Luis Martín-Encinar^1*, Daniele Lanzoni^2*, Andrea Fantasia², Fabrizio Rovaris², Roberto Bergamaschini^2*, Francesco Montalenti^2*

1 Dpto. de Electricidad y Electrónica, E.T.S.I. de Telecomunicación, Universidad de Valladolid, Paseo Belén 15, 47011, Valladolid, Spain

2 L-NESS and Dept. of Materials Science, University of Milano-Bicocca, Via R. Cozzi 55, 20125, Milano, Italy

* Corresponding authors emails: luis.martin.encinar@uva.es, d.lanzoni@campus.unimib.it, roberto.bergamaschini@unimib.it, francesco.montalenti@unimib.it

DOI10.24435/materialscloud:zn-b4 [version v1]

Publication date: Jan 05, 2024

How to cite this record

Luis Martín-Encinar, Daniele Lanzoni, Andrea Fantasia, Fabrizio Rovaris, Roberto Bergamaschini, Francesco Montalenti, Deep learning of surface elastic chemical potential in strained films: from statics to dynamics, Materials Cloud Archive 2024.3 (2024), https://doi.org/10.24435/materialscloud:zn-b4

Description

We develop a convolutional neural network (NN) approach able to predict the elastic contribution to chemical potential μₑ at the surface of a 2D strained film given its profile h(x). Arbitrary h(x) profiles are obtained by using a Perlin Noise generator and the corresponding μₑ profiles are calculated either by a Green's function approximation (GA) or by Finite Element Method (FEM). First, a large dataset is produced by exploiting the GA method and it is then used for the training of the NN model. The performance of the trained NN is extensively examined, demonstrating its ability to predict μₑ looking both to the training/validation set and to an additional testing set containing different profiles, including sinusoids, gaussians and sharp peaks never considered in the NN training. The NN is then applied to simulate the morphological evolution of strained Ge films, where the predicted μₑ at each integration timestep plays the role of driving force for material redistribution in competition with a surface energy term (proportional to local curvature) and eventually a wetting energy contribution. Both surface diffusion and evaporation/condensation dynamics are considered and the proposed NN approach is shown to well match the evolution expected by using GA. On this basis, a smaller dataset is built with μₑ profiles calculated by FEM and a new NN model is trained on it. Once again the trained NN-model returns reliable prediction of the FEM μₑ. The findings suggest that the proposed NN-based strategy can be used in replacement of the computationally intensive FEM calculations, enabling the simulation of larger scales and longer time scales untreatable by direct FEM calculation.

Materials Cloud sections using this data

Files

File name	Size	Description
README.txt MD5md5:bd5486347916e4cc267ee6fa4edd1665	413 Bytes	Description of the record content
GA.zip MD5md5:dca99298c18010a56ccc97d747e7110b	860.6 MiB	Dataset and test cases (statics and dynamics) with elastic chemical potential computed by Green's approximation
FEM.zip MD5md5:c96f28d2d280d220f56e78ffdd5ca248	957.0 MiB	Dataset and test cases with elastic chemical potential computed by Finite Element Method

License

Files and data are licensed under the terms of the following license: Creative Commons Attribution 4.0 International.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Keywords

deep learning elastic chemical potential surface evolution thin films