JAIST Repository >
School of Knowledge Science >
Conference Papers >
Conference Papers >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10119/14785
|
Title: | Novel mixture model for the representation of potential energy surfaces |
Authors: | Pham, Tien Lam Kino, Hiori Terakura, Kiyoyuki Miyake, Takashi Dam, Hieu Chi |
Keywords: | Materials informatics Data mining Machine learning Potential energy surface |
Issue Date: | 2016-10-17 |
Publisher: | American Institute of Physics |
Magazine name: | The Journal of Chemical Physics |
Volume: | 145 |
Number: | 15 |
Start page: | 154103-1 |
End page: | 154103-6 |
DOI: | 10.1063/1.4964318 |
Abstract: | We demonstrate that knowledge of chemical physics on a materials system can be automatically extracted from first-principles calculations using a data mining technique; this information can then be utilized to construct a simple empirical atomic potential model. By using unsupervised learning of the generative Gaussian mixture model, physically meaningful patterns of atomic local chemical environments can be detected automatically. Based on the obtained information regarding these atomic patterns, we propose a chemical-structure-dependent linear mixture model for estimating the atomic potential energy. Our experiments show that the proposed mixture model significantly improves the accuracy of the prediction of the potential energy surface for complex systems that possess a large diversity in their local structures. |
Rights: | Copyright 2016 American Institute of Physics. This article may be downloaded for personal use only. Any other use requires prior permission of the author and the American Institute of Physics. The following article appeared in Tien Lam Pham, Hiori Kino, Kiyoyuki Terakura, Takashi Miyake and Hieu Chi Dam, The Journal of Chemical Physics, 145(15), 154103 (2016) and may be found at http://dx.doi.org/10.1063/1.4964318 |
URI: | http://hdl.handle.net/10119/14785 |
Material Type: | publisher |
Appears in Collections: | a11-1. 会議発表論文 (Conference Papers)
|
Files in This Item:
File |
Description |
Size | Format |
22980.pdf | | 2044Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|