The ChemSpace Tool, when fully developed, is intended to divide chemical space into three subsets: the detectable space, the identifiable space, and the region that includes compounds that are not detectable or identifiable.
Three PNNL authored papers were accepted as posters to the ICLR 2023 Workshop on Physics for Machine Learning and Workshop on Mathematical and Empirical Understanding of Foundation Models.
A new policy database containing energy equity-related actions could serve as a useful starting point for state policymakers and stakeholders who want to enact similar energy equity measures or adapt policies to their local circumstances.
A PNNL innovation uses steam to recover heat from the high-temperature reactor effluent in the HTL process, substantially reducing the propensity for fouling and potentially reducing costs.
Machine learning models help identify important environmental properties that influence how often extreme rain events occur with critical intensity and duration.