TRIPODS+X:RES: Collaborative Research: Creating Inference from Machine Learned and Science Based Generative Models

TRIPODS X:RES：协作研究：从机器学习和基于科学的生成模型中创建推理

• 批准号: 1839234
• 负责人: Joshua Agar
• 金额: $ 20万
• 依托单位: Lehigh University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1839234&HistoricalAwards=false
• 关键词: TRIPODS+X; RES; Collaborative; Research; Creating

In many scientific disciplines computational simulations are used to enhance our understanding of physical processes of complex systems. In all such simulations simplifications are required to make the problem tractable, limiting the scope of the questions that can be addressed. Generally, computational simulations of large systems with many interacting components, based on the governing physics, requires complex and time consuming computations. This project will apply deep learning neural networks (NN) with geometric transformations based on the physics of the system to accurately approximate traditional physics-based computational simulations in a highly efficient manner. The increased efficiency imparted by the NN model will facilitate the asking of scientific questions which are currently computationally intractable. While the proposed work will focus on using this method to discover new strain-induced polar phases and phase competition, and to understand the large-scale structure in the universe, the concepts developed in this work can be applied to computational simulations in other scientific disciplines.The proposed work will focus on the development of foundational data science methods and the application of these methods to augment computationally-expensive science-based generative models in a way that is principled and efficient, thereby enabling improved data-driven scientific inference. The work will place specific emphasis on the design of neural network models, which through physically-significant domain architectures can approximate N-body and highly-correlated phenomena with minimal loss of information. The work will develop tools to guide the discovery and experimental synthesis of new strain-induced polar phases and phase competition, which exhibit enhanced electromechanical responses; and it will expand our simulation capabilities and understanding of the large-scale structure in the universe. Ultimately, this work will provide both domain specific advances, as well as a framework for other domain areas to augment computationally intensive, highly-correlated, N-body problems with data-driven models, which respect the physics of the problem and lead to increased computational efficiency.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

在许多科学学科中，计算模拟被用来增强我们对复杂系统物理过程的理解。在所有这样的模拟中，简化是需要的，使问题易于处理，限制了可以解决的问题的范围。一般来说，具有许多相互作用的组件的大型系统的计算模拟，基于管理物理，需要复杂和耗时的计算。该项目将应用深度学习神经网络（NN），并基于系统的物理特性进行几何变换，以高效的方式准确地近似传统的基于物理的计算模拟。NN模型所带来的效率提高将有助于提出目前计算上难以解决的科学问题。虽然拟议的工作将集中在使用这种方法来发现新的应变诱导极性相和相竞争，并了解宇宙中的大尺度结构，在这项工作中开发的概念可以应用于其他科学学科的计算模拟。拟议的工作将集中在基础数据科学方法的发展和这些方法的应用，以增强计算昂贵的科学-以一种有原则且高效的方式基于生成模型，从而实现改进的数据驱动的科学推理。这项工作将特别强调神经网络模型的设计，通过物理上重要的域架构，可以近似N体和高度相关的现象，以最小的信息损失。这项工作将开发工具来指导新的应变诱导极性相和相竞争的发现和实验合成，这些相竞争表现出增强的机电响应;它将扩大我们的模拟能力和对宇宙大尺度结构的理解。最终，这项工作将提供特定领域的进展，以及其他领域的框架，以增加计算密集型，高度相关的，N体问题与数据驱动的模型，该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的评估被认为值得支持。影响审查标准。

项目成果

Revealing ferroelectric switching character using deep recurrent neural networks

• DOI: 10.1038/s41467-019-12750-0
• 发表时间: 2019-10-22
• 期刊: NATURE COMMUNICATIONS
• 影响因子: 16.6
• 作者: Agar, Joshua C.;Naul, Brett;Martin, Lane W.
• 通讯作者: Martin, Lane W.

Application of a long short-term memory for deconvoluting conductance contributions at charged ferroelectric domain walls

应用长短期记忆对带电铁电畴壁的电导贡献进行去卷积

• DOI: 10.1038/s41524-020-00426-z
• 发表时间: 2020
• 期刊: npj Computational Materials
• 影响因子: 9.7
• 作者: Holstad, Theodor S.;Ræder, Trygve M.;Evans, Donald M.;Småbråten, Didirk R.;Krohns, Stephan;Schaab, Jakob;Yan, Zewu;Bourret, Edith;van Helvoort, Antonius T.;Grande, Tor
• 通讯作者: Grande, Tor

Symmetry-aware recursive image similarity exploration for materials microscopy

• DOI: 10.1038/s41524-021-00637-y
• 发表时间: 2021-10
• 期刊: npj Computational Materials
• 影响因子: 9.7
• 作者: Tri Nguyen;Yichen Guo;Shuyu Qin;Kylie S. Frew;R. Xu;J. Agar

Why it is Unfortunate that Linear Machine Learning “Works” so well in Electromechanical Switching of Ferroelectric Thin Films

为什么不幸的是，线性机器学习在铁电薄膜的机电开关中表现得如此出色

• DOI: 10.1002/adma.202202814
• 发表时间: 2022
• 期刊: Advanced Materials
• 影响因子: 29.4
• 作者: Qin, Shuyu;Guo, Yichen;Kaliyev, Alibek T.;Agar, Joshua C.
• 通讯作者: Agar, Joshua C.

Deep learning for electron and scanning probe microscopy: From materials design to atomic fabrication

电子和扫描探针显微镜的深度学习：从材料设计到原子制造

• DOI: 10.1557/s43577-022-00413-3
• 发表时间: 2022
• 期刊: MRS Bulletin
• 影响因子: 5
• 作者: Kalinin, Sergei V.;Ziatdinov, Maxim;Spurgeon, Steven R.;Ophus, Colin;Stach, Eric A.;Susi, Toma;Agar, Josh;Randall, John
• 通讯作者: Randall, John