Air pollution is a leading contributor to the global disease burden, which is a crucial concern as the air quality across sub-Saharan Africa significantly and rapidly deteriorates with accelerated urbanization, industrialization, and population growth. The synergistic association between heat waves and air pollution is expected to exacerbate with the changing climate, which poses a crucial threat to the health of vulnerable populations in low-income settings. Studies which indicate associations between maternal and prenatal exposure to environmental pollution and adverse health outcomes, highlight the need for further investigation in African populations, as such vulnerable subpopulations are not consistently investigated. Pregnant women who are exposed to heat stress coupled with air pollution are more susceptible to adverse birth outcomes including; miscarriages, stillbirth, preterm birth, low birth weight, and preeclampsia. Developing appropriate health sector responses and adaptive interventions relies on identifying these vulnerable populations along with their level of environmental risk. Socio-economic factors such as poverty, food and water insecurity, and limited access to healthcare facilities perpetuate vulnerability among these communities. Impacts of pollution exposure over periods of increased temperatures are difficult to measure and require refined data science and analytical approaches. The current poor networks of ground sensors for measuring air quality, piecemeal approaches to quantifying associations with adverse health outcomes and dearth of translation from evidence to intervention warrants a paradigm shift in approach. To address the lack of understanding of the environmental risk impacts on the changing epidemiology in sub-Saharan Africa, the proposed research project will aim to quantify the current and future impacts of air pollution on maternal and neonatal health through innovative data science approaches such as machine learning, by accelerating low-cost characterization of pollution exposure data while understanding its associations with adverse outcomes related to pregnancy, childbirth and early life. Further to this we will develop adaptive interventions that will help pregnant women and their children counter the risk imposed by exposure to pollutants and build resilience against the high odds of adverse health outcomes. The CHEAQI-MNCH project will provide an opportunity for emerging data scientists and researchers in Africa to engage, collaborate and develop transferrable skills, while contributing to a continental resource center for knowledge translation and dissemination within the fields of climate and health.

Monitoring air quality is fundamental for understanding the biological and environmental vulnerabilities of a population in order to mitigate the effects of climate change and to ensure human health. Quantifying the impacts of ambient air pollution on pregnant women and neonates is a complex task, especially in countries across sub-Saharan Africa, where access to pollution exposure data is limited. In this proposed research project, we will utilize advanced data science solutions such as machine learning approaches to characterize pollution exposure and to understand its associations with adverse outcomes in maternal, newborn and child health.