Root cause analysis for space weather events

1. A method for preventing spacecraft damage, comprising:

identifying a space weather event that corresponds to a spacecraft system failure, including identifying time periods of system failure in a set of time series data from respective sensors;

determining a spacecraft system that causes the spacecraft system failure, triggered by the space weather event;

performing a corrective action on the determined spacecraft system to prevent spacecraft system failures from being triggered by future space weather events.

2. The method of claim 1 , wherein determining a spacecraft system that causes the spacecraft system failure further includes identifying time periods of normal operation before respective periods of system failure.

3. The method of claim 2 , wherein determining a spacecraft system that causes the spacecraft system failure further includes selecting representative segments of each time period of normal operation based on distances between a respective time period of system failure and segments of the time period of normal operation.

4. The method of claim 3 , wherein the distances are calculated according to a metric selected from the group consisting of Euclidean distance, cosine distance, and dynamic time warping distance.

5. The method of claim 1 , wherein determining a spacecraft system that causes the spacecraft system failure includes clustering time series according to similarity of the respective time series to form attribute clusters.

6. The method of claim 5 , wherein determining a spacecraft system that causes the spacecraft system failure further includes ranking representative time segments from each cluster according to how uniqueness of the respective representative time segments.

7. The method of claim 5 , wherein the similarity of time series is determined according to a Pearson correlation coefficient.

8. The method of claim 1 , wherein determining a spacecraft system that causes the spacecraft system failure further includes selecting a group of sensors associated with a highest-ranked representative time segment.

9. The method of claim 1 , wherein the corrective action is selected from the group consisting of shielding the determined system and turning off the system in advance of predicted adverse space weather.

10. A system for preventing spacecraft damage, comprising:

a hardware processor;

a memory, coupled to the hardware processor, that stores executable program code that, when executed by the hardware processor, causes the hardware processor to to identify a space weather event that corresponds to a spacecraft system failure including identification of time periods of system failure in a set of time series data from respective sensors, to determine a spacecraft system that causes the spacecraft system failure, triggered by the space weather event, and to perform a corrective action on the determined spacecraft system to prevent spacecraft system failures from being triggered by future space weather events.

11. The system of claim 10 , wherein the task manager is further configured to identify time periods of normal operation before respective periods of system failure.

12. The system of claim 11 , wherein the task manager is further configured to select representative segments of each time period of normal operation based on distances between a respective time period of system failure and segments of the time period of normal operation.

13. The system of claim 12 , wherein the distances are calculated according to a metric selected from the group consisting of Euclidean distance, cosine distance, and dynamic time warping distance.

14. The system of claim 10 , wherein the task manager is further configured to cluster time series according to similarity of the respective time series to form attribute clusters.

15. The system of claim 14 , wherein the task manager is further configured to rank representative time segments from each cluster according to how uniqueness of the respective representative time segments.

16. The system of claim 14 , wherein the similarity of time series is determined according to a Pearson correlation coefficient.

17. The system of claim 10 , wherein the task manager is further configured to select a group of sensors associated with a highest-ranked representative time segment.

18. The system of claim 10 , wherein the corrective action is selected from the group consisting of shielding the determined system and turning off the system in advance of predicted adverse space weather.