1
|
Rautela M, Williams A, Scheinker A. A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators. Sci Rep 2024; 14:18157. [PMID: 39103435 PMCID: PMC11300895 DOI: 10.1038/s41598-024-68944-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2024] [Accepted: 07/30/2024] [Indexed: 08/07/2024] Open
Abstract
Particle accelerators are complex systems that focus, guide, and accelerate intense charged particle beams to high energy. Beam diagnostics present a challenging problem due to limited non-destructive measurements, computationally demanding simulations, and inherent uncertainties in the system. We propose a two-step unsupervised deep learning framework named as Conditional Latent Autoregressive Recurrent Model (CLARM) for learning the spatiotemporal dynamics of charged particles in accelerators. CLARM consists of a Conditional Variational Autoencoder transforming six-dimensional phase space into a lower-dimensional latent distribution and a Long Short-Term Memory network capturing temporal dynamics in an autoregressive manner. The CLARM can generate projections at various accelerator modules by sampling and decoding the latent space representation. The model also forecasts future states (downstream locations) of charged particles from past states (upstream locations). The results demonstrate that the generative and forecasting ability of the proposed approach is promising when tested against a variety of evaluation metrics.
Collapse
Affiliation(s)
- Mahindra Rautela
- Applied Electrodynamics Group (AOT-AE), Los Alamos National Laboratory, Los Alamos, NM, 87547, USA.
| | - Alan Williams
- Applied Electrodynamics Group (AOT-AE), Los Alamos National Laboratory, Los Alamos, NM, 87547, USA
- Department of Mechanical and Aerospace Engineering, University of California, San Diego, CA, 92093, USA
| | - Alexander Scheinker
- Applied Electrodynamics Group (AOT-AE), Los Alamos National Laboratory, Los Alamos, NM, 87547, USA.
| |
Collapse
|
2
|
Nicolle A, Deng S, Ihme M, Kuzhagaliyeva N, Ibrahim EA, Farooq A. Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview. J Chem Inf Model 2024; 64:597-620. [PMID: 38284618 DOI: 10.1021/acs.jcim.3c01633] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/30/2024]
Abstract
Artificial Neural Networks (ANNs) are transforming how we understand chemical mixtures, providing an expressive view of the chemical space and multiscale processes. Their hybridization with physical knowledge can bridge the gap between predictivity and understanding of the underlying processes. This overview explores recent progress in ANNs, particularly their potential in the 'recomposition' of chemical mixtures. Graph-based representations reveal patterns among mixture components, and deep learning models excel in capturing complexity and symmetries when compared to traditional Quantitative Structure-Property Relationship models. Key components, such as Hamiltonian networks and convolution operations, play a central role in representing multiscale mixtures. The integration of ANNs with Chemical Reaction Networks and Physics-Informed Neural Networks for inverse chemical kinetic problems is also examined. The combination of sensors with ANNs shows promise in optical and biomimetic applications. A common ground is identified in the context of statistical physics, where ANN-based methods iteratively adapt their models by blending their initial states with training data. The concept of mixture recomposition unveils a reciprocal inspiration between ANNs and reactive mixtures, highlighting learning behaviors influenced by the training environment.
Collapse
Affiliation(s)
- Andre Nicolle
- Aramco Fuel Research Center, Rueil-Malmaison 92852, France
| | - Sili Deng
- Massachusetts Institute of Technology, Cambridge 02139, Massachusetts, United States
| | - Matthias Ihme
- Stanford University, Stanford 94305, California, United States
| | | | - Emad Al Ibrahim
- King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia
| | - Aamir Farooq
- King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia
| |
Collapse
|
3
|
Lu S, Jayaraman A. Pair-Variational Autoencoders for Linking and Cross-Reconstruction of Characterization Data from Complementary Structural Characterization Techniques. JACS AU 2023; 3:2510-2521. [PMID: 37772182 PMCID: PMC10523369 DOI: 10.1021/jacsau.3c00275] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Revised: 07/11/2023] [Accepted: 07/11/2023] [Indexed: 09/30/2023]
Abstract
In materials research, structural characterization often requires multiple complementary techniques to obtain a holistic morphological view of a synthesized material. Depending on the availability and accessibility of the different characterization techniques (e.g., scattering, microscopy, spectroscopy), each research facility or academic research lab may have access to high-throughput capability in one technique but face limitations (sample preparation, resolution, access time) with other technique(s). Furthermore, one type of structural characterization data may be easier to interpret than another (e.g., microscopy images are easier to interpret than small-angle scattering profiles). Thus, it is useful to have machine learning models that can be trained on paired structural characterization data from multiple techniques (easy and difficult to interpret, fast and slow in data collection or sample preparation) so that the model can generate one set of characterization data from the other. In this paper we demonstrate one such machine learning workflow, Pair-Variational Autoencoders (PairVAE), that works with data from small-angle X-ray scattering (SAXS) that present information about bulk morphology and images from scanning electron microscopy (SEM) that present two-dimensional local structural information on the sample. Using paired SAXS and SEM data of newly observed block copolymer assembled morphologies [open access data from Doerk G. S.; et al. Sci. Adv.2023, 9 ( (2), ), eadd3687], we train our PairVAE. After successful training, we demonstrate that the PairVAE can generate SEM images of the block copolymer morphology when it takes as input that sample's corresponding SAXS 2D pattern and vice versa. This method can be extended to other soft material morphologies as well and serves as a valuable tool for easy interpretation of 2D SAXS patterns as well as an engine for generating ensembles of similar microscopy images to create a database for other downstream calculations of structure-property relationships.
