The use of generative models to speed up the discovery of materials

The use of generative models to speed up the discovery of materials

Andrea Gregores Coto1, Christian Eike Precker1, Tom Andersson2, Anssi Laukkanen2, Tomi Suhonen2, Pilar Rey Rodriguez1, Santiago Muíños-Landín1

1AIMEN Technology Centre, Smart Systems and Smart Manufacturing, Artificial Intelligence and Data Analytics Laboratory, PI. Cataboi, 36418 Pontevedra, Spain.
2VTT Technical Research Centre of Finland Ltd., 02044 Espoo, Finland.



Material Science is a key factor in the evolution of many industrial sectors. Fields such as the aeronautics, automotive, construction, and biotechnology industries have experienced tremendous development with the introduction of advanced, high-performance materials. Such materials not only provide new functionalities to products, but also significant consequences in terms of economic and environmental sustainability of the products and processes triggered by the more efficient use of energy that they provide. Under this scenario, materials that provide such high performance, such as high entropy alloys (HEAs) or polymer derived ceramics (PDCs), have captured the attention of both industry and researchers in recent years. However, the remarkable number of resources required to develop such materials, from its design phase to its synthesis and characterization, means that the discovery of new high-performance materials is moving at a relatively low pace. This fact places emergent strategies based on artificial intelligence (AI) for the design of materials in a good position to be used to accelerate the whole process, providing an impulse in the initial phases of materials design. The enormous number of combinations of elements and the complexity of synthesizability conditions of HEAs and PDCs respectively, paves the way to the deployment of AI techniques such as Generative Models addressed in this work to create synthetic HEAs and PDCs for highly intensive industrial processes. A specific conditional tabular generative adversarial network (CTGAN) was developed to be used on tabular data to generate novel synthetic compounds for each kind of material. The generated synthetic data was based on the conventional parametric design parameters used for HEAs and PDCs, with specific datasets created for them. The real and generated data are compared, calculation of phase diagrams (CALPHAD) simulations are provided to evaluate the performance of the generated samples and a verification of the novel generated compositions is done in open materials databases available in the literature.

Cite as:

Gregores Coto, A., Precker, C.E., Andersson, T., Laukkanen, A., Suhonen, T., Rodriguez, P.R. & Muíños-Landín, S. (2023). The use of generative models to speed up the discovery of materials. Computer Methods in Materials Science, 23(1), 13-26.

Article (PDF):


Artificial intelligence, Materials science, High-performance materials, Generative models


Ainger, F., & Herbert, J. (1960). The preparation of phosphorus-nitrogen compounds as non-porous solids. Special Ceramics, 168, 168–182.

Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. Proceedings of Machine Learning Research, 70, 214–223.

Barlow, H.B. (1989). Unsupervised learning. Neural Computation, 1(3), 295–311.

Butler, K.T., Frost, J.M., Skelton, J.M., Svane, K.L., & Walsh, A. (2016). Computational materials design of crystalline solids. Chemical Society Reviews, 45(22), 6138–6146.

Cantor, B., Chang, I.T.H., Knight, P., & Vincent, A.J.B. (2004). Microstructural development in equiatomic multicomponent alloys. Materials Science and Engineering: A, 375–377, 213–218.

Chantrell, P., & Popper, P. (1964). Inorganic polymers for ceramics. In Special Ceramics 1964 (pp. 87–103). Academic Press. Colombo, P., Mera, G., Riedel, R., & Sorarù, G.D. (2013). Polymer-derived ceramics: 40 years of research and innovation in advanced ceramics. In R. Riedel, I-Wei Chen (Eds.), Ceramics Science and Technology (vol. 4: Applications, pp. 245–320). Wiley-VCH Verlag GmbH & Co. KGaA.

Cross, T.J., Raj, R., Cross, T.J., Prasad, S.V., & Tallant, D. R. (2006). Synthesis and tribological behavior of silicon oxycarbonitride thin films derived from poly(urea)methyl vinyl silazane. International Journal of Applied Ceramic Technology, 3(2), 113–126.

Cunningham, P., Cord, M., & Delany, S.J. (2008). Supervised learning. In M. Cord, P. Cunningham (Eds.), Machine Learning Techniques for Multimedia. Case Studies on Organization and Retrieval (pp. 21–49). Springer Berlin, Heidelberg.

Curtarolo, S., Setyawan, W., Hart, G.L.W., Jahnatek, M., Chepulskii, R.V., Taylor, R.H., Wang, S., Xue, J., Yang, K., Levy, O., Mehl, M.J., Stokes, H.T., Demchenko, D.O., & Morgan, D. (2012). AFLOW: An automatic framework for high-throughput materials discovery. Computational Materials Science, 58, 218–226.

