Berlin 2024 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
MP: Fachverband Theoretische und Mathematische Grundlagen der Physik
MP 11: Many-body Theory II
MP 11.4: Talk
Thursday, March 21, 2024, 10:50–11:10, HL 102
TBMaLT, a flexible toolkit for combining tight-binding and machine learning — •Wenbo Sun1, Guozheng Fan1, Adam McSloy2, Thomas Frauenheim3, and Bálint Aradi1 — 1University of Bremen, Bremen 28359, Germany — 2University of Bristol, Bristol BS8 1TS, United Kingdom — 3Constructor University, Bremen 28759, Germany
Tight-binding approaches, especially the Density Functional Tight-Binding (DFTB) and the Extended Tight-Binding (xTB), allow for efficient quantum mechanical simulations of large systems and long time scales. They are derived from ab initio Density Functional Theory using pragmatic approximations and some empirical terms, ensuring a fine balance between speed and accuracy. Their accuracy can be improved by tuning the empirical parameters using machine learning techniques, especially when information about the local environment of the atoms is incorporated. As the significant quantum mechanical contributions are still provided by the tight-binding models, and only short-ranged corrections are fitted, the learning procedure is typically shorter and more transferable. As a further advantage, derived quantum mechanical quantities can be calculated based on the tight-binding model without the need for additional learning.
We have developed the open-source framework TBMaLT, which allows the easy implementation of such combined approaches. The toolkit currently contains layers for the DFTB method and an interface to the GFN1-xTB Hamiltonian, but due to its modular structure, additional atom-based schemes can be implemented easily.
Keywords: tight-binding model; machine learning; DFTB; xTB