Collapse
Affiliation(s)
- Shizhao Lu
- Department
of Chemical and Biomolecular Engineering, University of Delaware, Newark, Delaware 19716, United States
| | - Arthi Jayaraman
- Department
of Chemical and Biomolecular Engineering, University of Delaware, Newark, Delaware 19716, United States
- Department
of Materials Science and Engineering, University
of Delaware, Newark, Delaware 19716, United
States
| |
Collapse
|
4
|
Wan X, Li Z, Yu W, Wang A, Ke X, Guo H, Su J, Li L, Gui Q, Zhao S, Robertson J, Zhang Z, Guo Y. Machine Learning Paves the Way for High Entropy Compounds Exploration: Challenges, Progress, and Outlook. ADVANCED MATERIALS (DEERFIELD BEACH, FLA.) 2023:e2305192. [PMID: 37688451 DOI: 10.1002/adma.202305192] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Revised: 08/08/2023] [Indexed: 09/10/2023]
Abstract
Machine learning (ML) has emerged as a powerful tool in the research field of high entropy compounds (HECs), which have gained worldwide attention due to their vast compositional space and abundant regulatability. However, the complex structure space of HEC poses challenges to traditional experimental and computational approaches, necessitating the adoption of machine learning. Microscopically, machine learning can model the Hamiltonian of the HEC system, enabling atomic-level property investigations, while macroscopically, it can analyze macroscopic material characteristics such as hardness, melting point, and ductility. Various machine learning algorithms, both traditional methods and deep neural networks, can be employed in HEC research. Comprehensive and accurate data collection, feature engineering, and model training and selection through cross-validation are crucial for establishing excellent ML models. ML also holds promise in analyzing phase structures and stability, constructing potentials in simulations, and facilitating the design of functional materials. Although some domains, such as magnetic and device materials, still require further exploration, machine learning's potential in HEC research is substantial. Consequently, machine learning has become an indispensable tool in understanding and exploiting the capabilities of HEC, serving as the foundation for the new paradigm of Artificial-intelligence-assisted material exploration.
