Environmental Justice and Lessons Learned from COVID-19 Outcomes – 1 Uncovering Hidden Patterns with Geometric Deep Learning and New NASA 2 Satellite Data

Irtually all aspects of our societal functioning – from food security to energy supply to healthcare – depend on the dynamics of environmental factors. Nevertheless, the social dimensions of weather and climate are noticeably less explored by the artificial intelligence community. Byharnessing the strength of geometric deep learning (GDL), we aim to investigate the pressing societal question the potential disproportional impacts of air quality on COVID-19 clinical severity. To quantify air pollution levels, here we use aerosol optical depth (AOD) records which measurethe reduction of the sunlight due to atmospheric haze, dust, and smoke. We also introduceunique and not yet broadly available NASA satellite records (NASAdat) on AOD, temperature andrelative humidity and discuss the utility of these new data for biosurveillance and climate justiceapplications, with a specific focus on COVID-19 in the States of Texas and Pennsylvania in USA.The results indicate that, in general, the poorer air quality tends to be associated with higherrates for clinical severity and, in case of Texas, this phenomenon particularly stands out in Texancounties characterized by higher socioeconomic vulnerability. This, in turn, raises a concern ofenvironmental injustice in these socio-economically disadvantaged communities. Furthermore,given that one of NASA’s recent long-term commitments is to address such inequitable burden ofenvironmental harm by expanding use of Earth science data such as NASAdat, this project is oneof the first steps toward developing a new platform integrating NASA’s satellite observations withDL tools for social good.