The primary challenge in the study of explosive astrophysical transients is their detection and characterization using multiple messengers. For this purpose, we have developed a new data-driven discovery framework, based on deep learning. We demonstrate its use for searches involving neutrinos, optical supernovae, and gamma-rays. We show that we can match or substantially improve upon the performance of state-of-the-art techniques, while significantly minimizing the dependence on modeling and on instrument characterization. Particularly, our approach is intended for near- and real-time analyses, which are essential for effective follow-up of detections. Our algorithm is designed to combine a range of instruments and types of input data, representing different messengers, physical regimes, and temporal scales. The methodology is optimized for agnostic searches of unexpected phenomena, and has the potential to substantially enhance their discovery prospects.

中文翻译：

---

数据驱动的多信使瞬态检测

研究爆炸性天体物理瞬变的主要挑战是使用多个信使对它们进行检测和表征。为此，我们基于深度学习开发了一个新的数据驱动的发现框架。我们展示了其在涉及中微子，光学超新星和伽玛射线的搜索中的用途。我们证明，我们可以在最先进技术的性能上与之匹配或大大提高，同时极大地减少了对建模和仪器表征的依赖。特别地，我们的方法旨在用于近距离和实时分析，这对于有效跟踪检测至关重要。我们的算法旨在结合各种工具和各种类型的输入数据，分别代表不同的信使，物理状态和时间尺度。