Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
arXiv:2307.08423 · doi:10.1561/2200000115
Abstract
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This work aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.
Published in Foundations and Trends in Machine Learning. Identical to the journal version except for formatting
References in corpus (166)
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- Variational Inference: A Review for Statisticians
- DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
- Well-Tempered Metadynamics: A Smoothly Converging and Tunable Free-Energy Method
- Maximally localized Wannier functions: Theory and applications
- Automatic chemical design using a data-driven continuous representation of molecules
- Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
- Machine Learning for Fluid Mechanics
- Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
- SchNet - a deep learning architecture for molecules and materials
- Deep Visual Domain Adaptation: A Survey
- Solving the Quantum Many-Body Problem with Artificial Neural Networks
- ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
- Quantum Spin Hall Effect and Topological Field Effect Transistor in Two-Dimensional Transition Metal Dichalcogenides
- E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
- DeepDTA: Deep Drug-Target Binding Affinity Prediction
- Outlook for inverse design in nanophotonics
- Perspective on density functional theory
- The Alloy Theoretic Automated Toolkit: A User Guide
- Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods
- Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
- Quantum-Chemical Insights from Deep Tensor Neural Networks
- Multiscale mobility networks and the large scale spreading of infectious diseases
- Computational complexity and fundamental limitations to fermionic quantum Monte Carlo simulations
- Machine Learning of Accurate Energy-Conserving Molecular Force Fields
- B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
- PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
- Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
- A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
- A Performance and Cost Assessment of Machine Learning Interatomic Potentials
- Big Data of Materials Science - Critical Role of the Descriptor
- Machine learning for molecular simulation
- Big Data meets Quantum Chemistry Approximations: The -Machine Learning Approach
- Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
- Molecular Contrastive Learning of Representations via Graph Neural Networks
- SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
- Invariant Variation Problems
- The Open Catalyst 2020 (OC20) Dataset and Community Challenges
- Atomistic Line Graph Neural Network for Improved Materials Property Predictions
- High-pressure phases of silane
- Smoothed Particle Hydrodynamics and Magnetohydrodynamics
- Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
- Machine-learning based interatomic potential for amorphous carbon
- Finding Density Functionals with Machine Learning
- DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks
- VAMPnets: Deep learning of molecular kinetics
- Deep neural network solution of the electronic Schrödinger equation
- Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
- Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
- Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements
- Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
- Predicting materials properties without crystal structure: Deep representation learning from stoichiometry
- Quantum Entanglement in Neural Network States
- Understanding and reducing errors in density functional calculations
- A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems
- Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm
- SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
- Efficient Representation of Quantum Many-body States with Deep Neural Networks
- Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
- The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts
- How accurate is density functional theory at predicting dipole moments? An assessment using a new database of 200 benchmark values
- Everything is Connected: Graph Neural Networks
- Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Prediction
- Higher-Order Explanations of Graph Neural Networks via Relevant Walks
- Deep autoregressive models for the efficient variational simulation of many-body quantum systems
- Symmetries and many-body excited states with neural-network quantum states
- Fermionic neural-network states for ab-initio electronic structure
- OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
- Equivalence of restricted Boltzmann machines and tensor network states
- Weak binding between two aromatic rings: feeling the van der Waals attraction by quantum Monte Carlo methods
- Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
- TorchMD: A deep learning framework for molecular simulations
- Quantum many-body dynamics in two dimensions with artificial neural networks
- Berry curvature memory through electrically driven stacking transitions
- Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
- Approximating quantum many-body wave-functions using artificial neural networks
- On the Completeness of Atomic Structure Representations
- Coarse Graining Molecular Dynamics with Graph Neural Networks
- An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties
- Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Science
- Learning to design drug-like molecules in three-dimensional space using deep generative models
- Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
- Coarse-Graining Auto-Encoders for Molecular Dynamics
- Backflow Transformations via Neural Networks for Quantum Many-Body Wave-Functions
- Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow
- Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning
- Stiff Neural Ordinary Differential Equations
- Real-time high-resolution CO geological storage prediction using nested Fourier neural operators
