Frabjous: Deep Learning Fast Radio Burst Morphologies
Bibliographic record
Abstract
The increasing field of view of radio telescopes and improved data processing capabilities have led to a surge in the detection of Fast Radio Bursts (FRBs). The discovery rate of FRBs is already a few per day and is expected to increase rapidly with new surveys coming online. The growing number of events necessitates prioritized follow-up due to limited multi-wavelength resources, requiring rapid and automated classification. In this study, we introduce Frabjous, a deep learning framework for an automated morphology classifier with an aim towards enabling the prompt follow-up of anomalous and intriguing FRBs, and a comprehensive statistical analysis of FRB morphologies. Deep learning models require a large training set of each FRB archetype, however, publicly available data lacks sufficient samples for most FRB types. In this paper, we build a simulation framework for generating realistic examples of FRBs and train a network based on a combination of simulated and real data, starting with the CHIME/FRB catalog. Applying our framework to the first CHIME/FRB catalog, we achieve an overall classification accuracy of approximately 55%, well over a random multiclass classification rate of 20 % with five balanced classes during training. While this falls short of desirable performance, we critically discuss the limitations of our approach and propose potential avenues for improvement. Future work should explore strategies to augment training datasets and broaden the scope of FRB morphological studies, aiming for more accurate and reliable classification results.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".