InvDesFlow-AL: active learning-based workflow for inverse design of functional materials

Abstract

Developing inverse design methods for functional materials with specific properties is critical to advancing fields like renewable energy, catalysis, energy storage, and carbon capture. Generative models based on diffusion principles can directly produce new materials that meet performance constraints, thereby significantly accelerating the material design process. However, existing methods for generating and predicting crystal structures often remain limited by low success rates. In this work, we propose a novel inverse material design generative framework called InvDesFlow-AL, which is based on active learning strategies. This framework can iteratively optimize the material generation process to gradually guide it towards desired performance characteristics. In terms of crystal structure prediction, the InvDesFlow-AL model achieves an RMSE of 0.0423 Å, representing an 32.96% improvement in performance compared to exsisting generative models. Additionally, InvDesFlow-AL has been successfully validated in the design of low-formation-energy and low-Ehull materials. It can systematically generate materials with progressively lower formation energies while continuously expanding the exploration across diverse chemical spaces. These results fully demonstrate the effectiveness of the proposed active learning-driven generative model in accelerating material discovery and inverse design. To further prove the effectiveness of this method, we took the search for BCS superconductors under ambient pressure as an example explored by InvDesFlow-AL. As a result, we successfully identified Li\(_2\)AuH\(_6\) as a conventional BCS superconductor with an ultra-high transition temperature of 140 K. This discovery provides strong empirical support for the application of inverse design in materials science.

29 pages, 11 figures

References in corpus (24)

• Optimized norm-conserving Vanderbilt pseudopotentials
• Conventional superconductivity at 203 K at high pressures
• Wannier90 as a community code: new features and applications
• Superconductivity at 250 K in lanthanum hydride under high pressures
• Evidence for superconductivity above 260 K in lanthanum superhydride at megabar pressures
• EPW: Electron-phonon coupling, transport and superconducting properties using maximally localized Wannier functions
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Superconductivity near 80 Kelvin in single crystals of La3Ni2O7 under pressure
• Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning
• Inverse design of 3d molecular structures with conditional generative neural networks
• Ambient-pressure superconductivity onset above 40 K in bilayer nickelate ultrathin films
• Feasible route to high-temperature ambient-pressure hydride superconductivity
• DPA-2: a large atomic model as a multi-task learner
• Prediction of Ambient Pressure Conventional Superconductivity above 80K in Thermodynamically Stable Hydride Compounds
• Bayesian optimization package: PHYSBO
• Designing High-Tc Superconductors with BCS-inspired Screening, Density Functional Theory and Deep-learning
• AI-driven inverse design of materials: Past, present and future
• Deep-learning electronic-structure calculation of magnetic superstructures
• Machine Learning Enabled Prediction of Cathode Materials for Zn ion Batteries
• Con-CDVAE: A method for the conditional generation of crystal structures
• Prediction of ambient pressure superconductivity in cubic ternary hydrides with MH${}_6$ octahedra
• The Maximum $T_c$ of Conventional Superconductors at Ambient Pressure
• InvDesFlow: An AI-driven materials inverse design workflow to explore possible high-temperature superconductors
• High-temperature superconductivity in Li${}_2$AuH${}_6$ mediated by strong electron-phonon coupling under ambient pressure