The LSSTC Data Science Fellowship program is a two year training program, designed to teach the skills required for LSST (Large Synoptic Survey Telescope) science that are not easily addressed by current astrophysics graduate programs. The program consists of three one-week schools per year over two years.
The first LSSTC DSFP session was August 1-5, 2016. The second session is January 23-27, 2017.
Exact dates for future sessions are TBD, but sessions will take place roughly every few months.
The first DSFP session was held in Chicago in the first week of August 2016. The second session will be held at the California Institute of Technology the last week of January 2017. Subsequently, we plan to open applications for LSST member institutions to host future sessions, so the program moves around over the course of the two year duration.
The LSSTC DSFP curriculum is being developed as an open source project, so classwork and related products (e.g. iPython notebooks for exercises) will be available to the community. Each session will focus on balancing informational talks with hands-on exercises.
Here is a broad list of topics that will be covered by the DSFP:
- Software engineering: building code repositories; object oriented programming; version control/GitHub; issue tracking; unit tests; continuous integration.
- Statistics: regression; frequentist vs. Bayesian methods; Gaussian processes; generative models; hierarchical models; missing information and selection effects.
- Machine learning: unsupervised methods; including density estimation, anomaly detection, feature extraction, and clustering techniques; supervised methods; end-to-end automated classification models; deep neural networks.
- Scalable programming and data management: parallel programming; databases; software profiling; cloud computing.
- Time series analysis: understanding variable sources with incomplete and noisy sampling; measures of periodicity; Gaussian processes; the LSST alert stream.
- Image processing: noisy astronomical detectors; processing pipelines; position, flux, and shape measurements; hands-on experience with the LSST image processing software stack.
- Visualization and communication: visualization of large dimensional data sets; interactive visualization for exploration; visual hierarchies; the effective use of space, color, contrast, and textures.
- Science communication: understanding your audience; effective body language for communication; presentation design principles; using data to tell a story.
Thanks to the generosity of the LSSTC, we can provide support for students to attend. The level of support will depend to a certain extent on demand, but we anticipate that the program will be free or nearly free (including travel and lodging) for students.
The only prerequisite is that students must be enrolled in an accredited graduate program. The program will be taught exclusively in the Python programming language, though prior knowledge of the language is not required. If you are not familiar with Python, don't worry-- an offline training course will be provided prior to the LSSTC DSFP sessions.
We are aiming for a class size of approximately 15-20 students.
With a new generation of ground and space-based surveys generating petabytes of data per year, together with the increasing complexity of data coming from these instruments, astrophysics is becoming ever more dependent on developments in computing. There is, however, a disconnect between the skills that are needed for an era rich in data and those that we teach to incoming graduate students and early-career postdocs. The DSFP was created to bridge this gap and provide a supplemental educational program to prepare early-career scientists for data-rich astronomy.
- Director: Dr. Lucianne Walkowicz (The Adler Planetarium)
- Deputy Director: Dr. Vicky Kalogera (CIERA/Northwestern)
- Director of Program Development and Communications: Dr. Adam Miller (CIERA/The Adler Planetarium)
- DSFP Leadership Council: Dr. Chris Lintott (Oxford); Dr. Andrew Connoly (UW); Dr. Zeljko Ivezic (UW); Dr. Phil Marshall (SLAC/Stanford); Dr. Mario Juric (LSST); Dr. Robert Lupton (Princeton)
- Administrative Assistant: Katherine Lamb
- Website: Lisa Raymond (Created by Gretchen Oehlschlager)
- Graphic Designer: Frank Okay
The LSSTC DSFP is made possible by the generous support of the LSST Corporation, the Data Science Initiative (DSI) at Northwestern, and CIERA.
You can apply using this form, or by clicking the "Apply Here" link at the top of this webpage.
The LSST DSFP application period has closed for this cycle. Stay tuned for more information!
Yes. While there are many single-serving schools that offer skill development in astronomy, the DSFP is intended as a true supplement to graduate education. Commitment to the full program allows students to not only study these topics in far greater depth, but to foster new collaborations and professional networks in the process.
Students are welcome to apply at any point in their graduate career.
Yes! We will be accepting applications for the next student cohort in 2017.
Students must attend all sessions, so if you are unavailable during this first session, we recommend you wait and apply during the next round of admissions (which will be in 2017).
For additional questions about the program, please contact:
Dr. Lucianne Walkowicz, LSSTC DSFP Director: LWalkowicz AT adlerplanetarium DOT org
Dr. Adam Miller, LSSTC DSFP Director of Program Development and Communications: amiller AT northwestern DOT edu
Data Science Programming Boot Camps
The LSSTC Data Science Fellowship is partly supported by the Data Science Seed Funding Program
Members of the LSST team gather to celebrate the successful casting
of the telescope's 27.5-foot-diameter mirror blank.