physics.ins-detNov 18, 2026

4D-TEMPO: Differentiable 4D-STEM ptychography via fast Physics Optimizers

Authors: Ramani Duraiswami, Yichao Zhang

Organizations: Computer Science and UMIACS, University of Maryland, College Park · Materials Science and Engineering, University of Maryland, College Park

Abstract

Electron ptychography recovers atomic structure from 4D-STEM data: diffraction patterns at multiple positions of a scanned probe. Current codes reconstruct an image and read atoms off it, or fit atoms under an L1L_1 loss; neither gives per-atom uncertainty. We propose 4D-TEMPO, a differentiable physical renderer that fits the atoms, the microscope, and the detector directly to the recorded electron counts under a Poisson likelihood. The output is a list of atoms, each a Gaussian primitive with a 3D position, a thermal width, and a model-conditional error bar from the Fisher information. The Fisher information also conditions the solver, gives the dose (electrons per Å2^2) each parameter needs, and separates calibration from imaging. On a simulated WSe2_2 bilayer, starting from the published reconstruction, fitted atoms cut in-plane error by a third (3.2 vs. 4.8 pm) and depth error by 40-61% against its 3D peaks. Depth comes from multiple scattering into the dark field, the faint counts outside the direct beam. The two layers, 10×10\times closer than the depth of field, separate; per-atom depth then follows the layer geometry. When the model is well specified, the bars are calibrated (69% of position coordinates within 1σ1σ). On experimental WSe2_2, fitted atoms predict held-out patterns better than the three published codes we test. With free probe modes where atoms are incomplete, the same likelihood predicts best on all three held-out benchmarks, matches every WSe2_2 baseline in 5 min against up to 20.5 h, and passes torchslice at its released setting 180×\times sooner on PrScO3_3. Per-atom error bars, planned doses, and fast reconstruction point to low-dose, real-time 3D imaging of beam-sensitive and dynamic materials.

Figures & tables

Explore similar work

CardsList
  1. Real-Time Atomic-Resolution Electron Phase Imaging without Probe Calibration via Ptychography-Supervised Learning

    Sep 22, 2026H. Yue, C. -C. Chen, C. -N. Hsiao +4Supervised LearningElectron Microscopy

  2. Zero-Shot Cross-Material Ptychographic Phase Reconstruction Using Deep Learning

    Sep 12, 2026Wen-Chun Lin, Kuan-Peng Chen, Nan-Yow Chen +2Image ReconstructionScanning Transmission Electron Microscopy

  3. Gaussian Splatoms: Direct Atomic Structure Identification in Electron Tomography

    Nov 17, 2026Nalini Singh, Tiffany Chien, Cedric Lim +3Computed TomographyElectron Microscopy