Vortrag - Machine learning for Space Gardening

Referent: Ferdinand Rewicki (DLR)

Working in the EDEN NEXT GEN and EDEN LUNA projects, we are concerned with detecting unhealthiness within different kinds of data.In this talk, I will introduce different classic and deep-learning-based methods for finding anomalies in time series data and present our latest results on the differences regarding the types of anomalies these methods can find. Based on this, I will present our concept for using these techniques to detect unhealthy system states in telemetry data as well as unhealthy plants in images