CREST

Japan Science and Technology Agency Strategic Basic Research Programs
Strategic Basic Research Programs

[Innovative Measurement and Analysis] PRESTO Convergence Research (Year Started : 2026)

Daisuke Morikawa

Deep Learning-Driven QCBED for Multi-parameter Local Structural Analysis

Grant No.:JPMJCR26X9

Research Director : Daisuke Morikawa
Photo:Daisuke Morikawa

Assistant Professor
Institute of Multidisciplinary Research for Advanced Materials
Tohoku University

Collaborator
Kiyou Shibata Associate Professor
Institute of Materials and Systems for Sustainability
Nagoya University
Outline

This research aims to overcome the bottleneck of multi-parameter analysis in conventional QCBED by introducing Deep Learning (DL). Our objective is to develop a “Deep Learning-Driven QCBED Analysis Platform” that integrates DL-based advanced inverse problem analysis with conventional fitting techniques. Ultimately, we aim to establish an innovative measurement and analysis methodology capable of simultaneously decoupling and quantifying multiple local structural parameters at the nanoscale—such as atomic positions and polarization—that govern the performance of electronic device materials.

Page Top