| CONDENSED MATTER: STRUCTURAL, MECHANICAL, AND THERMAL PROPERTIES |
Prev
Next
|
|
|
Correcting the systematic error of the density functional theory calculation: the alternate combination approach of genetic algorithm and neural network |
| Wang Ting-Ting(王婷婷)a)b), Li Wen-Long(李文龙)a), Chen Zhang-Hui(陈章辉)b)†, and Miao Ling(缪灵)a) |
a Department of Electronic Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China;
bState Key Laboratory for Superlattices and Microstructures, Institute of Semiconductors, Chinese Academy of Sciences,Beijing 100083, China |
|
|
|
|
Abstract The alternate combinational approach of genetic algorithm and neural network (AGANN) has been presented to correct the systematic error of the density functional theory (DFT) calculation. It treats the DFT as a black box and models the error through external statistical information. As a demonstration, the AGANN method has been applied in the correction of the lattice energies from the DFT calculation for 72 metal halides and hydrides. Through the AGANN correction, the mean absolute value of the relative errors of the calculated lattice energies to the experimental values decreases from 4.93% to 1.20% in the testing set. For comparison, the neural network approach reduces the mean value to 2.56%. And for the common combinational approach of genetic algorithm and neural network, the value drops to 2.15%. The multiple linear regression method almost has no correction effect here.
|
|
Accepted manuscript online:
|
|
PACS:
|
84.35.+i
|
(Neural networks)
|
| |
02.60.Pn
|
(Numerical optimization)
|
|
| Fund: Project supported by the National Basic Research Program of China (973 Program) (Grant No. G2009CB929300) and the National Natural Science Foundation of China (Grant No. 60521001 and 60925016). |
Cite this article:
Wang Ting-Ting(王婷婷), Li Wen-Long(李文龙), Chen Zhang-Hui(陈章辉), and Miao Ling(缪灵) Correcting the systematic error of the density functional theory calculation: the alternate combination approach of genetic algorithm and neural network 2010 Chin. Phys. B 19 076401
|
| [1] |
Hohenberg P and Kohn W 1964 Phys. Rev. 136 B864
|
| [2] |
Kohn W and Sham L J 1965 Phys. Rev. 140 A1133
|
| [3] |
Kohn W 1999 Rev. Mod. Phys. 71 1253
|
| [4] |
Bechstedt F and Del Sole R 1988 Phys. Rev. B 38 7710
|
| [5] |
Castleton C W M, H?glund A and Mirbt S 2006 Phys. Rev. B 73 35215
|
| [6] |
John P P and Yue W 1992 Phys. Rev. B 45 13244
|
| [7] |
Hu L H, Wang X J, Wong L H and Chen G H 2003 J. Chem. Phys. 119 11501
|
| [8] |
Wang X J, Wong L H, Hu L H, Chan C Y, Su Z M and Chen G H 2004 J. Chem. Phys. A 108 8514
|
| [9] |
Duan X M, Li Z H, Song G L, Wang W N, Chen G H and Fan K N 2005 Chem. Phys. Lett. 410 125
|
| [10] |
Duan X M, Song G L and Li Z H 2004 J. Chem. Phys. 121 7086
|
| [11] |
Duan X M, Li Z H, Hu H R, Song G L, Wang W N, Chen G H and Fan K N 2005 Chem. Phys. Lett. 409 315
|
| [12] |
Widrow B and Lehr M A 1990 Proc. IEEE 9 1415
|
| [13] |
Li W, Chen J F and Wang T 2009 Chin. Phys. B 18 2441
|
| [14] |
Lance D C 1995 Practical Handbook of Genetic Algorithms (Boca Raton Florida USA: CRC Press)
|
| [15] |
Li H, Shi L L, Zhang M and Su Z M 2007 J. Chem. Phys. 126 144101
|
| [16] |
Cook D F, Ragsdale C T and Major R L 2000 Eng. Appl. Artif. Intell. 13 391
|
| [17] |
Goldberg D E and Holland J H 1988 Machine Learning 3 95
|
| [18] |
Yu A L 2008 Chin. Phys. B 17 878
|
| [19] |
Zhang S, Liu H X, Gao D T and Du S D 2003 Chin. Phys. 12 594
|
| [20] |
John P P, Kieron B and Matthias E 1996 Phys. Rev. Lett. 77 3865
|
| [21] |
Perdew J P and Wang Y 1992 Phys. Rev. B 45 13244
|
| [22] |
Kresse G and Hafner J 1993 Phys. Rev. B 47 558
|
| [23] |
Kresse G and Furthmuller J 1996 Phys. Rev. B 54 11169
|
| [24] |
David V 1990 Phys. Rev. B 41 7892
|
| [25] |
David R L 2006 Handbook of Chemistry and Physics 87th edition (Boca Raton Florida USA: CRC Press) endfootnotesize
|
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
