東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

AtomDNN : = A New Simulation Tool for Atomistic Modeling with Machine Learning Potential.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	AtomDNN :/
其他題名:	A New Simulation Tool for Atomistic Modeling with Machine Learning Potential.
作者:	Kubena, Colton.
面頁冊數:	1 online resource (56 pages)
附註:	Source: Masters Abstracts International, Volume: 82-12.
Contained By:	Masters Abstracts International82-12.
標題:	Mechanical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28497015click for full text (PQDT)
ISBN:	9798516060076

AtomDNN : = A New Simulation Tool for Atomistic Modeling with Machine Learning Potential.
Kubena, Colton.

AtomDNN :A New Simulation Tool for Atomistic Modeling with Machine Learning Potential. - 1 online resource (56 pages)

Source: Masters Abstracts International, Volume: 82-12.

Thesis (M.S.)--The University of Texas at San Antonio, 2021.

Includes bibliographical references

Traditional atomistic modeling fall into two broad categories: one based on quantum mechanics methods (e.g., Density Functional Theory), and the other based on empirical interatomic potentials. The former one is accurate but computationally demanding, limited to nanometers in length scale. The later one offers much more efficient simulations but less accurate, confined by the parametrization functions used in the potentials. This has always been the hurdle when people intend to get reliable modeling results for large material systems with atomistic details. The machine learning based potential has shown great promise to address the challenges posted. Machine learning potentials are not relying on a physical functional form, but instead learn the physical shape of the energy landscape from the training dataset.We found three key technical challenges in the existing tools, which prevent the practical application of machine learning potential for large material systems:• the computational efficiency of generating atom descriptors is low. • most of the existing tools are not directly integrated to widely used atomistic modeling package LAMMPS (Large-scale Atomic Massively Parallel Simulator).• stress calculations for periodic solid-state systems is not correct in many existing tools.To overcome the challenges, we developed a new tool, called AtomDNN, which has the following features:• use Tensorflow2 platform to train a deep neuron network (DNN) based potential.• compute atom descriptors with LAMMPS, taking advantage of the already built in high efficient parallel algorithm in LAMMPS.• organic integration with LAMMPS without computation overhead.•rigorous evaluation of stress. As an example, AtomDNN has been applied to train a two dimensional material MoTe2.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798516060076Subjects--Topical Terms:

649730
Mechanical engineering.
Subjects--Index Terms:

Machine learningIndex Terms--Genre/Form:

542853
Electronic books.

AtomDNN : = A New Simulation Tool for Atomistic Modeling with Machine Learning Potential.
LDR:03134nmm a2200385K 4500 001 2353355
005 20230306113809.5
006 m o d
007 cr mn ---uuuuu
008 241011s2021 xx obm 000 0 eng d
020 $a 9798516060076
035 $a (MiAaPQ)AAI28497015
035 $a AAI28497015
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Kubena, Colton. $3 3693696
245 1 0 $a AtomDNN : $b A New Simulation Tool for Atomistic Modeling with Machine Learning Potential.
264 0 $c 2021
300 $a 1 online resource (56 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 82-12.
500 $a Advisor: Gao, Wei.
502 $a Thesis (M.S.)--The University of Texas at San Antonio, 2021.
504 $a Includes bibliographical references
520 $a Traditional atomistic modeling fall into two broad categories: one based on quantum mechanics methods (e.g., Density Functional Theory), and the other based on empirical interatomic potentials. The former one is accurate but computationally demanding, limited to nanometers in length scale. The later one offers much more efficient simulations but less accurate, confined by the parametrization functions used in the potentials. This has always been the hurdle when people intend to get reliable modeling results for large material systems with atomistic details. The machine learning based potential has shown great promise to address the challenges posted. Machine learning potentials are not relying on a physical functional form, but instead learn the physical shape of the energy landscape from the training dataset.We found three key technical challenges in the existing tools, which prevent the practical application of machine learning potential for large material systems:• the computational efficiency of generating atom descriptors is low. • most of the existing tools are not directly integrated to widely used atomistic modeling package LAMMPS (Large-scale Atomic Massively Parallel Simulator).• stress calculations for periodic solid-state systems is not correct in many existing tools.To overcome the challenges, we developed a new tool, called AtomDNN, which has the following features:• use Tensorflow2 platform to train a deep neuron network (DNN) based potential.• compute atom descriptors with LAMMPS, taking advantage of the already built in high efficient parallel algorithm in LAMMPS.• organic integration with LAMMPS without computation overhead.•rigorous evaluation of stress. As an example, AtomDNN has been applied to train a two dimensional material MoTe2.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Mechanical engineering. $3 649730
650 4 $a Energy. $3 876794
650 4 $a Artificial intelligence. $3 516317
650 4 $a Atomic physics. $3 3173870
653 $a Machine learning
653 $a Potential energy surfaces
653 $a Atomistic modeling
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0548
690 $a 0800
690 $a 0748
690 $a 0791
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a The University of Texas at San Antonio. $b Mechanical Engineering. $3 2103934
773 0 $t Masters Abstracts International $g 82-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28497015 $z click for full text (PQDT)