Morphological evolution via surface diffusion learned by convolutional, recurrent neural networks: extrapolation and prediction uncertainty
| العنوان: | Morphological evolution via surface diffusion learned by convolutional, recurrent neural networks: extrapolation and prediction uncertainty |
|---|---|
| المؤلفون: | Daniele Lanzoni, Marco Albani, Roberto Bergamaschini, Francesco Montalenti |
| المساهمون: | Lanzoni, D, Albani, M, Bergamaschini, R, Montalenti, F |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | Condensed Matter - Materials Science, Cahn-Hilliard, Physics and Astronomy (miscellaneous), Condensed Matter - Mesoscale and Nanoscale Physics, Recurrent Neural Network, Materials Science (cond-mat.mtrl-sci), FOS: Physical sciences, Convolutional Neural Network, Computational Physics (physics.comp-ph), Machine Learning, Surface, Mesoscale and Nanoscale Physics (cond-mat.mes-hall), Prediction uncertainty, General Materials Science, Phase Field, Physics - Computational Physics |
| الوصف: | We use a Convolutional Recurrent Neural Network approach to learn morphological evolution driven by surface diffusion. To this aim we first produce a training set using phase field simulations. Intentionally, we insert in such a set only relatively simple, isolated shapes. After proper data augmentation, training and validation, the model is shown to correctly predict also the evolution of previously unobserved morphologies and to have learned the correct scaling of the evolution time with size. Importantly, we quantify prediction uncertainties based on a bootstrap-aggregation procedure. The latter proved to be fundamental in pointing out high uncertainties when applying the model to more complex initial conditions (e.g. leading to splitting of high aspect-ratio individual structures). Automatic smart-augmentation of the training set and design of a hybrid simulation method are discussed. 11 pages, 7 figures |
| وصف الملف: | ELETTRONICO |
| اللغة: | English |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f1a90411b127a6317ca619be4723c620Test http://arxiv.org/abs/2206.08110Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....f1a90411b127a6317ca619be4723c620 |
| قاعدة البيانات: | OpenAIRE |
| الوصف غير متاح. |