Ding, H.Y., & Yao, K.F. (2013). High entropy Ti20Zr20Cu20Ni20Be20 bulk metallic glass. Journal of Non-Crystalline Solids, 364, 9–12.

Fu, S., Zhu, M., & Zhu, Y. (2019). Organosilicon polymer-derived ceramics: An overview. Journal of Advanced Ceramics, 8(4), 457–478.

González-Val, C., & Muíños-Landín, S. (2020). Generative design for Social Manufacturing. Zenodo.

Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. Arxiv.

Gorsse, S., Nguyen, M.H., Senkov, O.N., & Miracle, D.B. (2018). Database on the mechanical properties of high entropy alloys and complex concentrated alloys. Data in Brief, 21, 2664–2678.

Gulrajani, I., Ahmed, F., Arjovsky, M., Dumolin, V., & Courville, A.C. (2017). Improved training of wasserstein GANs. Arxiv.

Hart, G.L.W., Mueller, T., Toher, C., & Curtarolo, S. (2020). A roadmap for machine learning in alloy modelling. Bulletin of the American Physical Society, 65(1), X43.00012.

Hart, G.L.W., Mueller, T., Toher, C., & Curtarolo, S. (2021). Machine learning for alloys. Nature Reviews Materials, 6(8), 730–755.

Huang, W., Martin, P., & Zhuang, H.L. (2019). Machine-learning phase prediction of high-entropy alloys. Acta Materialia, 169, 225–236.

Kirklin, S., Saal, J.E., Meredig, B., Thompson, A., Doak, J.W., Aykol, M., Rühl, S., & Wolverton, C. (2015). The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies. Npj Computational Materials, 1(1),

Lee, S.Y., Byeon, S., Kim, H.S., Jin, H., & Lee, S. (2021). Deep learning-based phase prediction of high-entropy alloys: Optimization, generation, and explanation. Materials & Design, 197, 109260.

Li, L., Fang, Q., Li, J., Liu, B., Liu, Y., & Liaw, P. K. (2020). Lattice-distortion dependent yield strength in high entropy alloys. Materials Science and Engineering: A, 784, 139323.

Lin, Z., Khetan, A., Fanti, G., & Oh, S. (2018). PacGAN: The power of two samples in generative adversarial networks. Arxiv.

Martínez-Crespiera, S., Ionescu, E., Kleebe, H.-J., & Riedel, R. (2011). Pressureless synthesis of fully dense and crack-free SiOC bulk ceramics via photo-crosslinking and pyrolysis of a polysiloxane. Journal of the European Ceramic Society, 31(5), 913–919.

Mazheika, A., Wang, Y.-G., Valero, R., Viñes, F., Illas, F., Ghiringhelli, L.M., Levchenko, S. V., & Scheffler, M. (2022). Artificial-intelligence-driven discovery of catalyst genes with application to CO2 activation on semiconductor oxides. Nature Communications, 13(1), 419.

Menon, D.B., & Ranganathan, R. (2022). A generative approach to materials discovery, design, and optimization. ACS Omega, 7(30), 25958–25973.

Miracle, D.B., & Senkov, O.N. (2017). A critical review of high entropy alloys and related concepts. Acta Materialia, 122, 448–511.

Miracle, D.B., Miller, J.D., Senkov, O.N., Woodward, C., Uchic, M.D., & Tiley, J. (2014). Exploration and development of high entropy alloys for structural applications. Entropy, 16(1), 494–525.

Mirza, M., & Osindero, S. (2014). Conditional generative adversarial nets. Arxiv.

Mitchell, T., Buchanan, B., DeJong, G., Dietterich, T., Rosenbloom, P., & Waibel, A. (1990). Machine learning. Annual Review of Computer Science, 4, 417–433.

Patki, N., Wedge, R., & Veeramachaneni, K. (2016). The synthetic data vault. 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), 399–410.

Precker, C.E., Gregores Coto, A., & Muíños-Landín, S. (2021a). Materials for design open repository. High entropy alloys. Zenodo.

Precker, C.E., Gregores Coto, A., & Muíños-Landín, S. (2021b). Materials for design open repository. Polymer derived ceramics. Zenodo.

Riedel, R., Mera, G., Hauser, R., & Klonczynski, A. (2006). Silicon-based polymer-derived ceramics: Synthesis properties and applications – a review. Journal of the Ceramic Society of Japan, 114(1330), 425–444.

