AI-driven inverse design of materials: Past, present and future

Abstract

The discovery of advanced materials is the cornerstone of human technological development and progress. The structures of materials and their corresponding properties are essentially the result of a complex interplay of multiple degrees of freedom such as lattice, charge, spin, symmetry, and topology. This poses significant challenges for the inverse design methods of materials. Humans have long explored new materials through a large number of experiments and proposed corresponding theoretical systems to predict new material properties and structures. With the improvement of computational power, researchers have gradually developed various electronic structure calculation methods, such as the density functional theory and high-throughput computational methods. Recently, the rapid development of artificial intelligence technology in the field of computer science has enabled the effective characterization of the implicit association between material properties and structures, thus opening up an efficient paradigm for the inverse design of functional materials. A significant progress has been made in inverse design of materials based on generative and discriminative models, attracting widespread attention from researchers. Considering this rapid technological progress, in this survey, we look back on the latest advancements in AI-driven inverse design of materials by introducing the background, key findings, and mainstream technological development routes. In addition, we summarize the remaining issues for future directions. This survey provides the latest overview of AI-driven inverse design of materials, which can serve as a useful resource for researchers.

44 pages, 6 figures, 2 tables

References in corpus (97)

• Electric Field Effect in Atomically Thin Carbon Films
• Topological Insulators
• Graphene: Status and Prospects
• A Comprehensive Survey on Graph Neural Networks
• 2D materials and van der Waals heterostructures
• Quantum sensing
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Conventional superconductivity at 203 K at high pressures
• Antiferromagnetic spintronics
• SchNet - a deep learning architecture for molecules and materials
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds
• New Tolerance Factor to Predict the Stability of Perovskite Oxides and Halides
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Topological Insulator Materials
• Topological quantum chemistry
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• The Computational 2D Materials Database: High-Throughput Modeling and Discovery of Atomically Thin Crystals
• The (High Quality) Topological Materials In The World
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Altermagnetism: spin-momentum locked phase protected by non-relativistic symmetries
• Catalogue of Topological Electronic Materials
• Crystal Hall effect in Collinear Antiferromagnets
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Symmetry-based Indicators of Band Topology in the 230 Space Groups
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Superconductivity near 80 Kelvin in single crystals of La3Ni2O7 under pressure
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• The space group classification of topological band insulators
• Topological classification of crystalline insulators through band structure combinatorics
• Observation of the Anomalous Hall Effect in a Collinear Antiferromagnet
• Building logical qubits in a superconducting quantum computing system
• Recent Progress of the Computational 2D Materials Database (C2DB)
• Giant momentum-dependent spin splitting in centrosymmetric low Z antiferromagnets
• Efficient Electrical Spin-Splitter Based on Non-Relativistic Collinear Antiferromagnetism
• The Joint Automated Repository for Various Integrated Simulations (JARVIS) for data-driven materials design
• Momentum-Dependent Spin Splitting by Collinear Antiferromagnetic Ordering
• Quantum transduction of optical photons from a superconducting qubit
• Multifunctional Antiferromagnetic Materials with Giant Piezomagnetism and Noncollinear Spin Current
• Anion height dependence of Tc for the Fe-based superconductor
• Machine learning modeling of superconducting critical temperature
• Observation of spin splitting torque in a collinear antiferromagnet RuO2
• Giant and tunneling magnetoresistance effects from anisotropic and valley-dependent spin-momentum interactions in antiferromagnets
• Spontaneous anomalous Hall effect arising from an unconventional compensated magnetic phase in a semiconductor
• Materials Cloud, a platform for open computational science