Collapse
Affiliation(s)
- Xuhao Wan
- School of Electrical Engineering and Automation, Wuhan University, Wuhan, Hubei, 430072, China
| | - Zeyuan Li
- School of Power and Mechanical Engineering, Wuhan University, Wuhan, Hubei, 430072, China
| | - Wei Yu
- School of Electrical Engineering and Automation, Wuhan University, Wuhan, Hubei, 430072, China
| | - Anyang Wang
- School of Electrical Engineering and Automation, Wuhan University, Wuhan, Hubei, 430072, China
| | - Xue Ke
- School of Electrical Engineering and Automation, Wuhan University, Wuhan, Hubei, 430072, China
| | - Hailing Guo
- School of Electrical Engineering and Automation, Wuhan University, Wuhan, Hubei, 430072, China
| | - Jinhao Su
- School of Electrical Engineering and Automation, Wuhan University, Wuhan, Hubei, 430072, China
| | - Li Li
- The Institute of Technological Sciences, Wuhan University, Wuhan, Hubei, 430072, China
| | - Qingzhong Gui
- School of Electrical Engineering and Automation, Wuhan University, Wuhan, Hubei, 430072, China
| | - Songpeng Zhao
- The Institute of Technological Sciences, Wuhan University, Wuhan, Hubei, 430072, China
| | - John Robertson
- Department of Engineering, Cambridge University, Cambridge, CB2 1PZ, UK
| | - Zhaofu Zhang
- The Institute of Technological Sciences, Wuhan University, Wuhan, Hubei, 430072, China
| | - Yuzheng Guo
- School of Electrical Engineering and Automation, Wuhan University, Wuhan, Hubei, 430072, China
| |
Collapse
|
5
|
Chen X, Xu S, Shabani S, Zhao Y, Fu M, Millis AJ, Fogler MM, Pasupathy AN, Liu M, Basov DN. Machine Learning for Optical Scanning Probe Nanoscopy. ADVANCED MATERIALS (DEERFIELD BEACH, FLA.) 2023; 35:e2109171. [PMID: 36333118 DOI: 10.1002/adma.202109171] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/12/2021] [Revised: 07/09/2022] [Indexed: 06/16/2023]
Abstract
The ability to perform nanometer-scale optical imaging and spectroscopy is key to deciphering the low-energy effects in quantum materials, as well as vibrational fingerprints in planetary and extraterrestrial particles, catalytic substances, and aqueous biological samples. These tasks can be accomplished by the scattering-type scanning near-field optical microscopy (s-SNOM) technique that has recently spread to many research fields and enabled notable discoveries. Herein, it is shown that the s-SNOM, together with scanning probe research in general, can benefit in many ways from artificial-intelligence (AI) and machine-learning (ML) algorithms. Augmented with AI- and ML-enhanced data acquisition and analysis, scanning probe optical nanoscopy is poised to become more efficient, accurate, and intelligent.
Collapse
Affiliation(s)
- Xinzhong Chen
- Department of Physics and Astronomy, Stony Brook University, Stony Brook, NY, 11794, USA
| | - Suheng Xu
- Department of Physics, Columbia University, New York, NY, 10027, USA
| | - Sara Shabani
- Department of Physics, Columbia University, New York, NY, 10027, USA
| | - Yueqi Zhao
- Department of Physics, University of California at San Diego, La Jolla, CA, 92093-0319, USA
| | - Matthew Fu
- Department of Physics, Columbia University, New York, NY, 10027, USA
| | - Andrew J Millis
- Department of Physics, Columbia University, New York, NY, 10027, USA
| | - Michael M Fogler
- Department of Physics, University of California at San Diego, La Jolla, CA, 92093-0319, USA
| | - Abhay N Pasupathy
- Department of Physics, Columbia University, New York, NY, 10027, USA
| | - Mengkun Liu
- Department of Physics and Astronomy, Stony Brook University, Stony Brook, NY, 11794, USA
- National Synchrotron Light Source II, Brookhaven National Laboratory, Upton, NY, 11973, USA
| | - D N Basov
- Department of Physics, Columbia University, New York, NY, 10027, USA
| |
Collapse
|
6
|
Toward the design of ultrahigh-entropy alloys via mining six million texts. Nat Commun 2023; 14:54. [PMID: 36599862 DOI: 10.1038/s41467-022-35766-5] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2022] [Accepted: 12/28/2022] [Indexed: 01/06/2023] Open
Abstract
It has long been a norm that researchers extract knowledge from literature to design materials. However, the avalanche of publications makes the norm challenging to follow. Text mining (TM) is efficient in extracting information from corpora. Still, it cannot discover materials not present in the corpora, hindering its broader applications in exploring novel materials, such as high-entropy alloys (HEAs). Here we introduce a concept of "context similarity" for selecting chemical elements for HEAs, based on TM models that analyze the abstracts of 6.4 million papers. The method captures the similarity of chemical elements in the context used by scientists. It overcomes the limitations of TM and identifies the Cantor and Senkov HEAs. We demonstrate its screening capability for six- and seven-component lightweight HEAs by finding nearly 500 promising alloys out of 2.6 million candidates. The method thus brings an approach to the development of ultrahigh-entropy alloys and multicomponent materials.
Collapse
|
7
|
For the greatest benefit to humankind. NATURE COMPUTATIONAL SCIENCE 2021; 1:705-706. [PMID: 38217137 DOI: 10.1038/s43588-021-00169-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/15/2024]
|
8
|
van Nieuwenburg E. To V or not to V. NATURE COMPUTATIONAL SCIENCE 2021; 1:644-645. [PMID: 38217200 DOI: 10.1038/s43588-021-00143-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/15/2024]
|