Generalized Time‐Series Analysis for In Situ Spacecraft Observations: Anomaly Detection and Data Prioritization Using Principal Components Analysis and Unsupervised Clustering.

In situ spacecraft observations are critical to our study and understanding of the various phenomena that couple mass, momentum, and energy throughout near‐Earth space and beyond. However, on‐orbit telemetry constraints can severely limit the capability of spacecraft to transmit high‐cadence data, and missions are often only able to telemeter a small percentage of their captured data at full rate. This presents a programmatic need to prioritize intervals with the highest probability of enabling the mission's science goals. Larger missions such as the Magnetospheric Multiscale mission (MMS) aim to solve this problem with a Scientist‐In‐The‐Loop (SITL), where a domain expert flags intervals of time with potentially interesting data for high‐cadence data downlink and subsequent study. Although suitable for some missions, the SITL solution is not always feasible, especially for low‐cost missions such as CubeSats and NanoSats. This manuscript presents a generalizable method for the detection of anomalous data points in spacecraft observations, enabling rapid data prioritization without substantial computational overhead or the need for additional infrastructure on the ground. Specifically, Principal Components Analysis and One‐Class Support Vector Machines are used to generate an alternative representation of the data and provide an indication, for each point, of the data's potential for scientific utility. The technique's performance and generalizability is demonstrated through application to intervals of observations, including magnetic field data and plasma moments, from the CASSIOPE e‐POP/Swarm‐Echo and MMS missions. Plain Language Summary: Measurements captured by spacecraft are necessary to our understanding the space environment near Earth and throughout our solar system. However, spacecraft can often only transmit a small portion of the data they capture back to Earth. This means that many spacecraft must prioritize intervals of data that have the highest probability of helping to further our understanding of these environments. Some missions utilize humans, on Earth, to help select these scientifically important intervals. This solution, called the Scientist‐In‐The‐Loop, can be too expensive or programmatically complex for many small missions to implement. This manuscript presents a technique for the detection of anomalous events in spaceflight measurements using statistical analysis and machine learning. These detected anomalies can be used to prioritize data that has a high probability of scientific relevance. Further, the proposed technique is highly generalizable and computationally lightweight, making it suitable for a variety of missions. Several case studies from multiple existing missions will be analyzed throughout this paper. Key Points: Spacecraft often cannot transmit all measurements to Earth at full cadence due to telemetry bandwidth limitationsMany missions must implement complex data prioritization schemes to ensure only the highest‐priority data is transmitted at high cadenceThe proposed data prioritization technique is highly generic, compatible with inexpensive hardware, and suitable for low‐cost missions [ABSTRACT FROM AUTHOR]