Artificial Intelligence‐Assisted Workflow for Transmission Electron Microscopy: From Data Analysis Automation to Materials Knowledge Unveiling
Abstract
Abstract (Scanning) transmission electron microscopy ((S)TEM) has significantly advanced materials science but faces challenges in correlating precise atomic structure information with the functional properties of devices due to its time‐intensive nature. To address this, an analytical workflow is introduced for the holistic characterization, modelling, and simulation of device heterostructures. This workflow automates the experimental (S)TEM data analysis, providing an in‐depth characterization of crystallographic information, 3D orientation, elemental composition, and strain distribution. It reduces a process that typically takes days for a trained human into an automatic routine solved in minutes. Utilizing a physics‐guided artificial intelligence model, it generates representative descriptions of materials and samples. The workflow culminates in creating digital twins of systems limited with at least one axis of translational invariance –3D finite element and atomic models of millions of atoms–enabling simulations that provide crucial insights into device behavior in practical applications. Demonstrated with SiGe planar heterostructures for scalable spin qubits, the workflow links digital twins to theoretical properties, revealing how atomic structure impacts materials and functional properties such as spatially‐resolved phononic or electronic characteristics, or (inverse) spin orbit lengths. The versatility of the workflow is demonstrated through its application to a wide array of materials systems, device configurations, and sample morphologies.
Article Details
Authors (20)
Marc Botifoll
Ivan Pinto‐Huguet
Catalan Institute of Nanoscience and Nanotechnology – ICN2 (CSIC and BIST) Campus UAB Bellaterra Barcelona 08193 Catalonia Spain
Enzo Rotunno
CNR, Istituto Nanoscienze 2 , via G. Campi 213/a, 41125 Modena,
Thomas Galvani
Catalan Institute of Nanoscience and Nanotechnology – ICN2 (CSIC and BIST) Campus UAB Bellaterra Barcelona 08193 Catalonia Spain
Catalina Coll
Catalan Institute of Nanoscience and Nanotechnology – ICN2 (CSIC and BIST) Campus UAB Bellaterra Barcelona 08193 Catalonia Spain
Payam Habibzadeh Kavkani
CNR Istituto Nanoscienze Via Campi 213/A 41125 Modena Italy
Maria Chiara Spadaro
Catalan Institute of Nanoscience and Nanotechnology (ICN2), CSIC and BIST, Campus UAB, Bellaterra, 08193, Barcelona, Catalonia Spain
Yann‐Michel Niquet
Univ. Grenoble Alpes CEA IRIG‐MEM‐L Sim Grenoble 38054 France
Martin Børstad Eriksen
PIC, CIEMAT Campus UAB, Bellaterra Bellaterra 08193 Barcelona Catalonia Spain
Sara Martí‐Sánchez
Catalan Institute of Nanoscience and Nanotechnology – ICN2 (CSIC and BIST) Campus UAB Bellaterra Barcelona 08193 Catalonia Spain
Georgios Katsaros
Giordano Scappucci
Peter Krogstrup
NNF Quantum Computing Programme Niels Bohr Institute University of Copenhagen Copenhagen 1165 Denmark
Giovanni Isella
Andreu Cabot
Catalonia Institute for Energy Research-IREC, Sant Adrià de Besòs, Barcelona 08930, Spain
Gonzalo Merino
Pablo Ordejón
Catalan Institute of Nanoscience and Nanotechnology – ICN2 (CSIC and BIST) Campus UAB Bellaterra Barcelona 08193 Catalonia Spain
Stephan Roche
Catalan Institute of Nanoscience and Nanotechnology (ICN2), CSIC and BIST 1 , Campus UAB, Bellaterra, 08193 Barcelona,
Vincenzo Grillo
CNR Istituto Nanoscienze Via Campi 213/A 41125 Modena Italy
Jordi Arbiol
Catalan Institute of Nanoscience and Nanotechnology − ICN2 (CSIC and BIST), Campus UAB, Bellaterra, Barcelona, Catalonia 08193, Spain