An Interpretable Machine Learning Model for Deformation of Multi-Walled Carbon Nanotubes
| Autor: | Shashank Pathrudkar, Susanta Ghosh, Upendra Yadav |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Functional principal component analysis
Basis (linear algebra) Artificial neural network Computer science business.industry Dimensionality reduction Nonlinear dimensionality reduction FOS: Physical sciences 02 engineering and technology Computational Physics (physics.comp-ph) 021001 nanoscience & nanotechnology Machine learning computer.software_genre 01 natural sciences Constraint (information theory) Rippling 0103 physical sciences Artificial intelligence 010306 general physics 0210 nano-technology business computer Physics - Computational Physics Interpretability |
| DOI: | 10.48550/arxiv.2011.08304 |
| Popis: | We present a novel interpretable machine learning model to accurately predict complex rippling deformations of Multi-Walled Carbon Nanotubes(MWCNTs) made of millions of atoms. Atomistic-physics-based models are accurate but computationally prohibitive for such large systems. To overcome this bottleneck, we have developed a machine learning model that consists of a novel dimensionality reduction technique and a deep neural network-based learning in the reduced dimension. The proposed nonlinear dimensionality reduction technique extends the functional principal component analysis to satisfy the constraint of deformation. Its novelty lies in designing a function space that satisfies the constraint exactly, which is crucial for efficient dimensionality reduction. Owing to the dimensionality reduction and several other strategies adopted in the present work, learning through deep neural networks is remarkably accurate. The proposed model accurately matches an atomistic-physics-based model while being orders of magnitude faster. It extracts universally dominant patterns of deformation in an unsupervised manner. These patterns are comprehensible and elucidate how the model predicts, yielding interpretability. The proposed model can form a basis for the exploration of machine learning toward the mechanics of one and two-dimensional materials. Comment: 6 pages, 9 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|