The expected wealth of data from the Rubin Observatory requires the developments of new approaches and algorithms to enable its scientific goals. Machine learning (ML) will likely be important for addressing challenges at each stage of the pipeline – from data processing to science results. In this session, we want to bring together different members of the Rubin community to prepare for the use of ML with Rubin Observatory’s data. 

This session will start with talks about current or planned use of ML with Rubin data by the community and within the Rubin project. Most of the session will then be dedicated to a discussion, based on the talks that provide practical examples. The discussion will be centered around the following questions: what are the current and planned use of ML with Rubin data? What computing resources will be needed to enable ML with Rubin data? How will the ML models and training set be stored and accessed? How will synergies with other surveys such as Euclid, Roman, JWST be used when developing ML algorithms for Rubin? 

A great outcome of this session will be to identify common needs and solutions for ML applications with Rubin data, and to brainstorm useful standard practices.

Slides: https://docs.google.com/presentation/d/19v-1i_tpOZnJeFWjmd6FerhMqxJfBxlb...

Zoom: https://stanford.zoom.us/j/9036647806?pwd=cjlxNzQvTDZuTDRDamlBZWtoUGxtZz09

Contributed Talks

The Arrival of the Transformers for Advanced Analysis of Alert Streams (Guillermo Cabrera-Vives)
Transformers are deep learning architectures that have shown to reach state-of-the-art performances across various domains. They were originally conceived for natural language processing, but recently the have been used for images, tabular data, and time series, among others. In this talk we will review the recent advances of transformers when applied to the characterization of alert streams, and how they have outpermorfed previous approaches. Transformers have become the new state-of-the-art and will play a key role in analizing data from the Vera C. Rubin Observatory and its Legacy Survey of Space and Time (LSST), propelling us towards new frontiers in data analysis and discovery.

Talk by Nima Sedaghat

Talk by Alex Malz

Talk by Simona Mei