A SCALABLE TRANSFORMER MODEL FOR REAL-TIME DECISION MAKING IN NEUTRON SCATTERING EXPERIMENTS
-
Published:2023
Issue:1
Volume:4
Page:95-107
-
ISSN:2689-3967
-
Container-title:Journal of Machine Learning for Modeling and Computing
-
language:en
-
Short-container-title:J Mach Learn Model Comput
Author:
Yin Junqi,Liu Siyan,Reshniak Viktor,Wang Xiaoping,Zhang Guannan
Abstract
The U.S. Department of Energy's (DOE's) neutron research facilities at Oak Ridge National Laboratory (ORNL), including the High Flux Isotope Reactor (HFIR) and the Spallation Neutron Source (SNS), are a state-of-the-art neutron scattering facility that allows researchers to study the structure and dynamics of materials at the atomic scale. At the SNS, neutrons are measured using the time-of-flight (TOF) technique as they move through a neutron beamline to interact with a sample. Large volumes of neutron scattering data are collected and recorded in neutron event mode. Optimal productivity of the TOF instrument is limited due to the lack of real-time data analysis tools. The large amount of data generated by the experiments can be challenging to process and analyze in real time, particularly for experiments that require rapid feedback and adjustment of experimental parameters. The regular computer/workstation cannot keep up with the experiment speed to provide real-time feedback to adjust experimental parameters, so connecting the supercomputers available to the neutron facility is necessary to achieve real-time data analysis and experiment steering. To address this challenge, we exploit the Frontier supercomputer at Oak Ridge Leadership Computing Facility (OLCF) to train a scalable temporal fusion transformer model for real-time decision making of TOF neutron scattering experimentation. In this paper, we present the results using Frontier to provide the processing power needed to rapidly process and analyze large volumes of single-crystal diffraction data collected at TOPAZ, a neutron time-of-flight Laue single-crystal diffractometer at the SNS.
Reference10 articles.
1. Coates, L., Cao, H.B., Chakoumakos, B.C., Frontzek, M.D., Hoffmann, C., Kovalevsky, A.Y., Liu, Y., Meilleur, F., dos Santos, A.M., Myles, D.A.A., Wang, X.P., and Ye, F., A Suite-Level Review of the Neutron Single-Crystal Diffraction Instruments at Oak Ridge National Laboratory, Rev. Sci. Instrum., vol. 89, no. 9, p. 092802, 2018. 2. Fancher, C.M., Hoffmann, C., Sedov, V., Parizzi, A., Zhou, W., Schultz, A.J., Wang, X.P., and Long, D., Time Filtering of Event Based Neutron Scattering Data: A Pathway to Study the Dynamic Structural Responses of Materials, Rev. Sci. Instrum., vol. 89, no. 9, p. 092803, 2018. 3. Ke, T.W., Brewster, A.S., Yu, S.X., Ushizima, D., Yang, C., and Sauter, N.K., A Convolutional Neural Network-Based Screening Tool for X-Ray Serial Crystallography, J. Synchrotron Radiat., vol. 25, no. 3, pp. 655-670, 2018. 4. Lim, B., Ar?k, S.O., Loeff, N., and Pfister, T., Temporal Fusion Transformers for Interpretable Multihorizon Time Series Forecasting, Int. J. Forecast., vol. 37, no. 4, pp. 1748-1764, 2021. 5. Michels-Clark, T.M., Savici, A.T., Lynch, V.E., Wang, X., and Hoffmann, C.M., Expanding Lorentz and Spectrum Corrections to Large Volumes of Reciprocal Space for Single-Crystal Time-of-Flight Neutron Diffraction, J. Appl. Crystallogr., vol. 49, no. 2, pp. 497-506, 2016.
|
|