Open Access
Subscription or Fee Access
Discovery of Materials through Applied Machine Learning and General Machine Learning Architecture
Abstract
Advances in artificial intelligence technologies, especially machine learning, have generated possibilities in the material sciences to facilitate material exploration and to achieve a profound understanding of the relationship between the constituent elements of the material and the properties represented by the material. The application of machine learning to the exploration of experimental materials is sluggish due to the monetary and temporal costs of experimental data, however parallel methods, such as continuous compositional gradients or high-performance characterization setups, are capable of producing more data than the traditional experimental method and are thus ideal for conjunction with machine learning. A random forest machine learning algorithm has been introduced to two separate substance discovery problems the discovery of modern metallic glass forming ternary compositions and the discovery of novel ammonia decomposition catalysts and has accelerated the creation of high-performance materials.
Keywords: Artificial intelligence technology, machine learning, materials genome initiative (MGI), metallic glasses (MG), random forest (RF) algorithms
References
Ankit Agrawal and Alok Choudhary. “Perspective: Materials informatics and big data:
Realization of the ’fourth paradigm’ of science in materials science”. In: APL Materials 4.5
(2016). issn: 2166532X. doi: 10.1063/1.4946894.
Klaus Schwab. “The Fourth Industrial Revolution”. In: Foreign Affairs (2015). url:
https://www.foreignaffairs.com/articles/2015-12-12/fourthindustrial- revolution.
L. K. Hansen and P. Salamon. “Neural network ensembles.” In: IEEE Transactions on
Pattern Analysis and Machine Intelligence 12.October (1990), pp. 993–1001. issn: 0162-8828.
doi: 10.1109/34.58871.
M. I. Jordan and T. M. Mitchell. “Machine learning: Trends, perspectives, and prospects”. In:
Science 349.6245 (2015), pp. 255–260. issn: 0036-8075. doi: 10.1126/science.aaa8415. arXiv:
arXiv:1011.1669v3. url: http: //www.sciencemag.org/cgi/doi/10.1126/science.aaa8415.
Yue Liu et al. “Materials discovery and design using machine learning”. In: Journal of
Materiomics 3.3 (Sept. 2017), pp. 159–177. issn: 23528486. doi: 10.1016/j.jmat.2017.08.002.
arXiv: 1704.03983. url: http://dx.doi. org/10.1016/j.jmat.2017.08.002.
Oludare Isaac Abiodun et al. “State-of-the-art in artificial neural network applications: A
survey”. In: Heliyon 4.11 (2018), e00938. issn: 24058440. doi: 10.1016/j.heliyon.2018.e00938.
url: https://doi.org/10.1016/j. heliyon.2018.e00938.
David E. Goldberg and John H. Holland. “Genetic Algorithms and Machine Learning”. In:
Machine Learning 3.2 (1988), pp. 95–99. issn: 15730565. doi: 10.1023/A:1022602019183.
Hao Ding et al. “Similarity-basedmachine learning methods for predicting drug-target
interactions: A brief review”. In: Briefings in Bioinformatics 15.5 (2013), pp. 734–747. issn:
doi: 10.1093/bib/bbt056.
Felipe Oviedo et al. “Fast and interpretable classification of small X-ray diffraction datasets
using data augmentation and deep neural networks”. In: npj Computational Materials 5.1 (2019),
pp. 1–9. issn: 20573960. doi: 10.1038/ s41524- 019-0196- x. url:
http://dx.doi.org/10.1038/s41524-019- 0196-x
J.R. Quinlan. “Induction of Decision Trees”. In: Machine Learning (1986), pp. 81–106. issn:
-6125, 1573-0565. doi: 10.1023/A:1022643204877.
Nicolai Meinshausen. “Quantile Regression Forests”. In: Journal of Machine Learning
Research 7 (2006), pp. 983–999.
J J Hopfield. “Neural networks and physical systems with emergent collective
computational abilities (associative memory/parallel processing/categorization/content-
addressable memory/fail-soft devices)”. In: Biophysics 79.April (1982), pp. 2554–2558.
Tin Kam Ho. “Random decision forests”. In: Proceedings of 3rd International Conference
on Document Analysis and Recognition. Vol. 1. IEEE Comput. Soc. Press, pp. 278–282. isbn: 0-
-7128-9. doi: 10.1109/ICDAR.1995.598994. url:
http://ieeexplore.ieee.org/document/598994/.
Materials Genome Initiative for Global Competitiveness. 2011. url: http : / / www .
whitehouse . gov / sites / default / files / microsites / ostp /
materials%7B%5C_%7Dgenome%7B%5C_%7Dinitiative-final.pdf.
“Human Genome Program”. In: Human Genome News 1.1 (1989).
