Computer Vision Assisted Decomposition Analysis of Atom Probe Tomography Data

13 (V,Al)N and 3 (Ti,Al)N APT reconstructions in .epos format with corresponding range files. Training data includes images and masks for 9 labeled (V,Al)N APT samples in h5 format, created by Janis A. Sälker from RWTH Aachen University. The image data has a shape of (2, number_of_slices, 608, 192), where 2 corresponds to V- and Al-contribution channels.

Use Cases

• Train semantic segmentation models based on the provided image and mask data.
• Develop decomposition analysis algorithms for APT reconstructions using the V- and Al-contribution channels.
• Benchmark computer vision methods for materials science applications using the labeled (V,Al)N samples.

Strengths

• Includes 13 (V,Al)N and 3 (Ti,Al)N APT reconstructions with corresponding range files.
• Provides training data with images and masks for 9 labeled APT samples.
• Image data structure is explicitly defined with shape (2, number_of_slices, 608, 192) for V and Al channels.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

RWTH Aachen University, Materials Chemistry

Collection Method

APT measurements performed using a CAMECA LEAP 4000X HR; training data created by Janis A. Sälker.