Technical notes
Short reports on our methods, data and results. They are reviewed by members before publication but are not peer-reviewed papers.
-
ASRU-TN-2026-003
Classifying stars, emulsion defects and annotations on digitized photographic plates
We present a labeled set of 14,600 cutouts from 312 digitized DASCH plates and a classifier that sorts detections into stars, five kinds of defect, and handwritten annotations. The classifier agrees with human reviewers on 93 percent of held-out cutouts. We release the labels, the model, and a catalog of about 41,000 classified detections from 1,200 plates.
-
ASRU-TN-2026-002
trailmask: a lightweight model for segmenting satellite trails in wide-field images
trailmask is a small convolutional segmentation model that marks satellite trails in amateur wide-field images. Trained on 2,140 frames with 3,870 hand-labeled trails, version 0.1 finds 94 percent of trails in held-out test images with a precision of 91 percent, and processes a 24-megapixel frame in about 1.4 seconds on a laptop processor.
-
ASRU-TN-2026-001
Calibration, plate solving and quality checks for member-submitted images
We describe the first version of the ASRU member image pipeline, which takes raw frames and calibration frames from members’ own equipment and returns calibrated, astrometrically solved images with quality metrics and a source catalog. On a test set of 412 frames from nine setups, 371 frames (90 percent) were solved automatically.