Real Time Adaptive Event Detection in Astronomical Data Streams: Lessons from the Very Long Baseline Array
A new generation of observational science instruments is dramatically increasing collected data volumes in a range of fields. These instruments include the Square Kilometre Array (SKA), Large Synoptic Survey Telescope (LSST), terrestrial sensor networks, and NASA satellites participating in "de...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Journal Article |
| Published: |
IEEE
2014
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/16875 |
| _version_ | 1848749302363455488 |
|---|---|
| author | Thompson, D. Burke-Spolaor, S. Deller, A. Majid, W. Palaniswamy, D. Tingay, Steven Wagstaff, K. Wayth, Randall |
| author_facet | Thompson, D. Burke-Spolaor, S. Deller, A. Majid, W. Palaniswamy, D. Tingay, Steven Wagstaff, K. Wayth, Randall |
| author_sort | Thompson, D. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | A new generation of observational science instruments is dramatically increasing collected data volumes in a range of fields. These instruments include the Square Kilometre Array (SKA), Large Synoptic Survey Telescope (LSST), terrestrial sensor networks, and NASA satellites participating in "decadal survey" missions. Their unprecedented coverage and sensitivity will likely reveal wholly new categories of unexpected and transient events. Commensal methods passively analyze these data streams, recognizing anomalous events of scientific interest and reacting in real time. We report on a case example: V-FASTR, an ongoing commensal experiment at the Very Long Baseline Array (VLBA) that uses online adaptive pattern recognition to search for anomalous fast radio transients. V-FASTR triages a millisecond-resolution stream of data and promotes candidate anomalies for further offline analysis. It tunes detection parameters in real time, injecting synthetic events to continually retrain itself for optimum performance. This self-tuning approach retains sensitivity to weak signals while adapting to changing instrument configurations and noise conditions. The system has operated since July 2011, making it the longest-running real time commensal radio transient experiment to date. |
| first_indexed | 2025-11-14T07:18:47Z |
| format | Journal Article |
| id | curtin-20.500.11937-16875 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T07:18:47Z |
| publishDate | 2014 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-168752017-09-13T15:44:15Z Real Time Adaptive Event Detection in Astronomical Data Streams: Lessons from the Very Long Baseline Array Thompson, D. Burke-Spolaor, S. Deller, A. Majid, W. Palaniswamy, D. Tingay, Steven Wagstaff, K. Wayth, Randall Time Series Analysis Real Time Machine Learning Radio Astronomy Pattern Recognition Fast Radio Transients A new generation of observational science instruments is dramatically increasing collected data volumes in a range of fields. These instruments include the Square Kilometre Array (SKA), Large Synoptic Survey Telescope (LSST), terrestrial sensor networks, and NASA satellites participating in "decadal survey" missions. Their unprecedented coverage and sensitivity will likely reveal wholly new categories of unexpected and transient events. Commensal methods passively analyze these data streams, recognizing anomalous events of scientific interest and reacting in real time. We report on a case example: V-FASTR, an ongoing commensal experiment at the Very Long Baseline Array (VLBA) that uses online adaptive pattern recognition to search for anomalous fast radio transients. V-FASTR triages a millisecond-resolution stream of data and promotes candidate anomalies for further offline analysis. It tunes detection parameters in real time, injecting synthetic events to continually retrain itself for optimum performance. This self-tuning approach retains sensitivity to weak signals while adapting to changing instrument configurations and noise conditions. The system has operated since July 2011, making it the longest-running real time commensal radio transient experiment to date. 2014 Journal Article http://hdl.handle.net/20.500.11937/16875 10.1109/MIS.2013.10 IEEE restricted |
| spellingShingle | Time Series Analysis Real Time Machine Learning Radio Astronomy Pattern Recognition Fast Radio Transients Thompson, D. Burke-Spolaor, S. Deller, A. Majid, W. Palaniswamy, D. Tingay, Steven Wagstaff, K. Wayth, Randall Real Time Adaptive Event Detection in Astronomical Data Streams: Lessons from the Very Long Baseline Array |
| title | Real Time Adaptive Event Detection in Astronomical Data Streams: Lessons from the Very Long Baseline Array |
| title_full | Real Time Adaptive Event Detection in Astronomical Data Streams: Lessons from the Very Long Baseline Array |
| title_fullStr | Real Time Adaptive Event Detection in Astronomical Data Streams: Lessons from the Very Long Baseline Array |
| title_full_unstemmed | Real Time Adaptive Event Detection in Astronomical Data Streams: Lessons from the Very Long Baseline Array |
| title_short | Real Time Adaptive Event Detection in Astronomical Data Streams: Lessons from the Very Long Baseline Array |
| title_sort | real time adaptive event detection in astronomical data streams: lessons from the very long baseline array |
| topic | Time Series Analysis Real Time Machine Learning Radio Astronomy Pattern Recognition Fast Radio Transients |
| url | http://hdl.handle.net/20.500.11937/16875 |