skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Emerging materials intelligence ecosystems propelled by machine learning

Abstract

We report that the age of cognitive computing and artificial intelligence (AI) is just dawning. Inspired by its successes and promises, several AI ecosystems are blossoming, many of them within the domain of materials science and engineering. These materials intelligence ecosystems are being shaped by several independent developments. Machine learning (ML) algorithms and extant materials data are utilized to create surrogate models of materials properties and performance predictions. Materials data repositories, which fuel such surrogate model development, are mushrooming. Automated data and knowledge capture from the literature (to populate data repositories) using natural language processing approaches is being explored. The design of materials that meet target property requirements and of synthesis steps to create target materials appear to be within reach, either by closed-loop active-learning strategies or by inverting the prediction pipeline using advanced generative algorithms. AI and ML concepts are also transforming the computational and physical laboratory infrastructural landscapes used to create materials data in the first place. Surrogate models that can outstrip physics-based simulations (on which they are trained) by several orders of magnitude in speed while preserving accuracy are being actively developed. Automation, autonomy and guided high-throughput techniques are imparting enormous efficiencies and eliminating redundancies in materialsmore » synthesis and characterization. The integration of the various parts of the burgeoning ML landscape may lead to materials-savvy digital assistants and to a human-machine partnership that could enable dramatic efficiencies, accelerated discoveries and increased productivity. Here, we review these emergent materials intelligence ecosystems and discuss the imminent challenges and opportunities. The materials research landscape is being transformed by the infusion of approaches based on machine learning. This Review discusses the emerging materials intelligence ecosystems and the potential of human-machine partnerships for fast and efficient virtual materials screening, development and discovery.« less

Authors:
ORCiD logo [1];  [2]; ORCiD logo [2]
  1. Argonne National Lab. (ANL), Lemont, IL (United States)
  2. Georgia Institute of Technology, Atlanta, GA (United States)
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Laboratory Directed Research and Development (LDRD) Program; US Department of the Navy, Office of Naval Research (ONR)
OSTI Identifier:
1864296
Grant/Contract Number:  
AC02-06CH11357; PRJ1007392
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Nature Reviews. Materials
Additional Journal Information:
Journal Volume: 6; Journal Issue: 8; Journal ID: ISSN 2058-8437
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; machine learning; materials science; techniques; instrumentation; theory; computation

Citation Formats

Batra, Rohit, Song, Le, and Ramprasad, Rampi. Emerging materials intelligence ecosystems propelled by machine learning. United States: N. p., 2020. Web. doi:10.1038/s41578-020-00255-y.
Batra, Rohit, Song, Le, & Ramprasad, Rampi. Emerging materials intelligence ecosystems propelled by machine learning. United States. https://doi.org/10.1038/s41578-020-00255-y
Batra, Rohit, Song, Le, and Ramprasad, Rampi. 2020. "Emerging materials intelligence ecosystems propelled by machine learning". United States. https://doi.org/10.1038/s41578-020-00255-y. https://www.osti.gov/servlets/purl/1864296.
@article{osti_1864296,
title = {Emerging materials intelligence ecosystems propelled by machine learning},
author = {Batra, Rohit and Song, Le and Ramprasad, Rampi},
abstractNote = {We report that the age of cognitive computing and artificial intelligence (AI) is just dawning. Inspired by its successes and promises, several AI ecosystems are blossoming, many of them within the domain of materials science and engineering. These materials intelligence ecosystems are being shaped by several independent developments. Machine learning (ML) algorithms and extant materials data are utilized to create surrogate models of materials properties and performance predictions. Materials data repositories, which fuel such surrogate model development, are mushrooming. Automated data and knowledge capture from the literature (to populate data repositories) using natural language processing approaches is being explored. The design of materials that meet target property requirements and of synthesis steps to create target materials appear to be within reach, either by closed-loop active-learning strategies or by inverting the prediction pipeline using advanced generative algorithms. AI and ML concepts are also transforming the computational and physical laboratory infrastructural landscapes used to create materials data in the first place. Surrogate models that can outstrip physics-based simulations (on which they are trained) by several orders of magnitude in speed while preserving accuracy are being actively developed. Automation, autonomy and guided high-throughput techniques are imparting enormous efficiencies and eliminating redundancies in materials synthesis and characterization. The integration of the various parts of the burgeoning ML landscape may lead to materials-savvy digital assistants and to a human-machine partnership that could enable dramatic efficiencies, accelerated discoveries and increased productivity. Here, we review these emergent materials intelligence ecosystems and discuss the imminent challenges and opportunities. The materials research landscape is being transformed by the infusion of approaches based on machine learning. This Review discusses the emerging materials intelligence ecosystems and the potential of human-machine partnerships for fast and efficient virtual materials screening, development and discovery.},
doi = {10.1038/s41578-020-00255-y},
url = {https://www.osti.gov/biblio/1864296}, journal = {Nature Reviews. Materials},
issn = {2058-8437},
number = 8,
volume = 6,
place = {United States},
year = {Mon Nov 09 00:00:00 EST 2020},
month = {Mon Nov 09 00:00:00 EST 2020}
}

