The unprecedented depth, cadence, and volume of LSST data presents a unique opportunity for serendipitous discoveries by identifying rare or unexpected phenomena ('anomalies'), and will necessitate the application of clever analytical techniques borrowed from the field of data science. In this session we will discuss computational techniques to identify anomalies, and state-of-the-art applications of machine learning (ML) and artificial intelligence (AI) software.

Agenda:

• 10:30 - 10:40: Guillermo Cabrera-Vives
• 10:40 - 10:50: Oleksandra Razim
• 10:50 - 11:00: Siddharth Chaini
• 11:00 - 11:10: Willow Fox Fortino
• 11:10 - 11:20: Somayeh Khakpash
• 11:20 - 11:30: Peter Veres
• 11:30 - 11:32: Rodiat Ayinde
• 11:32 - 12:00: Andrés A. Plazas Malagón & Siddharth Chaini

Contributed talks:

• [7 + 3 min] S31: Oleksandra Razim - Searching for anomalous variability with LSST and friends
• [7 + 3 min] S63: Siddharth Chaini - Anomaly hunting with Distance Metrics for LSST
• [7 + 3 min] S68: Willow Fox Fortino - ABC-SN: A New Spectroscopic Supernova Classifier
• [7 + 3 min] S92: Peter Veres - Machine Learning Methods for Automated Interstellar Object Classification with LSST
• [7 + 3 min] S67: Somayeh Khakpash - Automatic generation of magnification maps for lensed quasars and supernovae
• [Poster Flash Talk] S61: Rodiat Ayinde - Application of Industry-Ready Computer Vision Tools to Develop Expectations for LSST

Invited talks:

• [10 min] Guillermo Cabrera-Vives - Machine Learning and Anomaly Detection in the ALeRCE broker 
• [20 min] Andrés A. Plazas Malagón - Tutorial: How to do machine learning with the Rubin Science Platform (RSP)

Go to the list of all contributed abstracts.