SEMINÁRIO DO DEPARTAMENTO DE ASTRONOMIA
Machine Learning for small bodies of the Solar System
a talk by Prof. Valerio Carruba (UNESP) - Remotely
Abstract:
The astronomical field is entering the big data science age as the number and complexity of astronomical datasets grow rapidly. The enormous size of contemporary astronomy datasets necessitates the use of procedures other than human researcher eye assessment. Machine learning (ML) is the study and development of algorithms that learn from data. The term artificial intelligence (AI) refers to the replication of human intelligence in computers, which are programmed to think and learn like humans. The main goal of this book was to collect what have been the efforts of several separate independent researchers and to combine them into a coherent picture. The book covers a range of fields, going from applications to asteroids, asteroid families, small bodies interacting with mean-motion and secular resonances, to comets, TNOs, and detection of moving objects. Apart from reviewing the state-of-the-art in the various fields covered by this book, we provide links for GitHub repositories with Jupyter notebooks carrying examples of codes used in areas such as identification of asteroids interacting with mean-motion or secular resonances, and detection and characterization of moving objects with ML.
Short-Bio:
Prof. Valerio Carruba has a Ph.D. in Astronomy from Cornell University and is currently an Associate Professor at the São Paulo State University (UNESP) in Brazil. He is one of the founders of the Machine Learning applied to Small Bodies (MASB) research group. He has published more than 80 papers, 19 of which are on applications of machine learning to dynamics of small bodies. His recent interests involve the use of deep learning for the identification of asteroids in secular resonant configurations and machine learning applied for asteroid families identification. Asteroid 10741 has been named Valeriocarruba by the International Astronomical Union. His recent paper Optimization of artificial neural networks models applied to the identification of images of asteroids’ resonant arguments recently won the CELMEC prize for "Innovative computational methods in Dynamical Astronomy".
Google Meet: https://meet.google.com/pcw-gmem-jyi
Link da transmissão: https://www.youtube.com/c/AstronomiaIAGUSP/live