arXiv subjects

Antoine Le Calloch

Publications and source records attributed to Antoine Le Calloch.

5 recordsLinked to original sources

arXiv2026

Catching Disguised Transients with ASTRANet: Anomaly-Aware Spectroscopic Classification and Conformal Calibration

Time-domain surveys discover thousands of transients per year, but the spectroscopic identification of rare and physically peculiar objects remains rate-limited by closed-set classifiers that confidently assign every input to a known class -- including spectra that genuinely belong to no known class. We present the \texttt{ASTRANet} framework, a confidence-aware infrastructure for spectroscopic transient classification built around three coupled modules: a hierarchical spectral classifier that operates directly on observer-frame spectra without requiring host-galaxy redshift or spectral phase as inputs; an anomaly detection layer (\texttt{ASTRANet-Sentinel}) that non-linearly combines $16$ embedding-space anomaly scores spanning four physically motivated families; and a conformal uncertainty quantification layer (\texttt{ASTRANet-CP}). We validate the framework on a held-out evaluation set of $289$ rare and out-of-taxonomy transients spanning $11$ classes deliberately excluded from training, chosen to span the full physical diversity of the rare-anomaly population: AGN-related outliers, GRB-related events, gap transients, novae, and peculiar supernovae. Through five astrophysically distinct failure modes of closed-set classifiers, we show that classifier-internal uncertainty and embedding-based anomaly detection are structurally complementary axes of confidence rather than alternative implementations of the same estimator. We further introduce AD-stratified Mondrian conformal prediction (AD-MCP) within \texttt{ASTRANet-CP}, achieving uniform conditional coverage across anomaly-score strata where vanilla Mondrian under-covers in the operational regime. This establishes the methodological infrastructure for confidence-aware spectroscopic discovery in the Vera C.\ Rubin Observatory era.

astro-ph.IM↗

arXiv2026

Leveraging Multimodality for Real-Time Classification of Transients and Variables found by the Zwicky Transient Facility

Modern time-domain surveys such as the Zwicky Transient Facility (ZTF) generate hundreds of thousands of alerts each night, making real-time decisions for follow-up observations a central challenge in time-domain astronomy. Robust early classification is crucial for making informed decisions, but is hindered by sparse light curves and degeneracies between classes. In this work, we leverage multimodality to substantially improve real-time classification and demonstrate the practicality of our approach by deploying our model on the ZTF alert stream. Building on the Online Ranked Astrophysical CLass Estimator (ORACLE), we introduce the ORACLE-2 models, which combine light curves, metadata, and images for real-time hierarchical classification. Using both real and simulated datasets, we show that incorporating additional modalities consistently improves classification performance. On observations from ZTF's Bright Transient Survey, our best-performing model, ORACLE-2 Omni, achieves a macro F1 score of 0.73 -- an improvement of up to 11% over models using light curves and metadata alone, and up to 40% over light-curve-only models, with the strongest gains realized at early times. To demonstrate applicability to the Legacy Survey of Space and Time, which will increase alert volume by more than an order of magnitude, we train a light curve + metadata variant on the simulated ELAsTiCC dataset. This model achieves a macro F1 score of 0.88, an improvement of up to 13% over the light-curve-only variant, matching the performance of other state-of-the-art models. Finally, we quantify the trade-offs between performance and throughput, identifying regimes where multimodal approaches offer the greatest benefit. These results show that combining multiple modalities improves early-time classification, enabling more effective triage of high-volume alert streams for current and future time-domain surveys.

astro-ph.IM↗

arXiv2026

BOOM and Babamul: a real-time, multi-survey, optical alert broker system operating at scale

With the arrival of ever higher throughput wide-field surveys and a multitude of multi-messenger and multi-wavelength instruments to complement them, software capable of harnessing these associated data streams is urgently required. To meet these needs, a number of community supported alert brokers have been built, currently focused on processing of Zwicky Transient Facility (ZTF; $\sim 10^5$-$10^6$ alerts per night) with an eye towards Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST; $\sim 2 \times 10^7$ alerts per night). Building upon the system that successfully ran in production for ZTF's first seven years of operation, we introduce BOOM (Burst & Outburst Observations Monitor), an analysis framework focused on real-time, joint brokering of these alert streams. BOOM harnesses the performance of a Rust-based software stack relying on a non-relational MongoDB database combined with a Valkey in-memory processing queue and a Kafka cluster for message sharing. With this system, we demonstrate feature parity with the existing ZTF system with a throughput $\sim 7 \times$ higher. We describe the workflow that enables the real-time processing as well as the results with custom filters we have built to demonstrate the system's capabilities. In conclusion, we present the development roadmap for both BOOM and Babamul - the public-facing LSST alert broker built atop BOOM - as we begin the Rubin era.

astro-ph.IM↗

arXiv2025

AppleCiDEr II: SpectraNet -- A Deep Learning Network for Spectroscopic Data

Time-domain surveys such as the Zwicky Transient Facility (ZTF) have opened a new frontier in the discovery and characterization of transients. While photometric light curves provide broad temporal coverage, spectroscopic observations remain crucial for physical interpretation and source classification. However, existing spectral analysis methods -- often reliant on template fitting or parametric models -- are limited in their ability to capture the complex and evolving spectra characteristic of such sources, which are sometimes only available at low resolution. In this work, we introduce SpectraNet, a deep convolutional neural network designed to learn robust representations of optical spectra from transients. Our model combines multi-scale convolution kernels and multi-scale pooling to extract features from preprocessed spectra in a hierarchical and interpretable manner. We train and validate SpectraNet on low-resolution time-series spectra obtained from the Spectral Energy Distribution Machine (SEDM) and other instruments, demonstrating state-of-the-art performance in classification. Furthermore, in redshift prediction tasks, SpectraNet achieves a root mean squared relative redshift error of 0.02, highlighting its effectiveness in precise regression tasks as well.

astro-ph.IM↗

arXiv2025

Applying multimodal learning to Classify transient Detections Early (AppleCiDEr) I: Data set, methods, and infrastructure

Modern time-domain surveys like the Zwicky Transient Facility (ZTF) and the Legacy Survey of Space and Time (LSST) generate hundreds of thousands to millions of alerts, demanding automatic, unified classification of transients and variable stars for efficient follow-up. We present AppleCiDEr (Applying Multimodal Learning to Classify Transient Detections Early), a novel framework that integrates four key data modalities (photometry, image cutouts, metadata, and spectra) to overcome limitations of single-modality classification approaches. Our architecture introduces (i) two transformer encoders for photometry, (ii) a multimodal convolutional neural network (CNN) with domain-specialized metadata towers and Mixture-of-Experts fusion for combining metadata and images, and (iii) a CNN for spectra classification. Training on ~ 30,000 real ZTF alerts, AppleCiDEr achieves high accuracy, allowing early identification and suggesting follow-up for rare transient spectra. The system provides the first unified framework for both transient and variable star classification using real observational data, with seamless integration into brokering pipelines, demonstrating readiness for the LSST era.

astro-ph.IM↗