Description of the potential energy surface of the water dimer with an artificial neural network

Kyoung Tai No; Byung Ha Chang; Su Yeon Kim; Mu Shik Jhon; Harold A. Scheraga

doi:10.1016/s0009-2614(97)00448-x

Description of the potential energy surface of the water dimer with an artificial neural network

Kyoung Tai No, Byung Ha Chang, Su Yeon Kim, Mu Shik Jhon, Harold A. Scheraga

Research output: Contribution to journal › Article › peer-review

52 Citations (Scopus)

Abstract

A potential energy function for the water dimer has been developed with an artificial neural network (back propagation of error algorithm). The potential energy surface was obtained with 6s3p3d/3s3p MP2 ab initio MO calculations. The trained neural network reproduced the potential energy surface of the water dimer very well, not only in the low-energy region but also in the high-energy region.

Original language	English
Pages (from-to)	152-156
Number of pages	5
Journal	Chemical Physics Letters
Volume	271
Issue number	1-3
DOIs	https://doi.org/10.1016/s0009-2614(97)00448-x
Publication status	Published - 1997 Jun 6

Bibliographical note

Funding Information:
This work was supported by research grants from the Basic Science Research Inst. Program of the Ministry of Education (BSRI-96-3448), Korea, from the US National Institutes of Health (GM-14312), and from the US National Science Foundation (MCB95-13167 and INT93-06345). We thank Professor K.S. Kim for providing the coefficients of the basis functions.

All Science Journal Classification (ASJC) codes

Physics and Astronomy(all)
Physical and Theoretical Chemistry

Access to Document

10.1016/s0009-2614(97)00448-x

Cite this

@article{ac30756fc79c466994b0778da8d4ed29,

title = "Description of the potential energy surface of the water dimer with an artificial neural network",

abstract = "A potential energy function for the water dimer has been developed with an artificial neural network (back propagation of error algorithm). The potential energy surface was obtained with 6s3p3d/3s3p MP2 ab initio MO calculations. The trained neural network reproduced the potential energy surface of the water dimer very well, not only in the low-energy region but also in the high-energy region.",

author = "No, {Kyoung Tai} and Chang, {Byung Ha} and Kim, {Su Yeon} and Jhon, {Mu Shik} and Scheraga, {Harold A.}",

note = "Funding Information: This work was supported by research grants from the Basic Science Research Inst. Program of the Ministry of Education (BSRI-96-3448), Korea, from the US National Institutes of Health (GM-14312), and from the US National Science Foundation (MCB95-13167 and INT93-06345). We thank Professor K.S. Kim for providing the coefficients of the basis functions.",

year = "1997",

month = jun,

day = "6",

doi = "10.1016/s0009-2614(97)00448-x",

language = "English",

volume = "271",

pages = "152--156",

journal = "Chemical Physics Letters",

issn = "0009-2614",

publisher = "Elsevier",

number = "1-3",

}

TY - JOUR

T1 - Description of the potential energy surface of the water dimer with an artificial neural network

AU - No, Kyoung Tai

AU - Chang, Byung Ha

AU - Kim, Su Yeon

AU - Jhon, Mu Shik

AU - Scheraga, Harold A.

N1 - Funding Information: This work was supported by research grants from the Basic Science Research Inst. Program of the Ministry of Education (BSRI-96-3448), Korea, from the US National Institutes of Health (GM-14312), and from the US National Science Foundation (MCB95-13167 and INT93-06345). We thank Professor K.S. Kim for providing the coefficients of the basis functions.

PY - 1997/6/6

Y1 - 1997/6/6

N2 - A potential energy function for the water dimer has been developed with an artificial neural network (back propagation of error algorithm). The potential energy surface was obtained with 6s3p3d/3s3p MP2 ab initio MO calculations. The trained neural network reproduced the potential energy surface of the water dimer very well, not only in the low-energy region but also in the high-energy region.

AB - A potential energy function for the water dimer has been developed with an artificial neural network (back propagation of error algorithm). The potential energy surface was obtained with 6s3p3d/3s3p MP2 ab initio MO calculations. The trained neural network reproduced the potential energy surface of the water dimer very well, not only in the low-energy region but also in the high-energy region.

UR - http://www.scopus.com/inward/record.url?scp=0031555986&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031555986&partnerID=8YFLogxK

U2 - 10.1016/s0009-2614(97)00448-x

DO - 10.1016/s0009-2614(97)00448-x

M3 - Article

AN - SCOPUS:0031555986

SN - 0009-2614

VL - 271

SP - 152

EP - 156

JO - Chemical Physics Letters

JF - Chemical Physics Letters

IS - 1-3

ER -

Description of the potential energy surface of the water dimer with an artificial neural network

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this