Works referenced in this record:

Beyond Scaling Relations for the Description of Catalytic Materials
journal, February 2019


Deep learning
journal, May 2015


“Found in Translation”: predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models
journal, January 2018


Accelerated Discovery of Large Electrostrains in BaTiO 3 -Based Piezoelectrics Using Active Learning
journal, January 2018


Amp: A modular approach to machine learning in atomistic simulations
journal, October 2016


Understanding and visualizing microstructure and microstructure variance as a stochastic process
journal, September 2011


Potential Energy Surfaces Fitted by Artificial Neural Networks
journal, March 2010


A Least Absolute Shrinkage and Selection Operator (Lasso) for Nonlinear System Identification
journal, January 2006


Predicting the fracture toughness of PNCs: A stochastic approach based on ANN and ANFIS
journal, May 2015


Machine Learning Interatomic Potentials as Emerging Tools for Materials Science
journal, September 2019


High-dimensional neural-network potentials for multicomponent systems: Applications to zinc oxide
journal, April 2011


ChemSpider: An Online Chemical Information Resource
journal, November 2010


Genetic programming for experimental big data mining: A case study on concrete creep formulation
journal, October 2016


Boosting Quantum Machine Learning Models with a Multilevel Combination Technique: Pople Diagrams Revisited
journal, December 2018


Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials
journal, January 2016


Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
journal, November 2018


Transferable Machine-Learning Model of the Electron Density
journal, December 2018


Solving the electronic structure problem with machine learning
journal, February 2019


Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning
journal, February 2019


Exploring the Stability of Novel Wide Bandgap Perovskites by a Robot Based High Throughput Approach
journal, October 2017


A Machine Learning Approach to Zeolite Synthesis Enabled by Automatic Literature Data Extraction
journal, April 2019


Active-learning and materials design: the example of high glass transition temperature polymers
journal, June 2019


Predicting Crystallization Tendency of Polymers Using Multifidelity Information Fusion and Machine Learning
journal, June 2020


A universal strategy for the creation of machine learning-based atomistic force fields
journal, September 2017


Comparing the accuracy of high-dimensional neural network potentials and the systematic molecular fragmentation method: A benchmark study for all-trans alkanes
journal, May 2016


Extracting Grain Orientations from EBSD Patterns of Polycrystalline Materials Using Convolutional Neural Networks
journal, October 2018


Network analysis of synthesizable materials discovery
journal, May 2019


Inverse molecular design using machine learning: Generative models for matter engineering
journal, July 2018


New tolerance factor to predict the stability of perovskite oxides and halides
journal, February 2019


Accelerating the discovery of materials for clean energy in the era of smart automation
journal, April 2018


Neural network predictions of oxygen interactions on a dynamic Pd surface
journal, January 2017


How van der Waals interactions determine the unique properties of water
journal, July 2016


