"This group works in widely disparate fields, ranging from astronomy to nuclear physics, with applications that share the common goal of extracting rare and, sometimes, weak signals from the data. The glue that connects each is an AI framework developed by UNM Postdoc Dr. Jeff Schueler to search for rare events consisting of distinct, highly overlapping objects that span a large dynamic range. Earlier efforts have separated overlapping features, but not with high efficiency and often only with heavy computing, so the UNM/LANL team proposes replacing the cutoff with a more flexible AI framework. “Our framework goes further: rather than discarding weak signals, it detects them, reconstructs them, and identifies what they are,” the researchers said. Our hope is that this kind of AI workflow could be integrated into the Genesis platform to serve the entire scientific community," concluded Loomba.