High levels of ambient fine particulate matter (PM2.5) combined with sparse ground monitoring networks that pose challenges to studying health effects of PM in India. We used machine learning to develop a PM2.5 model calibrated against ground monitoring based data from 1060 stations spanning 2008-2020. The resulting predictions can leverage existing, ongoing and future health studies in both urban and rural India to accurately assess the burden of ambient PM2.5 on a multitude of health outcomes.