Autonomous decision making for solid-state synthesis of inorganic materials

Abstract

To aid in the automation of inorganic materials synthesis, we introduce an algorithm (ARROWS3) that guides the selection of precursors used in solid-state reactions. Given a target phase, ARROWS3 iteratively proposes experiments and learns from their outcomes to identify an optimal set of precursors that leads to maximal yield of that target. Initial experiments are selected based on thermochemical data collected from first principles calculations, which enable the identification of precursors exhibiting large thermodynamic force to form the desired target. Should the initial experiments fail, their associated reaction paths are determined by sampling a range of synthesis temperatures and identifying their products. ARROWS3 then uses this information to pinpoint which intermediate reactions consume most of the available free energy associated with the starting materials. In subsequent experimental iterations, precursors are selected to avoid such unfavorable reactions and therefore maintain a strong driving force to form the target. We validate this approach on three experimental datasets containing results from more than 200 distinct synthesis procedures. When compared to several black-box optimization algorithms, ARROWS3 identifies the most effective set of precursors for each target while requiring substantially fewer experimental iterations. These findings highlight the importance of using domain knowledge in the design of optimization algorithms for materials synthesis, which are critical for the development of fully autonomous research platforms.

References in corpus (13)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Learning to Plan Chemical Syntheses
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Theory of Chemical Kinetics and Charge Transfer based on Nonequilibrium Thermodynamics
• On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning
• Physical descriptor for the Gibbs energy of inorganic crystalline solids and temperature-dependent materials chemistry
• A probabilistic deep learning approach to automate the interpretation of multi-phase diffraction spectra
• Observing and modeling the sequential pairwise reactions that drive solid-state ceramic synthesis
• Machine-learning rationalization and prediction of solid-state synthesis conditions
• Precursor recommendation for inorganic synthesis by machine learning materials similarity from scientific literature
• Computational and experimental investigation of unreported transition metal selenides and sulphides
• Selective formation of metastable polymorphs in solid-state synthesis

Cited by in corpus (2)

• AlabOS: A Python-based Reconfigurable Workflow Management Framework for Autonomous Laboratories
• Probabilistic Phase Labeling and Lattice Refinement for Autonomous Material Research