Correcting the systematic error of the density functional theory calculation: the alternate combination approach of genetic algorithm and neural network
文献类型：期刊论文
| ; | |
| 作者 | Wang TT (Wang Ting-Ting); Li WL (Li Wen-Long); Chen ZH (Chen Zhang-Hui); Miao L (Miao Ling); Chen, ZH, Chinese Acad Sci, Inst Semicond, State Key Lab Superlattices & Microstruct, Beijing 100083, Peoples R China. 电子邮箱地址: zhanghuichen88@gmail.com |
| 刊名 | chinese physics b
 ; CHINESE PHYSICS B
|
| 出版日期 | 2010 ; 2010 |
| 卷号 | 19期号:7页码:art. no. 076401 |
| 关键词 | density functional theory Density Functional Theory Neural Network Genetic Algorithm Alternate Combination Linear-regression Correction Training Set Electron-gas Prediction Approximation Descriptors Accurate Energy Heat neural network genetic algorithm alternate combination LINEAR-REGRESSION CORRECTION TRAINING SET ELECTRON-GAS PREDICTION APPROXIMATION DESCRIPTORS ACCURATE ENERGY HEAT |
| 通讯作者 | chen, zh, chinese acad sci, inst semicond, state key lab superlattices & microstruct, beijing 100083, peoples r china. 电子邮箱地址: zhanghuichen88@gmail.com |
| 合作状况 | 国内 |
| 英文摘要 | 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.; 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.; submitted by 阎军 (yanj@red.semi.ac.cn) on 2010-08-17t01:33:38z no. of bitstreams: 1 correcting the systematic error of the density functional theory calculation.pdf: 187209 bytes, checksum: 692be22238bc711b969609e372eef80b (md5); approved for entry into archive by 阎军(yanj@red.semi.ac.cn) on 2010-08-17t02:26:30z (gmt) no. of bitstreams: 1 correcting the systematic error of the density functional theory calculation.pdf: 187209 bytes, checksum: 692be22238bc711b969609e372eef80b (md5); made available in dspace on 2010-08-17t02:26:30z (gmt). no. of bitstreams: 1 correcting the systematic error of the density functional theory calculation.pdf: 187209 bytes, checksum: 692be22238bc711b969609e372eef80b (md5) previous issue date: 2010; 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).; 国内 |
| 学科主题 | 半导体物理 ; 半导体物理 |
| 收录类别 | SCI |
| 资助信息 | 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). |
| 语种 | 英语 ; 英语 |
| 资助机构 | 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). |
| 公开日期 | 2010-08-17 ; 2010-08-17 ; 2010-10-15 |
| 源URL | [http://ir.semi.ac.cn/handle/172111/13483]  |
| 专题 | 半导体研究所_半导体超晶格国家重点实验室 |
| 通讯作者 | Chen, ZH, Chinese Acad Sci, Inst Semicond, State Key Lab Superlattices & Microstruct, Beijing 100083, Peoples R China. 电子邮箱地址: zhanghuichen88@gmail.com |
| 推荐引用方式 GB/T 7714 | Wang TT ,Li WL ,Chen ZH ,et al. Correcting the systematic error of the density functional theory calculation: the alternate combination approach of genetic algorithm and neural network, Correcting the systematic error of the density functional theory calculation: the alternate combination approach of genetic algorithm and neural network[J]. chinese physics b, CHINESE PHYSICS B,2010, 2010,19, 19(7):art. no. 076401, Art. No. 076401. |
| APA | Wang TT ,Li WL ,Chen ZH ,Miao L ,&Chen, ZH, Chinese Acad Sci, Inst Semicond, State Key Lab Superlattices & Microstruct, Beijing 100083, Peoples R China. 电子邮箱地址: zhanghuichen88@gmail.com.(2010).Correcting the systematic error of the density functional theory calculation: the alternate combination approach of genetic algorithm and neural network.chinese physics b,19(7),art. no. 076401. |
| MLA | Wang TT ,et al."Correcting the systematic error of the density functional theory calculation: the alternate combination approach of genetic algorithm and neural network".chinese physics b 19.7(2010):art. no. 076401. |
入库方式： OAI收割
来源：半导体研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。