Fully Automated Identification of Two-Dimensional Material Samples

Thin nanomaterials are key constituents of modern quantum technologies and materials research. The identification of specimens of these materials with the properties required for the development of state-of-the-art quantum devices is usually a complex and tedious human task. In this work, we provide a neural-network-driven solution that allows for accurate and efficient scanning, data processing, and sample identification of experimentally relevant two-dimensional materials. We show how to approach the classification of imperfect and imbalanced data sets using an iterative application of multiple noisy neural networks. We embed the trained classifier into a comprehensive solution for end-to-end automatized data processing and sample identification.

[1]  Eric A. Wan,et al.  Neural network classification: a Bayesian interpretation , 1990, IEEE Trans. Neural Networks.

[2]  T. Ihn,et al.  Electrostatically Induced Quantum Point Contacts in Bilayer Graphene. , 2017, Nano letters.

[3]  K. Shepard,et al.  Boron nitride substrates for high-quality graphene electronics. , 2010, Nature nanotechnology.

[4]  Recent progress in the assembly of nanodevices and van der Waals heterostructures by deterministic placement of 2D materials. , 2017, Chemical Society reviews.

[5]  M. Prato,et al.  Science and technology roadmap for graphene, related two-dimensional crystals, and hybrid systems. , 2015, Nanoscale.

[6]  Roger G. Melko,et al.  Machine learning phases of matter , 2016, Nature Physics.

[7]  A. Neto,et al.  Making graphene visible , 2007, Applied Physics Letters.

[8]  D. Graf,et al.  Tuning superconductivity in twisted bilayer graphene , 2018, Science.

[9]  X. Duan,et al.  Van der Waals heterostructures and devices , 2016 .

[10]  Jürgen Schmidhuber,et al.  Multi-column deep neural network for traffic sign classification , 2012, Neural Networks.

[11]  Penghui Li,et al.  Rapid identification of two-dimensional materials via machine learning assisted optic microscopy , 2019, Journal of Materiomics.

[12]  Madan Dubey,et al.  Two-dimensional material nanophotonics , 2014, 1410.3882.

[13]  P. Avouris,et al.  Photodetectors based on graphene, other two-dimensional materials and hybrid systems. , 2014, Nature nanotechnology.

[14]  A. Ferrari,et al.  Graphene Photonics and Optoelectroncs , 2010, CLEO 2012.

[15]  SUPARNA DUTTASINHA,et al.  Van der Waals heterostructures , 2013, Nature.

[16]  Giuseppe Iannaccone,et al.  Electronics based on two-dimensional materials. , 2014, Nature nanotechnology.

[17]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[18]  Hua Zhang,et al.  Rapid and reliable thickness identification of two-dimensional nanosheets using optical microscopy. , 2013, ACS nano.

[19]  Jed I. Ziegler,et al.  Bandgap engineering of strained monolayer and bilayer MoS2. , 2013, Nano letters.

[20]  Satoru Masubuchi,et al.  Classifying optical microscope images of exfoliated graphene flakes by data-driven machine learning , 2019, npj 2D Materials and Applications.

[21]  K. Novoselov,et al.  2D materials and van der Waals heterostructures , 2016, Science.

[22]  David J. Schwab,et al.  A high-bias, low-variance introduction to Machine Learning for physicists , 2018, Physics reports.

[23]  Makoto Yamada,et al.  Deep-learning-based quality filtering of mechanically exfoliated 2D crystals , 2019, npj Computational Materials.

[24]  Aurélien Géron,et al.  Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems , 2017 .

[25]  L. Lauhon,et al.  Emerging device applications for semiconducting two-dimensional transition metal dichalcogenides. , 2014, ACS nano.

[26]  Weisheng Zhao,et al.  Intelligent identification of two-dimensional nanostructures by machine-learning optical microscopy , 2018, Nano Research.

[27]  Takashi Taniguchi,et al.  Unconventional superconductivity in magic-angle graphene superlattices , 2018, Nature.

[28]  Sotiris B. Kotsiantis,et al.  Supervised Machine Learning: A Review of Classification Techniques , 2007, Informatica.

[29]  Takashi Taniguchi,et al.  Hunting for monolayer boron nitride: optical and Raman signatures. , 2011, Small.

[30]  Vijay Vasudevan,et al.  Learning Transferable Architectures for Scalable Image Recognition , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[31]  Kenji Watanabe,et al.  Deep-learning-based image segmentation integrated with optical microscopy for automatically searching for two-dimensional materials , 2020, npj 2D Materials and Applications.

[32]  Werner Wegscheider,et al.  Automated Tuning of Double Quantum Dots into Specific Charge States Using Neural Networks , 2019 .

[33]  T. Ihn,et al.  Transport Through a Network of Topological Channels in Twisted Bilayer Graphene. , 2018, Nano letters.

[34]  Qing Hua Wang,et al.  Electronics and optoelectronics of two-dimensional transition metal dichalcogenides. , 2012, Nature nanotechnology.

[35]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[36]  T. Ihn,et al.  Coupled Quantum Dots in Bilayer Graphene. , 2018, Nano letters.

[37]  CireşAnDan,et al.  2012 Special Issue , 2012 .

[38]  Alain C. Diebold,et al.  Spectroscopic imaging ellipsometry for automated search of flakes of mono- and n-layers of 2D-materials , 2017 .

[39]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[40]  C. K. Andersen,et al.  Quantum parameter estimation with a neural network , 2017, 1711.05238.

[41]  T. Ihn,et al.  Spin and Valley States in Gate-Defined Bilayer Graphene Quantum Dots , 2018, Physical Review X.

[42]  Takashi Taniguchi,et al.  Autonomous robotic searching and assembly of two-dimensional crystals to build van der Waals superlattices , 2018, Nature Communications.