DPG Phi
Verhandlungen
Verhandlungen
DPG

Regensburg 2019 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

CPP: Fachverband Chemische Physik und Polymerphysik

CPP 30: Complex Fluids and Colloids, Micelles and Vesicles (joint session CPP/DY)

CPP 30.7: Talk

Wednesday, April 3, 2019, 11:30–11:45, H14

A classical density functional from machine learning and a convolutional neural network — •shangchun Lin and Martin Oettel — Institut für Angewandte Physik, Universität Tübingen , Tübingen, Deutschland

We use machine learning methods to approximate a classical density functional. The functional *learns* by comparing the density profile it generates with that of simulations. As a study case, we choose the model problem of a Lennard Jones fluid in one dimension where there is no exact solution available and training data sets must be obtained from simulations. After separating the excess free energy functional into a "repulsive" and an "attractive" part, machine learning finds a functional in weighted density form for the attractive part. The density profile at a hard wall shows good agreement for thermodynamic conditions beyond the training set conditions. This also holds for the equation of state if it is evaluated near the training temperature.

100% | Mobile Layout | Deutsche Version | Contact/Imprint/Privacy
DPG-Physik > DPG-Verhandlungen > 2019 > Regensburg