonstration using published climate normals and the National Weather Service Heat Index places Bloemfontein in the Extreme Caution band, Pretoria, Durban, Polokwane and Johannesburg in the Caution band, and Cape Town just below Caution. A humidity-sensitivity analysis shows that the categories for Johannesburg and Durban depend on estimated humidity, and a scenario analysis shows that Johannesburg's record-heat days reach the Danger band, whereas its monthly normal remains at the Caution threshold. These findings support the development of day-resolved, location-specific prediction that uses quality-controlled humidity inputs.

ABUAD Journal of Engineering Research and Development (AJERD)Vol. 9(3)
Climate Change and Health Impacts
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon