Dark Matter

     

Using my MicroLIA classification framework, I have investigated advanced techniques for detecting dark matter lens events in the Legacy Survey of Space and Time (LSST). In recent work, we introduced a novel anomaly detection approach using isolation forests to efficiently identify these signals in lightcurve data. In a second paper, we showed that competitive constraints on primordial black holes as dark matter require minimizing the false positive rate, demonstrating that Boosted Decision Trees and the Bayesian Information Criterion serve as highly effective discriminators compared to standard statistical tests.