Related papers: Fast Identification of Transients: Applying Expect…

Recent results from IceCube regarding TXS 0506+056 suggest the presence of neutrino flares that are not temporally coincident with a significant corresponding gamma ray flare. Such flares are particularly difficult to identify, as their…

For transient sources with timescales of 1-100 seconds, standardized imaging for all observations at each time step become impossible as large modern interferometers produce significantly large data volumes in this observation time frame.…

KM3NeT has recently reported the detection of a very high-energy neutrino event, while IceCube has previously set upper limits on the differential neutrino flux above 100 PeV but has yet to observe a neutrino event with an energy comparable…

The recent association between IC-170922A and the blazar TXS0506+056 highlights the importance of real-time observations for identifying possible astrophysical neutrino sources. Thanks to its near-100\% duty cycle, 4$\pi$ steradian field of…

Realtime analyses are necessary to identify the source of high energy neutrinos. As an observatory with a 4$\pi$ steradian field of view and near-100% duty cycle, the IceCube Neutrino Observatory is a unique facility for investigating…

We search for additional neutrino emission from the direction of IceCube's highest energy public alert events. We take the arrival direction of 122 events with a high probability of being of astrophysical origin and look for steady and…

We present a method for optimising experimental cuts in order to place the strongest constraints (upper limits) on theoretical signal models. The method relies only on signal and background expectations derived from Monte-Carlo simulations,…

Shortcut learning, i.e., a model's reliance on undesired features not directly relevant to the task, is a major challenge that severely limits the applications of machine learning algorithms, particularly when deploying them to assist in…

The new generation of powerful instruments is reaching sensitivities and temporal resolutions that will allow multi-messenger astronomy of explosive transient phenomena, with high-energy neutrinos as a central figure. We derive general…

The amount of observational data produced by time-domain astronomy is exponentially in-creasing. Human inspection alone is not an effective way to identify genuine transients fromthe data. An automatic real-bogus classifier is needed and…

Vision-based Transformer have shown huge application in the perception module of autonomous driving in terms of predicting accurate 3D bounding boxes, owing to their strong capability in modeling long-range dependencies between the visual…

We describe an algorithm for identifying point-source transients and moving objects on reference-subtracted optical images containing artifacts of processing and instrumentation. The algorithm makes use of the supervised machine learning…

In 2017, IceCube detected a high energy neutrino in coincidence with the blazar TXS 0506+056. In a follow up analysis of archival data, evidence for previous neutrino emission from the blazar during 2014-15 was found. In this analysis, we…

Large Transformer models have achieved state-of-the-art results in neural machine translation and have become standard in the field. In this work, we look for the optimal combination of known techniques to optimize inference speed without…

The ability to discover new transients via image differencing without direct human intervention is an important task in observational astronomy. For these kind of image classification problems, machine Learning techniques such as…

Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we demonstrate a graph-based approach that uses the…

Neutrino observations are crucial for multi-messenger astronomy, but currently limited by effective area and atmospheric background. However, while other telescopes must point their limited field of view, IceCube can perform full-sky…

Over the past decade wide-field optical time-domain surveys have increased the discovery rate of transients to the point that $\lesssim 10\%$ are being spectroscopically classified. Despite this, these surveys have enabled the discovery of…

The use of machine learning techniques has significantly increased the physics discovery potential of neutrino telescopes. In the upcoming years, we are expecting upgrade of currently existing detectors and new telescopes with novel…

Computationally inexpensive algorithm for detecting of dispersed transients has been developed using Cumulative Sums (CUSUM) scheme for detecting abrupt changes in statistical characteristics of the signal. The efficiency of the algorithm…