• Observation of spin-splitter torque in collinear antiferromagnetic RuO${}_2$
• Prediction of unconventional magnetism in doped FeSb2
• Crystal Thermal Transport in Altermagnetic RuO2
• Beyond scaling relations for the description of catalytic materials
• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• Single-Atom Alloy Catalysts Designed by First-Principles Calculations and Artificial Intelligence
• Topology optimization of 2D structures with nonlinearities using deep learning
• Topological Superconductivity in Two-Dimensional Altermagnetic Metals
• Database of 2D hybrid perovskite materials: open-access collection of crystal structures, band gaps and atomic partial charges predicted by machine learning
• Orbital Graph Convolutional Neural Network for Material Property Prediction
• Machine learning-guided synthesis of advanced inorganic materials
• Influence of apical oxygen on the extent of in-plane exchange interaction in cuprate superconductors
• DPA-2: a large atomic model as a multi-task learner
• General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
• Quantum Anomalous Hall Effect in Antiferromagnetism
• Predicting the Activity and Selectivity of Bimetallic Metal Catalysts for Ethanol Reforming using Machine Learning
• Majorana corner modes and tunable patterns in an altermagnet heterostructure
• Materials science in the era of large language models: a perspective
• Electrically Controllable Crystal Chirality Magneto-Optical Effects in Collinear Antiferromagnets
• A generative artificial intelligence framework based on a molecular diffusion model for the design of metal-organic frameworks for carbon capture
• Topological correspondence between magnetic space group representations
• Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids
• Creation and Manipulation of Higher-Order Topological States by Altermagnets
• Designing High-Tc Superconductors with BCS-inspired Screening, Density Functional Theory and Deep-learning
• Deep learning generative model for crystal structure prediction
• Machine learning driven synthesis of few-layered WTe2
• Machine learning for materials discovery: two-dimensional topological insulators
• Deep-learning electronic-structure calculation of magnetic superstructures
• Deep-learning density functional perturbation theory
• Inverse Design of Next-generation Superconductors Using Data-driven Deep Generative Models
• Efficient Computational Design of 2D van der Waals Heterostructures: Band-Alignment, Lattice-Mismatch, Web-app Generation and Machine-learning
• Record-high-Tc elemental superconductivity in scandium
• Generative Language Model for Catalyst Discovery
• Universal materials model of deep-learning density functional theory Hamiltonian
• Autonomous synthesis of thin film materials with pulsed laser deposition enabled by in situ spectroscopy and automation
• Universal Machine Learning Kohn-Sham Hamiltonian for Materials
• Overcoming the Barrier of Orbital-Free Density Functional Theory for Molecular Systems Using Deep Learning
• Con-CDVAE: A method for the conditional generation of crystal structures
• Large intrinsic anomalous Hall effect in both Nb${}_2$FeB${}_2$ and Ta${}_2$FeB${}_2$ with collinear antiferromagnetism
• Neural-network Density Functional Theory Based on Variational Energy Minimization
• Data-driven Design of High Pressure Hydride Superconductors using DFT and Deep Learning
• Molecular Quantum Chemical Data Sets and Databases for Machine Learning Potentials
• Machine learning guided discovery of superconducting calcium borocarbides
• Topological crystalline insulators from stacked graphene layers
• Closed-loop Error Correction Learning Accelerates Experimental Discovery of Thermoelectric Materials
• Accelerating superconductor discovery through tempered deep learning of the electron-phonon spectral function
• Accelerating materials discovery for polymer solar cells: Data-driven insights enabled by natural language processing
• dZiner: Rational Inverse Design of Materials with AI Agents
• Exploring large language models for microstructure evolution in materials

Cited by in corpus (5)

• InvDesFlow: An AI-driven materials inverse design workflow to explore possible high-temperature superconductors
• InvDesFlow-AL: active learning-based workflow for inverse design of functional materials
• High-temperature superconductivity in Li${}_2$AuH${}_6$ mediated by strong electron-phonon coupling under ambient pressure
• Perovskite-R1: a domain-specialized large language model for intelligent discovery of precursor additives and experimental design
• HTSC-2025: A Benchmark Dataset of Ambient-Pressure High-Temperature Superconductors for AI-Driven Critical Temperature Prediction