News

Results of Kaggle competition IceCube - Neutrinos in Deep Ice

News, Top |

The kaggle competition IceCube - Neutrinos in Deep Ice ended on April 19 2023, with over eleven thousand entries by 901 participants. 3 winners and 5 runner-ups have been selected.

The kaggle competition IceCube - Neutrinos in Deep Ice ended on April 19 2023, with over eleven thousand entries by 901 participants. During the three months competition phase this project attracted active participants from 74 countries, and overall counted 6460 registrants.

The leaderboard has since been verified and finalized, and the winners are announced:

Furthermore, the Early Sharing Prize ($5k) is awarded to “Datasaurus”, and 5x $1k are awarded to the best solution write-ups:

1. Place     2. Place     3. Place     4. Place     5. Place

 

Details on winning solutions:

The top 3 placements share in common, that they all apply so-called “transformers”, which is the same architectures that powers the latest generation of large language models such as chatGPT. This is a new technique used on IceCube data, and surpasses the quality of previous machine learning based reconstructions significantly.

All top 3 solutions are able to reconstruct the direction of “track” events (neutrino events that contain an elongated signature caused by a muon from the interaction) to sub-degree resolution. This likely opens new possibilities to apply these algorithms to vast numbers of events, if not the entire IceCube data stream at once. Such high precision was until now reserved for select neutrino event candidates that needed to be processed with computationally intensive methods, taking easily minutes to hours per event. In contrast, the methods developed during this kaggle competition are blazing fast, and can be applied to millions of events within just a few hours.

In the article from October 24, 2023, the three best solutions are described, and the data processing, architecture and training processes of these models are presented and compared.