Public health research is critical for understanding the factors impacting entire populations, from climate change to air pollution, which significantly influences disease prevalence and overall well-being. Dr. Oladimeji Mudele, a leading Remote Sensing and Environmental Health Expert, pioneered an innovative tool that simplifies the analysis of satellite data, transforming the field.
“Pylandtemp focuses on extraction and measurement of land surface temperature using satellite image data without the need for extensive coding. The library simplifies the process of working with satellite imagery to analyze land surface temperature, which is crucial for various environmental and climate studies.,” Mudele said. “For instance, I investigate how high temperatures affect population-level cardiovascular and vector-borne diseases prevalence.”
Furthermore, Mudele’s motivation for creating systems that combine satellite imagery with geospatial data for early warning of disease spread stems from a critical need in regions where infectious diseases are prevalent, such as parts of Africa with a high malaria burden. “There is often a lack of sufficient meteorological data infrastructure, hindering our ability to investigate how climate influences disease spread and how we can mitigate these effects,” says Mudele. “To establish early warning systems in these areas, we rely heavily on satellite imagery.”
One of the researcher’s notable achievements is the development of an artificial intelligence tool to measure urban green spaces using satellite images. This tool addresses the challenge of modelling the spread of infectious diseases in urban areas by classifying urban vegetation based on high-resolution space-borne data. The framework, a collaborative effort with the Argentinean Commission for Space Activities, contributes to the control of infectious disease spread in Argentina.
In addition to his groundbreaking work in satellite data analysis, Mudele has made significant strides in predicting Dengue vector risks in urban areas using satellite data. His explainable machine learning pipeline predicts mosquito vector populations and identifies key environmental variables influencing vector population changes over time. This framework provides cities exposed to Dengue vectors with one-week-ahead predictions, enabling them to anticipate and plan for risk levels accordingly.
Mudele’s research, funded by prestigious grants and fellowships, including the Marie Sklodowska-Curie Actions under the European Commission’s H2020 project “EOXPOSURE,” has led to key insights in disease prediction and climate change mitigation. His work has not only expanded our understanding of the environmental mechanisms driving disease spread but has also paved the way for data-driven planning to minimize severe cases and deaths.
Looking to the future, he envisions a continued role for research and AI in measuring diseases in urban centers. He emphasises the need for more exploration in leveraging satellite imagery to develop causal models for understanding environmental mechanisms and driving precision public health interventions.
