Special Collection on ML4STEM in npj Computational Materials
I am thrilled to announce that I am co-editing a Special Collection for the prestigious journal npj Computational Materials titled: “Machine learning for automated experimentation in scanning transmission electron microscopy (STEM).”
This is a fantastic opportunity to be at the forefront of integrating cutting-edge machine learning (ML) with advanced microscopy techniques! We are exploring how ML can revolutionize experimental workflows in STEM, covering everything from real-time data analysis and automated workflow setups to autonomous decision-making using the latest ML methodologies.
The synergy between advancements in STEM hardware and the power of modern ML algorithms holds immense potential for breakthroughs in materials science and nanotechnology.
We welcome submissions covering a range of topics, including (but not limited to):
ML-Based Analysis: Novel methods for analyzing imaging and spectroscopic data from STEM, for both real-time and offline applications.
Automated STEM Workflows: Development of data pipelines, software/hardware ecosystems, and instrumentation for automated and autonomous STEM platforms.
STEM Simulations: Advanced simulations of STEM imaging and spectroscopy that can validate experimental results or train ML models for analysis tasks.
Autonomous Decision Making: Algorithms (like Bayesian optimization, reinforcement learning) enabling real-time, on-the-fly decision-making and control during STEM experiments for tasks such as materials manipulation or instrument control.
Theory-Experiment Coupling: Research exploring the integration of theoretical modeling and experimental work, especially in real-time scenarios.
I am honored to be editing this collection alongside Yimo Han and Rama Vasudevan.
Submission Deadline: March 17, 2026
We are incredibly excited about the potential of this field and look forward to receiving your groundbreaking contributions! Please visit the Collection Website for more details and submission guidelines: https://www.nature.com/collections/aejhegjahi/guest-editors
Let's push the boundaries of materials discovery together!