Environmental Health Data Science for Air Pollution Regulation
The Data Science Competence Center (DSCC) at the Swiss Federal Statistical Office is pleased to invite you to the next webinar in the "Data Science and AI for Public Good" series.
In this webinar Dr Corwin Zigler and Dr Lucas Henneman will introduce how statistical and machine learning methods for causal inference can help inform public policies.
Regulations to limit health impacts of air pollution exposure are among the most beneficial and expensive federal regulations in the US and abroad. Informing these regulations with evidence of the health impacts of air quality policies draws from many disciplines, all of which are experiencing a growth of modern data science methodologies to accompany advances in measurement technology, data availability, and computation. This talk will introduce how statistical and machine learning methods for causal inference have emerged at the forefront of ongoing regulatory policy debates and outline some areas for ongoing methods development. Then, a new data science framework for regulatory health impact assessment enabled by large-scale health data, statistical methods, and a novel computational air quality model will be presented. This framework will be illustrated through evaluating the health burden associated with 20 years’ worth of pollution from coal power plants, which quantifies changes in mortality burden amid regulations on US emissions sources. Outlining this array of research contributions demonstrates one example of an interdisciplinary health data science research program designed address questions of high relevance to environmental health decision makers.
Youtube Live Streaming: youtube.com/live/RGS6sk2Yxho
Mentimeter link for questions: www.menti.com/alypzr8mkt2i