Hypothesis Learning in Automated Experiment: Application to Combinatorial Materials Libraries

Abstract

Machine learning is rapidly becoming an integral part of experimental physical discovery via automated and high-throughput synthesis, and active experiments in scattering and electron/probe microscopy. This, in turn, necessitates the development of active learning methods capable of exploring relevant parameter spaces with the smallest number of steps. Here we introduce an active learning approach based on co-navigation of the hypothesis and experimental spaces. This is realized by combining the structured Gaussian Processes containing probabilistic models of the possible system's behaviors (hypotheses) with reinforcement learning policy refinement (discovery). This approach closely resembles classical human-driven physical discovery, when several alternative hypotheses realized via models with adjustable parameters are tested during an experiment. We demonstrate this approach for exploring concentration-induced phase transitions in combinatorial libraries of Sm-doped BiFeO3 using Piezoresponse Force Microscopy, but it is straightforward to extend it to higher-dimensional parameter spaces and more complex physical problems once the experimental workflow and hypothesis-generation are available.

arXiv commentFixed typo in Eq. 1. Expanded the introduction part. The code reproducing Algorithm 1 is available at https://github.com/ziatdinovmax/hypoAL

References in corpus (20)

• Deep Learning in Neural Networks: An Overview
• Colossal Magnetoresistant Materials: The Key Role of Phase Separation
• MCMC using Hamiltonian dynamics
• Complexity in Strongly Correlated Electronic Systems
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning
• Discovering Symbolic Models from Deep Learning with Inductive Biases
• Nanoelectromechanics of Piezoresponse Force Microscopy
• Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro
• Predicting morphotropic phase boundary locations and transition temperatures in Pb- and Bi-based perovskite solid solutions from crystal chemical data and first-principles calculations
• PySINDy: A comprehensive Python package for robust sparse system identification
• Materials Contrast in Piezoresponse Force Microscopy
• Domain Nucleation and Hysteresis Loop Shape in Piezoresponse Force Spectroscopy
• An improved continuous compositional-spread technique based on pulsed-laser deposition and applicable to large substrate areas
• Data Mining for better material synthesis: the case of pulsed laser deposition of complex oxides
• Domain Dynamics in Piezoresponse Force Microscopy: Quantitative Deconvolution and Hysteresis Loop Fine Structure
• Exploring physics of ferroelectric domain walls via Bayesian analysis of atomically resolved STEM data
• Bayesian inference in band excitation Scanning Probe Microscopy for optimal dynamic model selection in imaging
• Melting of Spatially Modulated Phases in La-doped BiFeO3 at Surfaces and Surface-Domain Wall Junctions
• Logic Guided Genetic Algorithms

Cited by in corpus (8)

• Bayesian optimization with experimental failure for high-throughput materials growth
• Autonomous scanning probe microscopy with hypothesis learning: Exploring the physics of domain switching in ferroelectric materials
• GFlowNets for AI-Driven Scientific Discovery
• Post-Experiment Forensics and Human-in-the-Loop Interventions in Explainable Autonomous Scanning Probe Microscopy
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space
• Co-orchestration of Multiple Instruments to Uncover Structure-Property Relationships in Combinatorial Libraries
• Integration of Scanning Probe Microscope with High-Performance Computing: fixed-policy and reward-driven workflows implementation