|
|
| Type |
Symposium |
| Area |
Recent Trends in Computational Chemistry: Bigdata and Artificial Intelligence |
| Room No. |
Room 402 |
| Time |
FRI 16:20-: |
| Code |
PHYS3-6 |
| Subject |
Applying machine learning algorithms to materials property prediction and potential energy calculation |
| Authors |
Hyun Woo Kim*, Jino Im*, Hyunju Chang*
Center for Molecular Modeling and Simulation, Korea Research Institute of Chemical Technology, Korea
|
| Abstract |
Machine learning approaches become a new trend in computational chemistry recently as there is a constant need for more efficient and more accurate methods and machine learning methods are expected to be one of those methods. In principle, after training the machine with huge computational and/or experimental data, machine learning methods can be employed to solve various chemical problems. Here, we will present two applications of machine learning algorithms in predicting materials properties and calculating potential energies of chemical systems. In the first part, we will show a machine learning method reasonably predicts band gaps and formation energies of inorganic materials. Later, we will explain that the same machine learning technique can be utilized to calculate potential energies of molecules on a metal surface. During the presentation, we will briefly discuss the performance of established machine learning approaches. |
| E-mail |
ahwk@krict.re.kr |
|
121st General Meeting of the KCS