Kyoungdoc Kim et al. “Machine-learning-accelerated high-throughput materials screening:
Discovery of novel quaternary Heusler compounds”. In: Physical Review Materials 2.12 (2018),
pp. 1–9. issn: 24759953. doi: 10.1103/ PhysRevMaterials.2.123801.
G. Pilania, J. E. Gubernatis, and T. Lookman. “Multi-fidelity machine learning models for
accurate bandgap predictions of solids”. In: Computational Materials Science 129 (2017), pp.
–163. issn: 09270256. doi: 10.1016/ j . commatsci . 2016 . 12 . 004.
Yigit M. Arisoy and Tugrul Özel. “Machine learning based predictive modeling of
machining induced microhardness and grain size in Ti-6Al-4V alloy”. In: Materials and
Manufacturing Processes 30.4 (2015), pp. 425–433. issn: 15322475. doi:
1080/10426914.2014.961476.
Juan Carrasquilla and Roger G. Melko. “Machine learning phases of matter”. In: Nature
Physics 13.5 (2017), pp. 431–434. issn: 17452481. doi: 10.1038/ nphys4035. arXiv:
arXiv:1605.01735v1.
Zachary W Ulissi et al. “Machine-Learning Methods Enable Exhaustive Searches for Active
Bimetallic Facets and Reveal Active Site Motifs for CO2 Reduction”. In: ACS Catalysis (2017),
acscatal.7b01648. issn: 2155-5435. doi: 10.1021/acscatal.7b01648. url:
http://pubs.acs.org/doi/10.1021/ acscatal.7b01648.
Zheng Li, Xianfeng Ma, and Hongliang Xin. “Feature engineering of machinelearning
chemisorption models for catalyst design”. In: Catalysis Today 280 (2017), pp. 232–238. issn:
doi: 10.1016/j.cattod.2016.04.013. arXiv: 0807.0093. url:
http://dx.doi.org/10.1016/j.cattod.2016.04. 013.
Jason Hattrick-Simpers, Cun Wen, and Jochen Lauterbach. “The materials super highway:
integrating high-throughput experimentation into mapping the catalysis materials genome”. In:
Catalysis Letters 145.1 (2014), pp. 290–298. issn: 1572879X. doi: 10.1007/s10562-014-1442-y.
url: http://link. springer.com/10.1007/s10562-014-1442-y.
Yadunandan L. Dar. “High-Throughput Experimentation: A Powerful Enabling Technology
for the Chemicals and Materials Industry”. In: Macromolecular Rapid Communications 25.1
(2004), pp. 34–47. issn: 10221336. doi: 10.1002/marc.200300166.
M. L. Green et al. “Fulfilling the promise of the materials genome initiative with high-
throughput experimental methodologies”. In: Applied Physics Reviews 4.1 (2017). issn:
doi: 10.1063/1.4977487.
Nick Wunder et al. “An Open Experimental Database for Exploring Inorganic Materials”.
In: Scientific Data 5 (2018), p. 180053. issn: 2052-4463. doi: 10.1038/sdata.2018.53. url:
http://www.nature.com/articles/ sdata201853.
Y. Kawazoe et al. “Nonequilibrium Phase Diagrams of Ternary Amorphous Alloys”. In:
Landolt-Börnstein - Group III Condensed Matter. Numerical Data and Functional Relationships
in Science and Technology. Springer, 1997.
Stefano Curtarolo et al. “AFLOWLIB.ORG: A distributed materials properties repository
from high-throughput ab initio calculations”. In: Computational Materials Science 58 (2012), pp.
–235. issn: 09270256. doi: 10.1016/j. commatsci.2012.02.002. url:
http://dx.doi.org/10.1016/j.commatsci. 2012.02.002.
Anubhav Jain et al. “Commentary: The Materials Project: A materials genome approach to
accelerating materials innovation”. In: APL Materials 1.1 (July 2013), p. 011002. issn: 2166-
X. doi: 10
Zhao Yin Hou et al. “Artificial neural network aided design of catalyst for
propane ammoxidation”. In: Applied Catalysis A: General 161.1-2 (1997), pp. 183–190. issn:
X. doi: 10.1016/S0926-860X(97)00063-X.
Dipendra Jha et al. “ElemNet: Deep Learning the Chemistry of Materials From Only
Elemental Composition”. In: Scientific Reports 8.1 (2018), pp. 1–13. issn: 20452322. doi:
1038/s41598-018-35934-y. url: http://dx. doi.org/10.1038/s41598-018-35934-y.
Catharina Klanner et al. “The development of descriptors for solids: Teaching ’catalytic
intuition’ to a computer”. In: Angewandte Chemie – International Edition 43.40 (2004), pp.