A brief history of CALPHAD
journal, March 2008


Space-filling designs for computer experiments: A review
journal, January 2016


Deep materials informatics: Applications of deep learning in materials science
journal, June 2019


Recent advances and applications of machine learning in solid-state materials science
journal, August 2019


Realistic Atomistic Structure of Amorphous Silicon from Machine-Learning-Driven Molecular Dynamics
journal, May 2018


Machine Learning Strategy for Accelerated Design of Polymer Dielectrics
journal, February 2016


Gaussian Processes for Machine Learning
book, January 2005


Closed-loop optimization of fast-charging protocols for batteries with machine learning
journal, February 2020


The Automation of Science
journal, April 2009


Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
journal, April 2010


A Tutorial on Thompson Sampling
journal, January 2018


Machine Learning Force Fields: Construction, Validation, and Outlook
journal, December 2016


Neural network potentials for dynamics and thermodynamics of gold nanoparticles
journal, February 2017


Statistical inference and adaptive design for materials discovery
journal, June 2017


Machine learning of accurate energy-conserving molecular force fields
journal, May 2017


A high-throughput data analysis and materials discovery tool for strongly correlated materials
journal, November 2018


Analytics for microstructure datasets produced by phase-field simulations
journal, January 2016


Active learning of linearly parametrized interatomic potentials
journal, December 2017


Symbolic regression in materials science
journal, June 2019


Performance and Cost Assessment of Machine Learning Interatomic Potentials
journal, October 2019


Similarity of Precursors in Solid-State Synthesis as Text-Mined from Scientific Literature
journal, August 2020


From Organized High-Throughput Data to Phenomenological Theory using Machine Learning: The Example of Dielectric Breakdown
journal, February 2016


Recent developments in the Inorganic Crystal Structure Database: theoretical crystal structure data and related features
journal, September 2019


A robotic platform for flow synthesis of organic compounds informed by AI planning
journal, August 2019


Construction of high-dimensional neural network potentials using environment-dependent atom pairs
journal, May 2012


ReaxFF Reactive Force Field for Molecular Dynamics Simulations of Hydrocarbon Oxidation
journal, February 2008


Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction
journal, August 2019


Imaging mechanism for hyperspectral scanning probe microscopy via Gaussian process modelling
journal, March 2020


Predicting compressive strength of lightweight foamed concrete using extreme learning machine model
journal, January 2018


Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials
journal, March 2015


Machine Learning Prediction of Heat Capacity for Solid Inorganics
journal, May 2018


Neural network interatomic potential for the phase change material GeTe
journal, May 2012


Machine Learning Assisted Predictions of Intrinsic Dielectric Breakdown Strength of ABX 3 Perovskites
journal, June 2016


Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
journal, April 2019


SchNetPack: A Deep Learning Toolbox For Atomistic Systems
journal, November 2018


Autonomous robotic searching and assembly of two-dimensional crystals to build van der Waals superlattices
journal, April 2018


Inverse design of porous materials using artificial neural networks
journal, January 2020


Application and further development of advanced image processing algorithms for automated analysis of serial section image data
journal, December 2008


The AFLOW standard for high-throughput materials science calculations
journal, October 2015


Designing computer experiments with multiple types of factors: The MaxPro approach
journal, June 2019


On the Determination of Molecular Fields. II. From the Equation of State of a Gas
journal, October 1924


Machine learning a bond order potential model to study thermal transport in WSe 2 nanostructures
journal, January 2019


Bayesian methods for image segmentation
journal, July 2011


How Chemical Composition Alone Can Predict Vibrational Free Energies and Entropies of Solids
journal, July 2017


Deep Multitask Learning for Railway Track Inspection
journal, January 2017


Genetic programming for multitimescale modeling
journal, August 2005


Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks
journal, January 2020


Physical descriptor for the Gibbs energy of inorganic crystalline solids and temperature-dependent materials chemistry
journal, October 2018


A Supervised Learning Approach for Dynamic Sampling
journal, February 2016


Bypassing the Kohn-Sham equations with machine learning
journal, October 2017


Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013


Experimental search for high-temperature ferroelectric perovskites guided by two-step machine learning
journal, April 2018


