A New Approach to Singularity Approximation

Mathematicians often take equations that govern fluid flow and run digital simulations. They start with a set of initial conditions, then watch until the value of some quantity like velocity or vorticity begins to grow wildly. Yet, computers can't definitively spot a singularity for the simple reason that they can't work with infinite values. If a singularity exists, computer models might get close to the point where the equations blow up, but they can never see it directly. A team of mathematicians has uncovered an entirely new way to approximate singularities. It's one that harnesses a recently developed form of deep learn. The results show how neural networks could help transform the search for new tions