The research proposal aims to use machine learning, including large-scale language models, to analyze large datasets of smaller Solar System bodies from the upcoming Rubin Observatory Legacy Survey of Space and Time (LSST). The research will focus on three main areas: main-belt asteroids in resonances, asteroids co-orbital to terrestrial planets, and trans-Neptunian objects. Traditional orbital dynamics methods will be combined with machine learning techniques, such as convolutional neural networks and Vision Transformers, to classify and analyze these celestial bodies.
The candidate should have a solid background in dynamic astronomy and extensive experience in manipulating and analyzing astronomical data. Knowledge of Python programming and machine learning tools, deep learning, and large language models is desirable.
The fellow will be based at the Engineering College of the São Paulo State University (UNESP), in its Guaratinguetá campus, and will receive a post-doctoral fellowship from FAPESP, the São Paulo Research Foundation.
Candidates should send the following to [email protected] by October 15th 2025:
– A FAPESP CV Summary, as per fapesp.br/en/6351;
– Cover letter with a brief description of your interests and research experience.
The position is open to Brazilians and international applicants. The selected candidate will receive a FAPESP Post-Doctoral Fellowship worth R$ 12,570.00 per month for one year and a Technical Reserve equivalent to 10% of the annual fellowship amount.
More information about the fellowship is at: fapesp.br/oportunidades/8517.