Polymer Genome: A Data-Powered Polymer Informatics Platform for Property Predictions
journal, July 2018


Nuclear Quantum Effects in Water at the Triple Point: Using Theory as a Link Between Experiments
journal, May 2016


Polymer design using genetic algorithm and machine learning
journal, January 2021


Data-driven discovery of formulas by symbolic regression
journal, July 2019


Computer-Assisted Retrosynthesis Based on Molecular Similarity
journal, November 2017


Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations?
journal, May 2015


Human versus Robots in the Discovery and Crystallization of Gigantic Polyoxometalates
journal, August 2017


Planning chemical syntheses with deep neural networks and symbolic AI
journal, March 2018


Predicting the thermodynamic stability of perovskite oxides using machine learning models
journal, July 2018


Fast machine-learning online optimization of ultra-cold-atom experiments
journal, May 2016


Machine Learning Classical Interatomic Potentials for Molecular Dynamics from First-Principles Training Data
journal, January 2019


Developing an interatomic potential for martensitic phase transformations in zirconium by machine learning
journal, August 2018


Data-driven prediction of battery cycle life before capacity degradation
journal, March 2019


Electrically Conductive Thermally Insulating Bi–Si Nanocomposites by Interface Design for Thermal Management
journal, July 2018


High Throughput Quantitative Metallography for Complex Microstructures Using Deep Learning: A Case Study in Ultrahigh Carbon Steel
journal, February 2019


Machine Learning the Physical Nonlocal Exchange–Correlation Functional of Density-Functional Theory
journal, October 2019


Prediction of Organic Reaction Outcomes Using Machine Learning
journal, April 2017


On representing chemical environments
journal, May 2013


Less is more: Sampling chemical space with active learning
journal, June 2018


Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network
journal, August 2019


Topology-Scaling Identification of Layered Solids and Stable Exfoliated 2D Materials
journal, March 2017


Machine Learning Directed Search for Ultraincompressible, Superhard Materials
journal, July 2018


Accelerated search for BaTiO 3 -based piezoelectrics with vertical morphotropic phase boundary using Bayesian learning
journal, November 2016


Fast, accurate, and transferable many-body interatomic potentials by symbolic regression
journal, November 2019


SchNet – A deep learning architecture for molecules and materials
journal, June 2018


DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
journal, July 2018


Computational screening of high-performance optoelectronic materials using OptB88vdW and TB-mBJ formalisms
journal, May 2018


Using SMILES strings for the description of chemical connectivity in the Crystallography Open Database
journal, May 2018


Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning
journal, October 2017


Machine learning assisted design of high entropy alloys with desired property
journal, May 2019


Learning physical descriptors for materials science by compressed sensing
journal, February 2017


Molecular graph convolutions: moving beyond fingerprints
journal, August 2016


ChemDataExtractor: A Toolkit for Automated Extraction of Chemical Information from the Scientific Literature
journal, October 2016


Machine Learning-Assisted Discovery of Solid Li-Ion Conducting Materials
journal, November 2018


The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies
journal, December 2015


Deep learning approaches for mining structure-property linkages in high contrast composites from simulation datasets
journal, August 2018


Taking the Human Out of the Loop: A Review of Bayesian Optimization
journal, January 2016


Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia
journal, April 2019


The Computational Materials Repository
journal, November 2012


Multi-fidelity machine learning models for accurate bandgap predictions of solids
journal, March 2017


The FAIR Guiding Principles for scientific data management and stewardship
journal, March 2016


SISSO: A compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
journal, August 2018


Iterative-Learning Strategy for the Development of Application-Specific Atomistic Force Fields
journal, August 2019


Database of novel magnetic materials for high-performance permanent magnet development
journal, October 2019


Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties
journal, May 2016


Machine learning for molecular and materials science
journal, July 2018


Mapping mesoscopic phase evolution during E-beam induced transformations via deep learning of atomically resolved images
journal, June 2018


