Benchmarking Inverse Optimization Algorithms for Materials Design

Abstract

Machine learning-based inverse materials discovery has attracted enormous attention recently due to its flexibility in dealing with black box models. Yet, many metaheuristic algorithms are not as widely applied to materials discovery applications as machine learning methods. There are ongoing challenges in applying different optimization algorithms to discover crystals with single- or multi-elemental compositions and how these algorithms differ in mining the ideal materials. We comprehensively compare 11 different optimization algorithms for the design of single- and multi-elemental crystals with targeted properties. By maximizing the bulk modulus and minimizing the Fermi energy through perturbing the parameterized elemental composition representations, we estimated the unique counts of elemental compositions, mean density scan of the objectives space, mean objectives and frequency distributed over the materials' representations and objectives. We found that nature-inspired algorithms contain more uncertainties in the defined elemental composition design tasks, which correspond to their dependency on multiple hyperparameters. Runge Kutta optimization (RUN) exhibits higher mean objectives whereas Bayesian optimization (BO) displayed low mean objectives compared with other methods. Combined with materials count and density scan, we propose that BO strives to approximate a more accurate surrogate of the design space by sampling more elemental compositions and hence have lower mean objectives, yet RUN will repeatedly sample the targeted elemental compositions with higher objective values. Our work shed light on the automated digital design of crystals with single- and multi-elemental compositions and is expected to elicit future studies on materials optimization such as composite and alloy design based on specific desired properties.

arXiv comment16 pages, 6 figures. 15 pages for Supplementary Information

References in corpus (12)

• Continuous control with deep reinforcement learning
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• MolGAN: An implicit generative model for small molecular graphs
• Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm
• MODNet -- accurate and interpretable property predictions for limited materials datasets by feature selection and joint-learning
• Deep Reinforcement Learning Optimizes Graphene Nanopores for Efficient Desalination
• Materials Representation and Transfer Learning for Multi-Property Prediction
• Interplay between phonons and anisotropic elasticity drives negative thermal expansion in PbTiO${}_3$
• Rapid Design of Top-Performing Metal-Organic Frameworks with Qualitative Representations of Building Blocks
• Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design
• Computational design of antimicrobial active surfaces via automated Bayesian optimization
• Multiscale mechanics of thermal gradient coupled graphene fracture: A molecular dynamics study

Cited by in corpus (1)

• Stress Predictions in Polycrystal Plasticity using Graph Neural Networks with Subgraph Training