This session will bring together researchers from environmental and health sciences addressing the complex challenges of integrating data and modelling approaches, with the aim order to harness the opportunities emerging for a fast increasing richness of environmental and health data. Pilot research in the UK has focused on how linking health and population records to forecasts of near-term air pollution can help to inform learning health systems and improve the management of frontline health services and patient health and well-being. Research focusing on life-course exposure and exposomics highlight the need for integrated modelling approaches and novel data science methods (e.g. blending, data cubes, deep/machine learning) to utilise long-term datasets, informing next-generation models of human exposure at individual to population level. We invite contributions focusing on methods for modelling and simulation of human-environment interactions, exposure and epidemiological studies with an emphasis on the utilisation of models and emerging environmental datasets (e.g. earth observation products from the SENTINEL satellites), as well as new methodological approaches for the integration of large, rich datasets. Our emphasis in this session will be on fostering an interdisciplinary dialogue between computer & data scientists, environmental researchers and public health experts to generate new ideas. Building on previous sessions and workshops, which have generated special journal issues and community papers, the intent for this session is to lay the foundations for a collaborative and interdisciplinary activity resulting in (a) publication(s) identifying the next steps and emerging research needs in this area.
Key topics: Environmental pollution, Public health, Integrated modelling, Data science