An automatic flake-search tool for 2D materials

Researchers at the Aachen Graphene & 2D Materials Center have released an open-source platform to automatically identify and classify exfoliated flakes of two-dimensional (2D) materials on a substrate, shortening one of the most time-consuming and tedious tasks in the study of 2D materials.

Exfoliated flakes of hexagonal Boron Nitride (hBN) on Si/SiO2 substrate. The red contour indicates a flake with a thickness of about 5 nanometers and size of approximately 50µm x 50µm.

In their 2013 perspective article on van der Waals heterostructures, Geim and Gregorieva introduced the effective analogy of 2D materials as atomic-sized Lego blocks. The analogy illustrates well not only the sheer variety of structures that can be realized by stacking different 2D materials, but also a common bottleneck in the fabrication process: finding the right piece. As any avid Lego builder knows, finding a piece of the right size and shape can take time and patience. The same is true in the 2D materials community, where researchers often spend hours at the microscope, manually scanning exfoliated 2D-material flakes to find a crystal with the desired properties.  The team of Prof. Christoph Stampfer at RWTH Aachen University has now developed an efficient tool to automatically detect and classify 2D material flakes and has made the source code openly available.

“Our goal was to develop a truly competitive alternative to the manual search by a patient and well-trained researcher,” says Jan-Lucas Uslu, who has been the main driving force behind the project. The fully automated workflow developed by Uslu and his colleagues starts at the very end of the exfoliation process, when the flakes are deposited on a silicon oxide substrate. Using classical machine learning models and a microscope with motorized scanning stage and motorized objective revolver, the system is able to reliably detect and classify all the flakes present on a substrate, indicating the number of layers of each flake, as well as its shape and dimensions. All of this information is then conveniently stored in an interactive database, along with images of the flakes taken at various resolutions. A Demo of the interactive database can be accessed here.

The automated flake search system has been tested in Stampfer’s lab for more than two years. “The effort to develop such a tool has already paid off,” says Stampfer. “Not only have we become much more efficient in assembling heterostructures, but there are also studies that we probably would have never started without a fast and efficient way to find flakes of the desired thickness.” One example is the systematic study of the dielectric screening in WS2-graphene heterostructures as a function of the thickness of the spacer layer, which was varied from one to 16 atomic layers of hBN – a daunting task without the flake-search tool.

The implementation of the automated flake search tool and the associated workflow have now been reported in the IOP journal Machine Learning: Science and Technology, while the source code has been made publicly available via GitHub in a package that includes both the control software and the detection algorithm and training routines, which can also be used as stand-alone software to identify flakes on manually captured images.  

In addition to the speed and reliability, one of the attractive features of the detection algorithm is that it can be trained on just a few images, allowing new materials to be quickly integrated into the workflow. “Since the detection is based on the color contrast of the materials, which is a physical property, the training could in principle be replaced by simulations.” says Uslu.

Overview of the workflow of the automated flake-search tool. Picture from the original manuscript by Uslu et al.

Bibliographic Information:

An open-source robust machine learning platform for real-time detection and classification of 2D material flakes
J.-L. Uslu, T. Ouaj, D. Tebbe, A. Nekrasov, J.H. Bertram, M. Schütte, K. Watanabe, T. Taniguchi, B. Beschoten, L. Waldecker, and C. Stampfer, Mach. Learn.: Sci. Technol. accepted (2024) (or: arXiv: 2306.14845)

A workshop in Aachen on “2D Materials for Future Electronics”

AMO GmbH and the Aachen Graphene & 2D Materials Center are organizing a two-day workshop on “2D Materials for Future Electronics”, in cooperation with RWTH Aachen University and the University of Wuppertal.

The workshop will take place on February 19-20, 2024 in the scenic lecture halls of the SuperC building, in Aachen.  The scope of the workshop is to discuss the opportunities offered by 2D materials for future electronics, as well as the challenges that still need to be solved to turn the scientific advancements of the field into marketable innovations.