Rational Co-Design of Polymer Dielectrics for Energy Storage
journal, May 2016


A review of deep learning in the study of materials degradation
journal, November 2018


Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models
journal, September 2017


A Kriging-Based Approach to Autonomous Experimentation with Applications to X-Ray Scattering
journal, August 2019


From DFT to machine learning: recent approaches to materials science–a review
journal, May 2019


A Deep Learning Solvent-Selection Paradigm Powered by a Massive Solvent/Nonsolvent Database for Polymers
journal, June 2020


Machine Learning for Molecular Simulation
journal, April 2020


Polymer genome–based prediction of gas permeabilities in polymers
journal, July 2020


Unsupervised word embeddings capture latent knowledge from materials science literature
journal, July 2019


Rapid structural mapping of ternary metallic alloy systems using the combinatorial approach and cluster analysis
journal, July 2007


Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design
journal, February 2019


CRYSTAL: a multi-agent AI system for automated mapping of materials' crystal structures
journal, April 2019


Exploratory designs for computational experiments
journal, February 1995


Machine learning in materials informatics: recent applications and prospects
journal, December 2017


Machine-Learning-Based Predictive Modeling of Glass Transition Temperatures: A Case of Polyhydroxyalkanoate Homopolymers and Copolymers
journal, November 2019


Efficient and accurate machine-learning interpolation of atomic energies in compositions with many species
journal, July 2017


Perspective: Machine learning potentials for atomistic simulations
journal, November 2016


Real-time coherent diffraction inversion using deep generative networks
journal, November 2018


Cheaper faster drug development validated by the repositioning of drugs against neglected tropical diseases
journal, March 2015


Insightful classification of crystal structures using deep learning
journal, July 2018


Discourse in Multimedia: A Case Study in Extracting Geometry Knowledge from Textbooks
journal, January 2020


Machine learning material properties from the periodic table using convolutional neural networks
journal, January 2018


A Transformer Model for Retrosynthesis
book, September 2019

  • Karpov, Pavel; Godin, Guillaume; Tetko, Igor V.
  • Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions: 28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings, p. 817-830
  • https://doi.org/10.1007/978-3-030-30493-5_78

CatApp: A Web Application for Surface Chemistry and Heterogeneous Catalysis
journal, December 2011


Autonomous intelligent agents for accelerated materials discovery
journal, January 2020


Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery
journal, January 2018


Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction
journal, February 2017


A charge density prediction model for hydrocarbons using deep neural networks
journal, March 2020


Machine learning models for the lattice thermal conductivity prediction of inorganic materials
journal, December 2019


Machine learning modeling of superconducting critical temperature
journal, June 2018


Development of a machine learning potential for graphene
journal, February 2018


Machine Learning in Computer-Aided Synthesis Planning
journal, April 2018


Sliced Latin Hypercube Designs
journal, March 2012


Deep learning analysis of defect and phase evolution during electron beam-induced transformations in WS2
journal, February 2019


Microstructural Materials Design Via Deep Adversarial Learning Methodology
journal, October 2018


Perspective: NanoMine: A material genome approach for polymer nanocomposites analysis and design
journal, March 2016


Recent advances in machine learning towards multiscale soft materials design
journal, March 2019


Scoping the polymer genome: A roadmap for rational polymer dielectrics design and beyond
journal, September 2018


Parameterization of empirical forcefields for glassy silica using machine learning
journal, June 2019


A multi-fidelity information-fusion approach to machine learn and predict polymer bandgap
journal, February 2020


Virtual screening of inorganic materials synthesis parameters with deep learning
journal, December 2017


Autonomy in materials research: a case study in carbon nanotube growth
journal, October 2016


Automated Phase Mapping with AgileFD and its Application to Light Absorber Discovery in the V–Mn–Nb Oxide System
journal, December 2016


Material structure-property linkages using three-dimensional convolutional neural networks
journal, March 2018


Machine learning for multi-fidelity scale bridging and dynamical simulations of materials
journal, May 2020


Quantum Loop Topography for Machine Learning
journal, May 2017