- Exploring Phononic Properties of Two-Dimensional Materials using Machine Learning Interatomic Potentials
- NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems
- Learning the electronic density of states in condensed matter
- Autonomously revealing hidden local structures in supercooled liquids
- Orbital-free Bond Breaking via Machine Learning
- Dirac-type nodal spin liquid revealed by refined quantum many-body solver using neural-network wave function, correlation ratio, and level spectroscopy
- Molecular geometry prediction using a deep generative graph neural network
- Solving the Bose-Hubbard model with machine learning
- Ab-initio quantum chemistry with neural-network wavefunctions
- General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
- Optimizing large parameter sets in variational quantum Monte Carlo
- Prediction of a large-gap and switchable Kane-Mele quantum spin Hall insulator
- Machine learning and density functional theory
- Pure density functional for strong correlations and the thermodynamic limit from machine learning
- A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
- Ferroelectric nonlinear anomalous Hall effect in few-layer WTe
- Machine learning technique to find quantum many-body ground states of bosons on a lattice
- Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting
- COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation
- Solving frustrated quantum many-particle models with convolutional neural networks
- Learning the exchange-correlation functional from nature with fully differentiable density functional theory
- Giant nonlinear photocurrent in -symmetric magnetic topological quantum materials
- Fermionic Wave Functions from Neural-Network Constrained Hidden States
- Neural Gutzwiller-projected variational wave functions
- HypoSVI: Hypocenter inversion with Stein variational inference and Physics Informed Neural Networks
- Design and Analysis of Machine Learning Exchange-Correlation Functionals via Rotationally Invariant Convolutional Descriptors
- Neural network wave functions and the sign problem
- Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids
- Discovering Quantum Phase Transitions with Fermionic Neural Networks
- Predictive Power of the Exact Constraints and Appropriate Norms in Density Functional Theory
- Autonomous Efficient Experiment Design for Materials Discovery with Bayesian Model Averaging
- Machine Learning Implicit Solvation for Molecular Dynamics
- Using a machine learning approach to determine the space group of a structure from the atomic pair distribution function (PDF)
- Group SELFIES: A Robust Fragment-Based Molecular String Representation
- Kinetic energy densities based on the fourth order gradient expansion: performance in different classes of materials and improvement via machine learning
- Direct prediction of phonon density of states with Euclidean neural networks
- ACCDB: A Collection of Chemistry DataBases for Broad Computational Purposes
- Flow-matching -- efficient coarse-graining of molecular dynamics without forces
- Natural Language Processing Models That Automate Programming Will Transform Chemistry Research and Teaching
- Graph Neural Networks Accelerated Molecular Dynamics
- Towards the ground state of molecules via diffusion Monte Carlo on neural networks
- Deep-learning electronic-structure calculation of magnetic superstructures
- JARVIS-Leaderboard: A Large Scale Benchmark of Materials Design Methods
- Machine Learning of Free Energies in Chemical Compound Space Using Ensemble Representations: Reaching Experimental Uncertainty for Solvation
- A simple linear algebra identity to optimize Large-Scale Neural Network Quantum States
- Wave function Ansatz (but Periodic) Networks and the Homogeneous Electron Gas
- Accurate Computation of Quantum Excited States with Neural Networks
- Inverse design of glass structure with deep graph neural networks
- Retrieval-Enhanced Machine Learning
- Harnessing Interpretable and Unsupervised Machine Learning to Address Big Data from Modern X-ray Diffraction
- Message-Passing Neural Quantum States for the Homogeneous Electron Gas
- A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
- Toward Orbital-Free Density Functional Theory with Small Data Sets and Deep Learning
- On the Brittleness of Bayesian Inference
- PaperRobot: Incremental Draft Generation of Scientific Ideas
- Evolving symbolic density functionals
- Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks
- Method to solve quantum few-body problems with artificial neural networks
- Exploring Supervised Machine Learning for Multi-Phase Identification and Quantification from Powder X-Ray Diffraction Spectra
- Gauge equivariant neural networks for quantum lattice gauge theories
- Machine learning the derivative discontinuity of density-functional theory
- Learning from the Density to Correct Total Energy and Forces in First Principle Simulations
- Robustness of Local Predictions in Atomistic Machine Learning Models
- Artifact Identification in X-ray Diffraction Data using Machine Learning Methods
- Ab-initio variational wave functions for the time-dependent many-electron Schrödinger equation
- Exact constraints and appropriate norms in machine learned exchange-correlation functionals
- CREMP: Conformer-rotamer ensembles of macrocyclic peptides for machine learning
- Machine Learning Diffusion Monte Carlo Energies
- Variational quantum dynamics of two-dimensional rotor models
- Variational Neural-Network Ansatz for Continuum Quantum Field Theory
- Ab initio machine learning of phase space averages
- Seven Useful Questions in Density Functional Theory
- Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions
- Fluidic Topology Optimization with an Anisotropic Mixture Model
- Neural Wave Functions for Superfluids
- Data-driven and constrained optimization of semi-local exchange and non-local correlation functionals for materials and surface chemistry
- Some Problems in Density Functional Theory
- How Well Does Kohn-Sham Regularizer Work for Weakly Correlated Systems?