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

Machine Learning Interatomic Potenti...

Fazel, Kamron.

FindBook

Google Book

Amazon

博客來

Machine Learning Interatomic Potentials for First-Principles Electrochemistry.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Machine Learning Interatomic Potentials for First-Principles Electrochemistry./
作者:	Fazel, Kamron.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2024,
面頁冊數:	67 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
標題:	Materials science. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31140183
ISBN:	9798383060131

Machine Learning Interatomic Potentials for First-Principles Electrochemistry.
Fazel, Kamron.

Machine Learning Interatomic Potentials for First-Principles Electrochemistry. - Ann Arbor : ProQuest Dissertations & Theses, 2024 - 67 p.

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

Thesis (Ph.D.)--Rensselaer Polytechnic Institute, 2024.

Computational predictions of material properties are growing in reliance on machine learning tools to unlocking the calculations at the timescales and sizes to compute dynamic properties (e.g., melting temperature, solvation, diffusion, reaction rates).Machine learning methods have mostly been trained and used on the homogeneous materials with a high degree of accuracy, but have not been readily applied to mixed systems of solutes, solvents, and interfaces. Our research explores use of machine learned interatomic potentials (MLP) on complex systems (molten salts, water, and polymer catalysts) to discover first-principles based properties.First, we study homogeneous molten salts and apply techniques in MLPs to compute phase diagrams. We apply techniques to predict uncertainties of data and MLPs as they project through these calculations to find an optimal density functional theory exchange correlation functional.Then, we develop and characterize MLP performance in inhomogeneous water and molten salt critical to developing solvation models. Inhomogeneous and heterogeneous materials push MLPs to their limit and beyond, requiring new methods for developing custom training data and quality validation. We show how standard homogeneous potentials fail to capture these environments and the need to design custom training data to teach the potentials properly. We also develop an alternate physically-informed delta MLP that can similarly capture the inhomogeneous environment of surface tension.Lastly, we study a heterogeneous polymer catalyst system (in fuel cells) to characterize structure and dynamic properties. With the most complex of interfaces, we explore advanced machine learning techniques and new MLPs. These include on-the-fly learning, delta learning, and state-of-the-art message passing neural networks with equivariance to build a stable and accurate MLP. This enabled us to determine proton diffusion differences between bulk and Pt surface, surface reactions, and early polymer structuring.

ISBN: 9798383060131Subjects--Topical Terms:

543314
Materials science.
Subjects--Index Terms:

Dynamic properties

Machine Learning Interatomic Potentials for First-Principles Electrochemistry.
LDR:03282nmm a2200409 4500 001 2402200
005 20241028051454.5
006 m o d
007 cr#unu||||||||
008 251215s2024 ||||||||||||||||| ||eng d
020 $a 9798383060131
035 $a (MiAaPQ)AAI31140183
035 $a AAI31140183
035 $a 2402200
040 $a MiAaPQ $c MiAaPQ
100 1 $a Fazel, Kamron. $0 (orcid)0009-0001-2663-5376 $3 3772424
245 1 0 $a Machine Learning Interatomic Potentials for First-Principles Electrochemistry.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 67 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
500 $a Advisor: Tajer, Ali;Sundararaman, Ravishankar.
502 $a Thesis (Ph.D.)--Rensselaer Polytechnic Institute, 2024.
520 $a Computational predictions of material properties are growing in reliance on machine learning tools to unlocking the calculations at the timescales and sizes to compute dynamic properties (e.g., melting temperature, solvation, diffusion, reaction rates).Machine learning methods have mostly been trained and used on the homogeneous materials with a high degree of accuracy, but have not been readily applied to mixed systems of solutes, solvents, and interfaces. Our research explores use of machine learned interatomic potentials (MLP) on complex systems (molten salts, water, and polymer catalysts) to discover first-principles based properties.First, we study homogeneous molten salts and apply techniques in MLPs to compute phase diagrams. We apply techniques to predict uncertainties of data and MLPs as they project through these calculations to find an optimal density functional theory exchange correlation functional.Then, we develop and characterize MLP performance in inhomogeneous water and molten salt critical to developing solvation models. Inhomogeneous and heterogeneous materials push MLPs to their limit and beyond, requiring new methods for developing custom training data and quality validation. We show how standard homogeneous potentials fail to capture these environments and the need to design custom training data to teach the potentials properly. We also develop an alternate physically-informed delta MLP that can similarly capture the inhomogeneous environment of surface tension.Lastly, we study a heterogeneous polymer catalyst system (in fuel cells) to characterize structure and dynamic properties. With the most complex of interfaces, we explore advanced machine learning techniques and new MLPs. These include on-the-fly learning, delta learning, and state-of-the-art message passing neural networks with equivariance to build a stable and accurate MLP. This enabled us to determine proton diffusion differences between bulk and Pt surface, surface reactions, and early polymer structuring.
590 $a School code: 0185.
650 4 $a Materials science. $3 543314
650 4 $a Physical chemistry. $3 1981412
650 4 $a Polymer chemistry. $3 3173488
650 4 $a Computational chemistry. $3 3350019
653 $a Dynamic properties
653 $a Electrochemistry
653 $a Machine learned potentials
653 $a Neural network potentials
653 $a Computational predictions
690 $a 0794
690 $a 0494
690 $a 0219
690 $a 0495
710 2 $a Rensselaer Polytechnic Institute. $b Electrical Engineering. $3 2098709
773 0 $t Dissertations Abstracts International $g 85-12B.
790 $a 0185
791 $a Ph.D.
792 $a 2024
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31140183