A Classifier Framework for ALMA Bandpass Calibration Anomalies

Abstract

Bandpass calibration corrects instrumental responses across observing frequencies in interferometric radio observations, so the measured calibration solutions inherently contain spectral variation that varies with instrumental configurations and noise conditions. However, some signals contain anomalies, which if not caught can lead to poorly constructed science products. Observatory pipelines often use scalar metrics with individual, linear decision boundaries. Constructing a simple parametric model can be effective for observations with a relatively limited parameter space, but it becomes progressively less accurate as the parameter space expands. To address this challenge, we design a machine learning framework that treats anomaly identification as a supervised classification task and learns complex, non-linear decision boundaries across multiple features optimized for predictive performance. In particular, we use an XGBoost model that sits on top of several features and specialized scan statistic models to classify anomalies in amplitude solutions from ALMA bandpass calibrations. Trained on an extensive, quality-controlled ALMA dataset, this classifier framework leverages features derived from kernel-based scan statistics to characterize deviating spectral intervals, while remaining extensible to additional feature sets. This method substantially reduces misclassifications in bandpass anomaly detection compared to the current pipeline heuristics. By improving flagging decisions and calibration quality, this classifier framework provides a scalable supplement for observatory operations and is generalizable to next-generation radio facilities.

Detectability-Aware Screening of Post-Merger Gravitational-Wave Damping Anomalies in Real Detector Noise: A Graph-Spectral Approach with Empirical Null Calibration
Ruslan Alaskarov
arXiv1 Sep 2026PreprintCC BY 4.0Full textInstrumentation & methods Gravitation & general relativityarXiv
Space Phase-Locking Theory (SPLT) Part IV: Space Phase-Locking Theory (SPLT) Part IV: Algebraic Approach to Standard Model Anomalies and a Parameter-Free Framework
Kiman Jung
Zenodo (CERN European Organization for Nuclear Research)20 Oct 2026PreprintCC BY6 citedGeneral astronomyOpenAlex
Fast and accurate bandpass integration of complex SEDs with neural networks
L. A. Bianchi
arXiv6 Oct 2026PreprintCC BY 4.0Full textInstrumentation & methodsarXiv
Resolving the heart of the Wolf-Rayet binary Apep with ALMA
S. del Palacio, W. Vlemmings, M. Fernández-López +5
Astronomy & Astrophysics22 Oct 2026Peer-reviewedPublisher termsSolar & stellar physicsCrossref
Complex Organic Molecules in Protostars with ALMA Spectral Surveys (COMPASS). VIII. First interstellar detection of fully deuterated methyl cyanide
A. Belloche, J. K. Jorgensen, M. N. Drozdovskaya +12
Astronomy & Astrophysics31 Oct 2026Peer-reviewedPublisher termsSolar & stellar physicsCrossref

Cite

BibTeX RIS

BibTeX

@misc{xue2026classifier,
  title = {{A Classifier Framework for ALMA Bandpass Calibration Anomalies}},
  author = {Ci Xue and Brian S. Mason and Gazi A. Rakib and Tristan Ashton and Jeff M. Phillips and Ignacio Toledo and Ryan A. Loomis and Ilsang Yoon and John E. Hibbard and Omkar Bait and Eric J. Murphy},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.07357},
  eprint = {2610.07357},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.07357},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - A Classifier Framework for ALMA Bandpass Calibration Anomalies
AU  - Ci Xue
AU  - Brian S. Mason
AU  - Gazi A. Rakib
AU  - Tristan Ashton
AU  - Jeff M. Phillips
AU  - Ignacio Toledo
AU  - Ryan A. Loomis
AU  - Ilsang Yoon
AU  - John E. Hibbard
AU  - Omkar Bait
AU  - Eric J. Murphy
PY  - 2026
DA  - 2026/10/05
PB  - arXiv
DO  - 10.48550/arxiv.2610.07357
UR  - https://arxiv.org/abs/2610.07357
AB  - Bandpass calibration corrects instrumental responses across observing frequencies in interferometric radio observations, so the measured calibration solutions inherently contain spectral variation that varies with instrumental configurations and noise conditions. However, some signals contain anomalies, which if not caught can lead to poorly constructed science products. Observatory pipelines often use scalar metrics with individual, linear decision boundaries. Constructing a simple parametric model can be effective for observations with a relatively limited parameter space, but it becomes progressively less accurate as the parameter space expands. To address this challenge, we design a machine learning framework that treats anomaly identification as a supervised classification task and learns complex, non-linear decision boundaries across multiple features optimized for predictive performance. In particular, we use an XGBoost model that sits on top of several features and specialized scan statistic models to classify anomalies in amplitude solutions from ALMA bandpass calibrations. Trained on an extensive, quality-controlled ALMA dataset, this classifier framework leverages features derived from kernel-based scan statistics to characterize deviating spectral intervals, while remaining extensible to additional feature sets. This method substantially reduces misclassifications in bandpass anomaly detection compared to the current pipeline heuristics. By improving flagging decisions and calibration quality, this classifier framework provides a scalable supplement for observatory operations and is generalizable to next-generation radio facilities.
ER  -

Abstract

Related

Cite