I’m a postdoctoral researcher at Stanford working on machine learning for computational imaging and inverse problems in electron microscopy (4DSTEM, ptychography, Lorentz TEM).
My main interestas the moment include self-supervised learning, deep priors, physics-informed reconstruction, and open-source scientific software.

• ML for inverse problems in (S)TEM: reconstruction, phase retrieval, robust and quantitative analysis on real-world data
• Computational imaging: ptychography, 4D-STEM workflows
• Scientific Python + PyTorch; reproducible research software and tooling
• Magnetic materials / spin textures / vdW ferromagnets

Repo and tutorials

• Core developer for ML modules in a growing EM analysis toolkit
• Developed ML-enabled iterative ptychography methods and code
• Contributed to core infrastructure (data structures, visualization, utilities, configuration backend)
• Wrote tutorials and examples to help new users adopt the toolkit

Repo

• Sole author and maintainer of a widely adopted Python codebase for Lorentz TEM (LTEM) simulation and analysis
• Used by the LTEM community for simulation-assisted interpretation and quantitative analysis of magnetic textures

• Deep generative priors for robust and efficient electron ptychography (2025)
• Accelerating iterative ptychography with an integrated neural network (Journal of Microscopy, 2025)
• AI-enabled Lorentz microscopy for quantitative imaging of nanoscale magnetic spin textures (npj Comput. Mater., 2024)
• Understanding Complex Magnetic Spin Textures with Simulation-Assisted Lorentz Transmission Electron Microscopy (Phys. Rev. Appl., 2022)
  Full list at Google Scholar

• amccray@stanford.edu
• LinkedIn