TY - JOUR
T1 - Implicit neural representations for experimental steering of advanced experiments
AU - Chen, Zhantao
AU - Petsch, Alexander N.
AU - Ji, Zhurun
AU - Chitturi, Sathya R.
AU - Peng, Cheng
AU - Jia, Chunjing
AU - Kolesnikov, Alexander I.
AU - Thayer, Jana B.
AU - Turner, Joshua J.
N1 - Publisher Copyright:
© 2024 The Author(s)
PY - 2025/1/15
Y1 - 2025/1/15
N2 - Scattering measurements using electrons, neutrons, or photons are essential for obtaining microscopic insights into materials. However, limited facility availability and high-dimensional scattering data necessitate more efficient experimental steering techniques. Here, we report a machine learning method that guides scattering data collection and facilitates real-time estimation of model parameters, given a reliable forward model to simulate experimental signals. We employ implicit neural representations as efficient surrogates that link model parameters with simulated spectroscopies. This enables a Bayesian optimal experimental design framework to estimate the probability distributions of parameters from high-dimensional scattering data. We demonstrate the proposed method using inelastic neutron scattering with simulated and real experimental data, highlighting the method's ability to provide real-time parameter estimation with quantified uncertainties and to deliver informed experimental guidance that reduces experimental time while maximizing scientific output. This approach paves the way for accelerated discoveries in condensed matter through scattering measurements.
AB - Scattering measurements using electrons, neutrons, or photons are essential for obtaining microscopic insights into materials. However, limited facility availability and high-dimensional scattering data necessitate more efficient experimental steering techniques. Here, we report a machine learning method that guides scattering data collection and facilitates real-time estimation of model parameters, given a reliable forward model to simulate experimental signals. We employ implicit neural representations as efficient surrogates that link model parameters with simulated spectroscopies. This enables a Bayesian optimal experimental design framework to estimate the probability distributions of parameters from high-dimensional scattering data. We demonstrate the proposed method using inelastic neutron scattering with simulated and real experimental data, highlighting the method's ability to provide real-time parameter estimation with quantified uncertainties and to deliver informed experimental guidance that reduces experimental time while maximizing scientific output. This approach paves the way for accelerated discoveries in condensed matter through scattering measurements.
KW - experimental design
KW - implicit neural representation
KW - machine learning
KW - parameter estimation
KW - scattering experiments
UR - http://www.scopus.com/inward/record.url?scp=85214329983&partnerID=8YFLogxK
U2 - 10.1016/j.xcrp.2024.102333
DO - 10.1016/j.xcrp.2024.102333
M3 - Article
AN - SCOPUS:85214329983
SN - 2666-3864
VL - 6
JO - Cell Reports Physical Science
JF - Cell Reports Physical Science
IS - 1
M1 - 102333
ER -