Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Enhancing materials property prediction by leveraging computational and experimental data using deep transfer learning

Journal Article · · Nature Communications
 [1];  [2];  [2];  [1];  [1];  [2];  [1]
  1. Northwestern Univ., Evanston, IL (United States). Dept. of Electrical and Computer Engineering
  2. National Inst. of Standards and Technology (NIST), Gaithersburg, MD (United States). Thermodynamics and Kinetics Group
+ Show Author Affiliations

The current predictive modeling techniques applied to Density Functional Theory (DFT) computations have helped accelerate the process of materials discovery by providing significantly faster methods to scan materials candidates, thereby reducing the search space for future DFT computations and experiments. However, in addition to prediction error against DFT-computed properties, such predictive models also inherit the DFT-computation discrepancies against experimentally measured properties. To address this challenge, we demonstrate that using deep transfer learning, existing large DFT-computational data sets (such as the Open Quantum Materials Database (OQMD)) can be leveraged together with other smaller DFT-computed data sets as well as available experimental observations to build robust prediction models. We build a highly accurate model for predicting formation energy of materials from their compositions; using an experimental data set of 1 , 963 observations, the proposed approach yields a mean absolute error (MAE) of 0.06 eV/atom, which is significantly better than existing machine learning (ML) prediction modeling based on DFT computations and is comparable to the MAE of DFT-computation itself.

Research Organization:
Northwestern Univ., Evanston, IL (United States); National Inst. of Standards and Technology (NIST), Gaithersburg, MD (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); Dept. of Commerce (United States); USDOE
Grant/Contract Number:
SC0014330; SC0019358; 70NANB19H005
OSTI ID:
1619594
Alternate ID(s):
OSTI ID: 1624217
Journal Information:
Nature Communications, Vol. 10, Issue 1; ISSN 2041-1723
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 131 works
Citation information provided by
Web of Science

References (92)

Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science journal April 2016
From Organized High-Throughput Data to Phenomenological Theory using Machine Learning: The Example of Dielectric Breakdown journal February 2016
A strategy to apply machine learning to small datasets in materials science journal May 2018
Deep learning journal May 2015
Elastic properties of bulk and low-dimensional materials using van der Waals density functional dataset January 2020
Prediction model of band-gap for AX binary compounds by combination of density functional theory calculations and machine learning techniques text January 2015
Elastic properties of bulk and low-dimensional materials using van der Waals density functional dataset January 2020
Diffusion of Ge below the Si(100) Surface: Theory and Experiment journal March 2000
Rapid and Accurate Machine Learning Recognition of High Performing Metal Organic Frameworks for CO 2 Capture journal August 2014
Including crystal structure attributes in machine learning models of formation energies via Voronoi tessellations journal July 2017
On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets journal September 2014
Comparison of theory with quenching experiments for the entropy and enthalpy of vacancy formation in Si and Ge journal October 1976
Machine learning of molecular electronic properties in chemical compound space journal September 2013
Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters journal April 2014
Optimizing transition states via kernel-based machine learning journal May 2012
SchNet – A deep learning architecture for molecules and materials journal June 2018
Computational screening of high-performance optoelectronic materials using OptB88vdW and TB-mBJ formalisms journal May 2018
AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations journal June 2012
Nobel Lecture: Electronic structure of matter—wave functions and density functionals journal October 1999
Properties of intrinsic point defects in silicon determined by zinc diffusion experiments under nonequilibrium conditions journal December 1995
Understanding NOx formation in nonpremixed flames: Experiments and modeling journal January 1995
Extracting Grain Orientations from EBSD Patterns of Polycrystalline Materials Using Convolutional Neural Networks journal October 2018
Recent progress in metallurgical thermochemistry journal January 1969
High-Throughput Machine-Learning-Driven Synthesis of Full-Heusler Compounds text January 2016
The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies journal December 2015
Accelerated search for materials with targeted properties by adaptive design journal April 2016
Accelerating materials property predictions using machine learning journal September 2013
A single-atom library for guided monometallic and concentration-complex multimetallic designs journal May 2022
Matminer: An open source toolkit for materials data mining journal September 2018
Machine learning with force-field-inspired descriptors for materials: Fast screening and mapping energy landscape journal August 2018
Toward Computational Materials Design: The Impact of Density Functional Theory on Materials Research journal September 2006
An introduction to ROC analysis journal June 2006
Recent progress in metallurgical thermochemistry journal January 1969
Deep materials informatics: Applications of deep learning in materials science journal June 2019
Machine-learning-assisted materials discovery using failed experiments journal May 2016
Machine learning modeling of superconducting critical temperature journal June 2018
High-throughput Identification and Characterization of Two-dimensional Materials using Density functional theory journal July 2017
Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD) journal September 2013
A high-throughput infrastructure for density functional theory calculations journal June 2011
Data-Driven Model for Estimation of Friction Coefficient Via Informatics Methods journal May 2012
A Survey on Transfer Learning journal October 2010
Machine Learning Energies of 2 Million Elpasolite ( A B C 2 D 6 ) Crystals journal September 2016
Quantum-chemical insights from deep tensor neural networks journal January 2017
Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals text January 2016
Universal fragment descriptors for predicting properties of inorganic crystals journal June 2017
Unprecedented generation of 3D heterostructures by mechanochemical disassembly and re-ordering of incommensurate metal chalcogenides journal June 2020
Machine learning in materials informatics: recent applications and prospects journal December 2017
Rapid and Accurate Machine Learning Recognition of High Performing Metal Organic Frameworks for CO 2 Capture journal August 2014
Optimizing transition states via kernel-based machine learning journal May 2012
From Organized High-Throughput Data to Phenomenological Theory using Machine Learning: The Example of Dielectric Breakdown journal February 2016
Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science journal April 2016
Computational screening of high-performance optoelectronic materials using OptB88vdW and TB-mBJ formalisms text January 2018
Elastic properties of bulk and low-dimensional materials using van der Waals density functional journal July 2018
Predicting density functional theory total energies and enthalpies of formation of metal-nonmetal compounds by linear regression journal February 2016
Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters journal April 2014
Dropout from Higher Education: A Theoretical Synthesis of Recent Research journal March 1975
Machine learning in materials informatics: recent applications and prospects journal December 2017
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning journal May 2016
On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets journal September 2014
High-throughput Identification and Characterization of Two-dimensional Materials using Density functional theory journal July 2017
Predicting the Thermodynamic Stability of Solids Combining Density Functional Theory and Machine Learning journal May 2017
Matrix- and tensor-based recommender systems for the discovery of currently unknown inorganic compounds journal January 2018
Accelerated search for materials with targeted properties by adaptive design journal April 2016
Coupling structural evolution and oxygen-redox electrochemistry in layered transition metal oxides journal March 2022
ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition journal December 2018
ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition journal December 2018
Understanding NOx formation in nonpremixed flames: Experiments and modeling journal January 1995
Accelerating materials property predictions using machine learning journal September 2013
Deep materials informatics: Applications of deep learning in materials science journal June 2019
Machine learning modeling of superconducting critical temperature journal June 2018
Machine learning with force-field inspired descriptors for materials: fast screening and mapping energy landscape text January 2018
How Chemical Composition Alone Can Predict Vibrational Free Energies and Entropies of Solids journal July 2017
How Chemical Composition Alone Can Predict Vibrational Free Energies and Entropies of Solids journal July 2017
A Statistical Learning Framework for Materials Science: Application to Elastic Moduli of k-nary Inorganic Polycrystalline Compounds journal October 2016
Data-Driven Model for Estimation of Friction Coefficient Via Informatics Methods journal May 2012
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation journal July 2013
Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD) journal September 2013
Formation enthalpies by mixing GGA and GGA + U calculations journal July 2011
Quantum-chemical insights from deep tensor neural networks journal January 2017
High-Throughput Machine-Learning-Driven Synthesis of Full-Heusler Compounds journal October 2016
AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations journal June 2012
Prediction of thermal boundary resistance by the machine learning method journal August 2017
Predicting the Thermodynamic Stability of Solids Combining Density Functional Theory and Machine Learning journal May 2017
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
  • Jha, Dipendra; Ward, Logan; Yang, Zijiang
  • KDD '19: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining https://doi.org/10.1145/3292500.3330703
conference July 2019
Matminer: An open source toolkit for materials data mining journal September 2018
Machine-learning-assisted materials discovery using failed experiments journal May 2016
A general-purpose machine learning framework for predicting properties of inorganic materials journal August 2016
Toward Computational Materials Design: The Impact of Density Functional Theory on Materials Research journal September 2006
Experimental formation enthalpies for intermetallic phases and other inorganic compounds journal October 2017
Combinatorial screening for new materials in unconstrained composition space with machine learning journal March 2014
Prediction model of band gap for inorganic compounds by combination of density functional theory calculations and machine learning techniques journal March 2016
Experimental formation enthalpies for intermetallic phases and other inorganic compounds [Supplemental Data] code October 2017

Cited By (1)

Machine Learning-Based Prediction of Crystal Systems and Space Groups from Inorganic Materials Compositions journal February 2020

Figures / Tables (10)

Fig. 1(p. 2)figure Fig. 1
Fig. 2(p. 3)figure Fig. 2
Table 1(p. 4)table Table 1
Table 2(p. 4)table Table 2
Fig. 3(p. 5)figure Fig. 3
Fig. 4(p. 6)figure Fig. 4
Table 3(p. 7)table Table 3
Fig. 5(p. 8)figure Fig. 5
Fig. 6(p. 9)figure Fig. 6
Table 4(p. 10)table Table 4

Similar Records

Related Subjects

97 MATHEMATICS AND COMPUTING
36 MATERIALS SCIENCE
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
theory and computation
materials chemistry
inorganic chemistry
density functional theory