# ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST

arXiv: https://arxiv.org/abs/2501.01496 · HTML: https://mlsanity.com/paper/2501.01496/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 41 references that are in the map.
- First posted on arXiv 2 Jan 2025.

## Builds on (most cited first, 5 of 5)

- [RAPID: Early Classification of Explosive Transients using Deep Learning](https://mlsanity.com/paper/1904.00014/) (2019)
- [A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients](https://mlsanity.com/paper/2103.12102/) (2021)
- [Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier](https://mlsanity.com/paper/2008.03309/) (2020)
- [Fink: early supernovae Ia classification using active learning](https://mlsanity.com/paper/2111.11438/) (2021)
- [A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients](https://mlsanity.com/paper/2403.14742/) (2024)

## Built on by (most cited first, 2 of 2)

- [StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars](https://mlsanity.com/paper/2510.06200/) (2025)
- [SELDON: Supernova Explosions Learned by Deep ODE Networks](https://mlsanity.com/paper/2603.04392/) (2026)

## Abstract (arXiv)

We present ORACLE, the first hierarchical deep-learning model for real-time, context-aware classification of transient and variable astrophysical phenomena. ORACLE is a recurrent neural network with Gated Recurrent Units (GRUs), and has been trained using a custom hierarchical cross-entropy loss function to provide high-confidence classifications along an observationally-driven taxonomy with as little as a single photometric observation. Contextual information for each object, including host galaxy photometric redshift, offset, ellipticity and brightness, is concatenated to the light curve embedding and used to make a final prediction. Training on ~0.5M events from the Extended LSST Astronomical Time-Series Classification Challenge, we achieve a top-level (Transient vs Variable) macro-averaged precision of 0.96 using only 1 day of photometric observations after the first detection in addition to contextual information, for each event; this increases to >0.99 once 64 days of the light curve has been obtained, and 0.83 at 1024 days after first detection for 19-way classification (including supernova sub-types, active galactic nuclei, variable stars, microlensing events, and kilonovae). We also compare ORACLE with other state-of-the-art classifiers and report comparable performance for the 19-way classification task, in addition to delivering accurate top-level classifications much earlier. The code and model weights used in this work are publicly available at our associated GitHub repository (https://github.com/uiucsn/ELAsTiCC-Classification).