Announcements of Opportunity
SURF@JPL: Announcements of Opportunity
Announcements of Opportunity are posted by JPL technical staff for the SURF@JPL 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!
**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.
<< Prev
Record
24 of
24
Back To List
| Project: |
Anomaly detection and algorithm development for Deep Space Network data
(JPL AO No. 15955)
|
||||||||
| Disciplines: | Data Science, Applied Math, Computer Science, Physics, Astronomy | ||||||||
| Mentor: |
Lisa Locke,
(JPL),
Lisa.S.Locke@jpl.nasa.gov, |
||||||||
| Background: |
NASA’s Deep Space Network (DSN) is the largest and most sensitive communication array in the world, and provides critical telemetry, command and control to spacecraft and international space assets beyond our solar system. With the increased data volume collected from missions, and aging of the antenna fleet, we have developed a program for advanced data analysis on operational track data, to identify problematic subsystems, and prioritize the antennas and subsystems in need of maintenance. There has been significant progress in developing analysis routines for antenna performance evaluation. Previous work was done to create machine learning analysis methods, but incomplete datasets detracted from the progress. Future work into this area would be beneficial. |
||||||||
| Description: |
The applicant will be tasked with investigating possible deep learning and machine learning approaches, and creatively applying machine learning techniques to current routines developed to analyze the enormous volume of multi-system multivariate data from the Deep Space Network. Using archived performance data to train and validate a machine learning algorithm using the classification or possibly other approaches, with known good and bad identifiers and known issues through the discrepancy report database. Application of the trained algorithm to incoming data can identify problems and anomalies in near real-time, predict failures, and forecast performance. Start date is flexible and extensions are negotiable. |
||||||||
| References: |
http://deepspace.jpl.nasa.gov/dsndocs/810-005/ https://descanso.jpl.nasa.gov/monograph/mono.html |
||||||||
| Student Requirements: |
Programming skills: one or more general-purpose programming languages including C/C++, Java, JavaScript, Lisp, Python Useful: database ideas for migration of large datasets, machine learning techniques, GIT Ability to work with other students and engineers; self-motivated; accountable. |
||||||||
| Location / Safety: | Project building and/or room locations: . Student will need special safety training: . | ||||||||
| Programs: |
This AO can be done under the following programs:
|
<< Prev Record 24 of 24 Back To List