–5349. issn: 14337851. doi: 10.1002/anie. 200460731.
Bryce Meredig and C. Wolverton. “Dissolving the periodic table in cubic zirconia: Data
mining to discover chemical trends”. In: Chemistry of Materials 26.6 (2014), pp. 1985–1991.
issn: 15205002. doi: 10.1021/cm403727z.
Logan Ward and Chris Wolverton. “Atomistic calculations and materials informatics: A
review”. In: Current Opinion in Solid State and Materials Science 21.3 (2017), pp. 167–176.
issn: 13590286. doi: 10.1016/j.cossms.2016.07. 002. url:
http://dx.doi.org/10.1016/j.cossms.2016.07.002.
B. Meredig et al. “Combinatorial screening for new materials in unconstrained composition
space with machine learning”. In: Physical Review B – Condensed Matter and Materials Physics
9 (2014), pp. 1–7. issn: 10980121. doi: 10. 1103/PhysRevB.89.094104.
Logan Ward et al. “A general-purpose machine learning framework for predicting
properties of inorganic materials”. In: npj Computational Materials 2.July (2016), p. 16028. issn:
-3960. doi: 10 . 1038 / npjcompumats . 2016.28. arXiv: 1606.09551. url:
http://www.nature.com/articles/ npjcompumats201628.
Xianfeng Ma et al. “Machine-Learning-Augmented Chemisorption Model for CO2
Electroreduction Catalyst Screening”. In: Journal of Physical Chemistry Letters 6.18 (2015), pp.
–3533. issn: 19487185. doi: 10 . 1021 / acs . jpclett.5b01660.
Luca M Ghiringhelli et al. “Learning physical descriptors for materials science by
compressed sensing”. In: 001 (2017).
José M Serra, Antonio Chica, and Avelino Corma. “Development of a low temperature light
paraffin isomerization catalysts with improved resistance to water and sulphur by combinatorial
methods”. In: Applied Catalysis A:.1063/1.4812323. url: http:
//aip.scitation.org/doi/10.1063/General 239.1-2 (2003), pp. 35–42. issn: 0926860X. doi:
1016/S0926-860X(02)00371-X.
Gregory A. Landrum, Julie E. Penzotti, and Santosh Putta. “Machine-learning models for
combinatorial catalyst discovery”. In: Measurement Science and Technology 16.1 (2005), pp.
–277. issn: 09570233. doi: 10.1088/0957-0233/16/1/035.
Keisuke Takahashi et al. “Unveiling Hidden Catalysts for the Oxidative Coupling of
Methane based on Combining Machine Learning with Literature Data”. In: ChemCatChem 10.15
(2018), pp. 3223–3228. issn: 18673899. doi: 10.1002/cctc.201800310.
Rampi Ramprasad et al. “Machine Learning and Materials Informatics: Recent Applications
and Prospects”. In: npj Computational Materials November (2017). issn: 2057-3960. doi: 10 .
/ s41524 - 017 - 0056 - 5. arXiv: 1707.07294. url: http://arxiv.org/abs/1707.07294.
Andrew J Medford et al. “From the Sabatier principle to a predictive theory of transition-
metal heterogeneous catalysis”. In: Journal of Catalysis 328 (Aug.2015), pp. 36–42. issn:
doi: 10.1016/j.jcat.2014.12.033. url:
https://linkinghub.elsevier.com/retrieve/pii/S0021951714003686.
Asif J. Chowdhury et al. “Prediction of Adsorption Energies for Chemical Species on Metal
Catalyst Surfaces Using Machine Learning”. In: The Journal of Physical Chemistry C 122
(2018), acs.jpcc.8b09284. issn: 1932-7447. doi: 10.1021/acs.jpcc.8b09284. url:
http://pubs.acs.org/doi/10.1021/acs.jpcc.8b09284.
Robert B. Wexler, John Mark P. Martirez, and Andrew M. Rappe. “Chemical Pressure-
Driven Enhancement of the Hydrogen Evolving Activity of Ni2P from Nonmetal Surface
Doping Interpreted via Machine Learning”. In: Journal of the American Chemical Society
13 (2018), pp. 4678–4683. issn: 15205126.doi: 10.1021/jacs.8b00947.
Fang Ren et al. “Accelerated discovery of metallic glasses through iteration of machine
learning and high-throughput experiments”. In: Science Advances 4.4 (Apr. 2018), eaaq1566.
issn: 2375-2548. doi: 10.1126/sciadv.aaq1566. url:
http://advances.sciencemag.org/lookup/doi/10.1126/sciadv. aaq1566.
Refbacks
- There are currently no refbacks.