The program will cover several facets of the field, including:

  • massive scaling and miniaturization (“2D materials for more Moore”)
  • flexible electronics and sensors (“2D materials for more than Moore”)
  • novel computing paradigms (“2D materials for neuromorphic computing”).

The workshop will also feature a special hybrid session dedicated to electronics based on transition metal dichalcogenide (TMDs) in cooperation with the 2D-Experimental Pilot Line.

Confirmed speakers:

  • Gianluca Fiori (Uni Pisa)
  • Michael Heuken (AIXTRON)
  • Andras Kis (EPFL)
  • Theresia Knobloch (TU Wien)
  • Karl Magnus Persson (VTT)
  • Dmitry Polyushkin (TU Wien)
  • Frank Schwierz (TU Illmenau)
  • Quentin Smets (imec)
  • Roman Sordan (Politecnico di Milano)
  • … more to come!

Original contributions by the participants in form of a poster are warmly welcome.

Participation to the workshop is free, but registration is mandatory due to the limited number of places available. The deadline for registration is February 10, 2024.

More information & registration

The workshop is organized with the financial support of the European Commission, through the projects ORIGENAL, MISEL2D-EPL, a nd AttoSwitch, and of the German Federal Ministry for Education and Research (BMBF) through the projects NeuroSys und NEUROTEC.

Scientific organizers: Max Lemme (AMO GmbH & RWTH Aachen University), Daniel Neumaier (University of Wuppertal & AMO GmbH), Zhenxing Wang (AMO GmbH) , Gordon Rinke (AMO GmbH)

First observation of coherent charge dynamics in graphene quantum dots

In a recent study published in Nature Communications, researchers from RWTH Aachen University and Forschungszentrum Jülich have reported the observation of coherent charge oscillations in bilayer graphene quantum dots. This marks a significant milestone on the way to spin and valley qubits in a two-dimensional material system.

Katrin Hecker (right), Christian Volk (left) and colleagues from RWTH Aachen University have realized the first “charge qubit” in bilayer graphene, marking a significant milestone on the way to spin and valley qubits in a two-dimensional material system. (Photo: Hubert Dulisch/RWTH Aachen University)
Continue reading “First observation of coherent charge dynamics in graphene quantum dots”

High quality hexagonal Boron Nitride – made in Aachen

Good news for the community working on two-dimensional materials in Europe: a team of researchers at RWTH Aachen University has successfully implemented the process for growing high-quality hexagonal Boron Nitride at atmospheric pressure and high temperature, increasing the resilience of the supply chain of this unique material.

Hexagonal Boron Nitride grown in Aachen: the growth process results in a continuous crystal-layer with crystal grains of the order of a few 100 µm.
Continue reading “High quality hexagonal Boron Nitride – made in Aachen”

A scalable pathway for the mechanical transfer of graphene grown by CVD 

Nowadays it is possible to grow high-quality graphene on large scale using chemical vapor deposition (CVD). What remains a major bottleneck for the industrialization of the material is the transfer of graphene from the growth substrate to a target one. A team of researchers from the University of Cambridge and RWTH Aachen University has now developed a methodology for optimizing simultaneously the growth and the transfer process, showing that it is possible to dry-transfer graphene with high-yield, if the crystallographic orientation of the growth surface is chosen appropriately.

Optical micrograph of star-shaped graphene flakes grown by CVD on copper.
(© Stampfer Lab, RWTH Aachen University) 
Continue reading “A scalable pathway for the mechanical transfer of graphene grown by CVD “

How to report and benchmark emerging field-effect transistors

One of the challenges encountered by research on novel electronic devices is to compare devices based on different materials in a consistent way. RWTH Professor Max Lemme and colleagues from USA, China, and Belgium have now proposed a set of clear guidelines for benchmarking key parameters and performance metrics of emergent field-effect transistors. The guidelines have been published as a Perspective Article in Nature Electronics.

Continue reading “How to report and benchmark emerging field-effect transistors”