Announcements of Opportunity
SURF: Announcements of Opportunity
Below are Announcements of Opportunity posted by Caltech faculty and JPL technical staff for the SURF program.
Each AO indicates whether or not it is open to non-Caltech students. If an AO is NOT open to non-Caltech students, please DO NOT contact the mentor.
Announcements of Opportunity are posted as they are received. Please check back regularly for new AO submissions! Remember: This is just one way that you can go about identifying a suitable project and/or mentor. Click here for more tips on finding a mentor.
Announcements for external summer programs are listed here.
New for 2021: Students applying for JPL projects should complete a SURF@JPL application instead of a "regular" SURF application.
Students pursuing opportunities at JPL must be
U.S. citizens or U.S. permanent residents.
|Project:||Using Machine Learning to Identify Compact Sources for Astrometry in the Next Generation of Surveys|
|Disciplines:||Astronomy, Computation and Neural Systems|
|Mentor:||Andreas Faisst, Faculty/Staff, (PMA), email@example.com|
|Mentor URL:||https://sites.astro.caltech.edu/~afaisst/ (opens in new window)|
|Background:||Surveys with the next generation of telescopes (such as Rubin/LSST, Roman, or Euclid) rely on a statistically accurate identification of stars and compact sources. On one hand, stars are necessary for proper astrometric alignment, which is crucial for the joint cataloging of datasets from these various missions across a large range of wavelengths, seeing conditions and time intervals. Furthermore, proper alignment is essential to search for asteroids and other moving objects in the sky. On the other hand, the identification of faint stars and the measurement of their proper motion over time from different datasets itself builds a strong science case for the study of stellar streams in our galaxy and/or kinematics of our Galaxy and nearby galaxies.|
|Description:||We seek a student as part of our Joint Survey Processing (JSP) group to implement and test a machine learning framework to identify isolated and unsaturated compact objects in future datasets based. The framework would use as input images cutouts as well as other measurements provided in catalogs (e.g. size, brightness, etc). The goal is to train this framework and perform various tests using realistic simulated images from Rubin/LSST, Euclid, and Roman (which will be created as the first part of the project). The trained model will then be tested on real data on the COSMOS field, which is the closest to future combined ground and space-based datasets.|
|Student Requirements:||Familiarity with programming in Python. Basic knowledge of machine learning preferred.|
This AO can be done under the following programs:
<< Prev Record 13 of 69 Next >> Back To List