SURF: Announcements of Opportunity
Below are Announcements of Opportunity posted by Caltech faculty and JPL technical staff for the SURF program. Additional AOs for the Amgen Scholars program can be found here.
Specific GROWTH projects being offerred for summer 2017 can be found here.
Students pursuing opportunities at JPL must be U.S. citizens or U.S. permanent residents.
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.
Announcements for external summer programs are listed here.
|Project:||Designing and Identifying Features for Classification|
|Disciplines:||Data Science, Astrophysics|
|Mentor:||Ashish Mahabal, Sr. Research Scientist, (PMA), email@example.com|
|Mentor URL:||http://www.astro.caltech.edu/~aam (opens in new window)|
|Background:||In the last several years the field of astronomy has moved from taking digital pictures to taking digital movies of large parts of the sky. We now routinely see several objects with large change in brightness over short periods of time. As Catalina Real-time Transient Survey, take 2 (CRTS II), the Zwicky Transient Factory (ZTF) start operating we expect the transient rates to ramp up. In a few years the rates will go up by orders of magnitude as the Large Synoptic Survey Telescope (LSST) starts operating. Identifying the rare objects from millions of run-of-the-mill objects will be required.|
The path to identifying rare objects includes generating good priors for different types of objects, and identifying the strengths of different surveys through the spacing of their observations (cadence), filters used (wavelength range), light collected (aperture) etc. This, in combination with expected features for different classes can lead to the objects being identified through the implementation of machine learning workflows.
The work will involve a combination of transfer learning (e.g. domain adaptation), deep learning (either images, feature sets or both) in order to map different datasets, and separate classes.
Deep Learning: http://deeplearning.net/tutorial/
Transfer Learning: https://en.wikipedia.org/wiki/Inductive_transfer
Proficiency in python, conversant with statistics basics, deep learning, knowledge about linux/unix, git and related software engineering techniques. Basic astronomy knowledge will be a plus.
This AO can be done under the following programs:
<< Prev Record 60 of 114 Next >> Back To List