Multi-objective Bayesian optimization of ferroelectric materials with interfacial control for memory and energy storage applications

Abstract

Optimization of materials performance for specific applications often requires balancing multiple aspects of materials functionality. Even for the cases where generative physical model of material behavior is known and reliable, this often requires search over multidimensional parameter space to identify low-dimensional manifold corresponding to required Pareto front. Here we introduce the multi-objective Bayesian Optimization (MOBO) workflow for the ferroelectric/anti-ferroelectric performance optimization for memory and energy storage applications based on the numerical solution of the Ginzburg-Landau equation with electrochemical or semiconducting boundary conditions. MOBO is a low computational cost optimization tool for expensive multi-objective functions, where we update posterior surrogate Gaussian process models from prior evaluations, and then select future evaluations from maximizing an acquisition function. Using the parameters for a prototype bulk antiferroelectric (PbZrO3), we first develop a physics-driven decision tree of target functions from the loop structures. We further develop a physics-driven MOBO architecture to explore multidimensional parameter space and build Pareto-frontiers by maximizing two target functions jointly: energy storage and loss. This approach allows for rapid initial materials and device parameter selection for a given application and can be further expanded towards the active experiment setting. The associated notebooks provide both the tutorial on MOBO and allow to reproduce the reported analyses and apply them to other systems (https://github.com/arpanbiswas52/MOBO_AFI_Supplements).

arXiv comment40 pages, including 12 figures in the main text and Appendixes with 4 figures

References in corpus (20)

• pymoo: Multi-objective Optimization in Python
• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• Tunneling electroresistance effect in ferroelectric tunnel junctions at the nanoscale
• Pathways Towards Ferroelectricity in Hafnia
• Max-value Entropy Search for Efficient Bayesian Optimization
• Multiple soft-mode vibrations of lead zirconate
• Predictive Entropy Search for Multi-objective Bayesian Optimization
• Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization
• Equilibrium and Stability of Polarization in Ultrathin Ferroelectric Films with Ionic Surface Compensation
• Causes of ferroelectricity in HfO${}_2$-based thin films: An $\text{ab initio}$ perspective
• Ferroionic states in ferroelectric thin films
• Autonomous Efficient Experiment Design for Materials Discovery with Bayesian Model Averaging
• Trilinear coupling driven ferroelectricity in HfO${}_2$
• Finite size and intrinsic field effect on the polar-active properties of the ferroelectric-semiconductor heterostructures
• Effect of surface ionic screening on polarization reversal scenario in ferroelectric thin films: crossover from ferroionic to antiferroionic states
• Phase-field modeling of chemical control of polarization stability and switching dynamics in ferroelectric thin film
• Piezoresponse of ferroelectric films in ferroionic states: time and voltage dynamics
• Guided search for desired functional responses via Bayesian optimization of generative model: Hysteresis loop shape engineering in ferroelectrics
• Effects of anisotropic elasticity in the problem of domain formation and stability of monodomain state in ferroelectric films
• Bayesian Optimization in Materials Science: A Survey