Abstract
This paper describes the application of neural network approaches to the discovery of new materials exhibiting thermoelectric properties. Thermoelectricity is the ability of a material to convert energy from heat to electricity. At present, only few materials are known to have this property to a degree which is interesting for use in industrial applications like, for example, large-scale energy harvesting [3, 8]. We employ a standard neural network architecture with supervised learning on a training dataset representing materials and later predict the properties on a disjoint test set. At this proof of concept stage, both sets are synthetically generated with plausible values of the features. A substantial increase in performance is seen when utilising available physical knowledge in the machine learning model. The results show that this approach is feasible and ready for future tests with experimental laboratory data.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
United States Environmetal Protection Agency. https://www.epa.gov/chp/chp-benefits. Accessed 04 Apr 2019
Forman, C., Muritala, I., Pardemann, R., Meyer, B.: Estimating the global waste heat potential. Renew. Sustain. Energy Rev. 57, 1568–1579 (2016)
Gayner, C., Kar, K.: Recent advances in thermoelectric materials. Prog. Mater. Sci. 83, 330–382 (2016)
Løvvik, O.M., Berland, K.: Predicting the thermoelectric figure-of-merit from first principles. Mater. Today Proc. 5, 10227–10234 (2018)
Parr, R.: Density functional theory of atoms and molecules. In: Horizons of Quantum Chemistry, pp. 5–15. Springer (1980). https://doi.org/10.1007/978-94-009-9027-2_2
Petsagkourakis, I., Tybrandt, K., Crispin, X., Ohkubo, I., Satoh, N., Mori, T.: Thermoelectric materials and applications for energy harvesting power generation. Sci. Technol. Adv. Mater. 19(1), 836–862 (2018)
Schuch, N., Verstraete, F.: Computational complexity of interacting electrons and fundamental limitations of density functional theory. Nat. Phys. 5(10), 732 (2009)
Shi, X., Chen, L., Uher, C.: Recent advances in high-performance bulk thermoelectric materials. Int. Mater. Rev. 61(6), 379–415 (2016)
Sirusi, A., Ross, J.: Recent NMR studies of thermoelectric materials. In: Annual Reports on NMR Spectroscopy, vol. 92, pp. 137–198. Academic Press (2017)
Tabib, M.V., Løvvik, O.M., Johannessen, K., Rasheed, A., Sagvolden, E., Rustad, A.M.: Discovering thermoelectric materials using machine learning: insights and challenges. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11139, pp. 392–401. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01418-6_39
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Remonato, F., Løvvik, O.M., Flage-Larsen, E. (2019). Effectiveness of Neural Networks for Research on Novel Thermoelectric Materials. A Proof of Concept. In: Bach, K., Ruocco, M. (eds) Nordic Artificial Intelligence Research and Development. NAIS 2019. Communications in Computer and Information Science, vol 1056. Springer, Cham. https://doi.org/10.1007/978-3-030-35664-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-35664-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-35663-7
Online ISBN: 978-3-030-35664-4
eBook Packages: Computer ScienceComputer Science (R0)