Saal, J.E., Kirklin, S., Aykol, M., Meredig, B., & Wolverton, C. (2013). Materials design and discovery with high-throughput density functional theory: the open quantum materials database (OQMD). JOM, 65(11), 1501–1509.

Shevlin, S., Castro, B., & Li, X. (2021). Computational materials design. Nature Materials, 20(6), 727–727.

Sorarù, G.D., Kundanati, L., Santhosh, B., & Pugno, N. (2018). Influence of free carbon on the Young’s modulus and hardness of polymer‐derived silicon oxycarbide glasses. Journal of the American Ceramic Society, 102(3), 907–913.

Sujith, R., Jothi, S., Zimmermann, A., Aldinger, F., & Kumar, R. (2021). Mechanical behaviour of polymer derived ceramics – a review. International Materials Reviews, 66(6), 426–449.

Tong, X., Liu, X., Tan, X., Li, X., Jiang, J., Xiong, Z., Xu, T., Jiang, H., Qiao, N., & Zheng, M. (2021). Generative models for de novo drug design. Journal of Medicinal Chemistry, 64(19), 14011–14027.

Tsai, M.-H., Tsai, R.-C., Chang, T., & Huang, W.-F. (2019). Intermetallic phases in high-entropy alloys: Statistical analysis of their prevalence and structural inheritance. Metals, 9(2), 247.

Vaidya, M., Muralikrishna, G.M., & Murty, B.S. (2019). High-entropy alloys by mechanical alloying: A review. Journal of Materials Research, 34(5), 664–686.

Verbeek, W. (1974). Production of shaped articles of homogeneous mixtures of silicon carbide and nitride. US Patent US3853567A.

Verbeek, W., & Winter, G. (1974). Formkoerper aus siliciumcarbid und verfahren zu ihrer herstellung. DE Patent, 2236078A1.

Vry, S., Roumanie, M., Laucournet, R., & Bernard-Granger, G. (2020). Transmission electron microscopy investigations on polysiloxane preceramic polymer pyrolyzed at high temperature in argon. Ceramics, 3(4), 421–427.

Wang, Z., Guo, S., & Liu, C. T. (2014). Phase selection in high-entropy alloys: from nonequilibrium to equilibrium. JOM, 66(10), 1966–1972.

Wang, X., Guo, W., & Fu, Y. (2021). High-entropy alloys: emerging materials for advanced functional applications. Journal of Materials Chemistry A, 9(2), 663–701.

Wen, Q., Yu, Z., & Riedel, R. (2020). The fate and role of in situ formed carbon in polymer-derived ceramics. Progress in Materials Science, 109, 100623.

Winter, G.D., Verbeek, W.D., & Mansmann, M.D. (1974). Formkoerper aus homogenen mischungen von siliciumcarbid und siliciumnitrid und verfahren zu ihrer herstellung. DE Patent, DE2243527A1.

Xu, L., Skoularidou, M., Cuesta-Infante, A., & Veeramachaneni, K. (2019). Modeling tabular data using conditional gan. Arxiv.

Yajima, S., Okamura, K., & Hayashi, J. (1975). Structural analysis in continuous silicon carbide fiber of high tensile strength. Chemistry Letters, 4(12), 1209–1212.

Yajima, S., Hasegawa, Y., Okamura, K., & Matsuzawa, T. (1978). Development of high tensile strength silicon carbide fibre using an organosilicon polymer precursor. Nature, 273(5663), 525–527.

Yeh, J.-W. (2013). Alloy design strategies and future trends in high-entropy alloys. JOM, 65(12), 1759–1771.

Yeh, J.-W. (2015). Physical metallurgy of high-entropy alloys. JOM, 67(10), 2254–2261.

Yeh, J.-W., Chen, S.-K., Lin, S.-J., Gan, J.-Y., Chin, T.-S., Shun, T.-T., Tsau, C.-H., & Chang, S.-Y. (2004). Nanostructured
high-entropy alloys with multiple principal elements: novel alloy design concepts and outcomes. Advanced Engineering Materials, 6(5), 299–303.

Zhang, Y., Yang, X., & Liaw, P. K. (2012). Alloy design and properties optimization of high-entropy alloys. JOM, 64(7), 830–838.

Zhou, Z., Zhou, Y., He, Q., Ding, Z., Li, F., & Yang, Y. (2019). Machine learning guided appraisal and exploration of phase design for high entropy alloys. Npj Computational Materials, 5(1), 128.