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 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Enhancing Robustness of Neural Netwo...

Tan, Aik Rui,

FindBook

Google Book

Amazon

博客來

Enhancing Robustness of Neural Network Interatomic Potentials Through Sampling Methods and Uncertainty Quantification /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Enhancing Robustness of Neural Network Interatomic Potentials Through Sampling Methods and Uncertainty Quantification // Aik Rui Tan.
作者:	Tan, Aik Rui,
面頁冊數:	1 electronic resource (186 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-08, Section: B.
Contained By:	Dissertations Abstracts International86-08B.
標題:	Behavior. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31850990
ISBN:	9798304942157

Enhancing Robustness of Neural Network Interatomic Potentials Through Sampling Methods and Uncertainty Quantification /
Tan, Aik Rui,

Enhancing Robustness of Neural Network Interatomic Potentials Through Sampling Methods and Uncertainty Quantification /Aik Rui Tan. - 1 electronic resource (186 pages)

Source: Dissertations Abstracts International, Volume: 86-08, Section: B.

Neural network interatomic potentials (NNIPs) are a significant advancement in computational materials science and chemistry for their ability to accurately approximate the potential energy surface (PES) of atomic systems with significantly reduced computational costs compared to quantum mechanical methods. Without relying on predefined interaction parameters, NNIPs offers greater flexibility and adaptability than classical force fields, and can be used for atomistic simulations of complex materials and biological systems. However, NNIPs face inherent limitations due to their dependence on diverse training data and limited extrapolative capabilities. This thesis proposes methodologies to address these challenges through analysis of uncertainty quantification (UQ) techniques, introduction of novel data sampling strategies, and development of structural similarity analysis algorithm to extract physical insights from diverse data sets. First, we examine the efficacy of UQ for single deterministic neural networks, demonstrating that a Gaussian mixture model-based approach can significantly reduce computational demands without sacrificing prediction accuracy and UQ reliability, although it does not significantly outperform the baseline ensemble method. Utilizing insights gained from the UQ analysis, we introduce a PES sampling technique based on adversarial attacks on predicted uncertainties, which samples atomic configurations with maximized uncertainties and mitigates the typical correlation issues associated with molecular dynamics sampling. Additionally, recognizing the limitations of the proposed adversarial sampling method, we introduce an enhanced sampling method using predicted uncertainty as collective variables (CVs) to enable more thorough exploration of under-sampled regions and to reduce confinement within local minima/maxima of energy and uncertainty landscapes. Finally, we propose a graph-based method to analyze structural variances in amorphous bulk systems that could be difficult to capture using conventional CVs, and yet can provide physical insights to explain the macroscopic properties of the materials. Overall, the methodologies proposed in this thesis improve the robustness and applicability of NNIPs in atomistic simulations and provide a groundwork for further advancements in this space.

English

ISBN: 9798304942157Subjects--Topical Terms:

532476
Behavior.
Subjects--Index Terms:

Neural network interatomic potentials

Enhancing Robustness of Neural Network Interatomic Potentials Through Sampling Methods and Uncertainty Quantification /
LDR:03806nmm a22004213i 4500 001 2433812
005 20250905091019.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798304942157
035 $a (MiAaPQD)AAI31850990
035 $a (MiAaPQD)MIT17211155357
035 $a AAI31850990
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Tan, Aik Rui, $e author. $3 3823571
245 1 0 $a Enhancing Robustness of Neural Network Interatomic Potentials Through Sampling Methods and Uncertainty Quantification / $c Aik Rui Tan.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (186 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: Dissertations Abstracts International, Volume: 86-08, Section: B.
500 $a Advisors: Gomez-Bombarelli, Rafael.
502 $b Ph.D. $c Massachusetts Institute of Technology $d 2024.
520 $a Neural network interatomic potentials (NNIPs) are a significant advancement in computational materials science and chemistry for their ability to accurately approximate the potential energy surface (PES) of atomic systems with significantly reduced computational costs compared to quantum mechanical methods. Without relying on predefined interaction parameters, NNIPs offers greater flexibility and adaptability than classical force fields, and can be used for atomistic simulations of complex materials and biological systems. However, NNIPs face inherent limitations due to their dependence on diverse training data and limited extrapolative capabilities. This thesis proposes methodologies to address these challenges through analysis of uncertainty quantification (UQ) techniques, introduction of novel data sampling strategies, and development of structural similarity analysis algorithm to extract physical insights from diverse data sets. First, we examine the efficacy of UQ for single deterministic neural networks, demonstrating that a Gaussian mixture model-based approach can significantly reduce computational demands without sacrificing prediction accuracy and UQ reliability, although it does not significantly outperform the baseline ensemble method. Utilizing insights gained from the UQ analysis, we introduce a PES sampling technique based on adversarial attacks on predicted uncertainties, which samples atomic configurations with maximized uncertainties and mitigates the typical correlation issues associated with molecular dynamics sampling. Additionally, recognizing the limitations of the proposed adversarial sampling method, we introduce an enhanced sampling method using predicted uncertainty as collective variables (CVs) to enable more thorough exploration of under-sampled regions and to reduce confinement within local minima/maxima of energy and uncertainty landscapes. Finally, we propose a graph-based method to analyze structural variances in amorphous bulk systems that could be difficult to capture using conventional CVs, and yet can provide physical insights to explain the macroscopic properties of the materials. Overall, the methodologies proposed in this thesis improve the robustness and applicability of NNIPs in atomistic simulations and provide a groundwork for further advancements in this space.
546 $a English
590 $a School code: 0753
650 4 $a Behavior. $3 532476
650 4 $a Neural networks. $3 677449
650 4 $a Flexibility. $3 3560705
650 4 $a Phase transitions. $3 3560387
650 4 $a Energy. $3 876794
650 4 $a Ammonia. $3 2148979
650 4 $a Materials science. $3 543314
650 4 $a Engineering. $3 586835
653 $a Neural network interatomic potentials
653 $a Potential energy surface
653 $a Uncertainty quantification
690 $a 0791
690 $a 0794
690 $a 0537
710 2 $a Massachusetts Institute of Technology. $b Department of Materials Science and Engineering. $e degree granting institution. $3 3823568
720 1 $a Gomez-Bombarelli, Rafael $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-08B.
790 $a 0753
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31850990