AI research

Detecting irregularities – The CausalAnomalies project

DLR's small and uncrewed superArtis helicopter in flight with payload
The CausalAnomalies project oversees the development of algorithms to detect suspicious behaviour patterns during the flights of uncrewed aircraft such as superArtis.
Image: 1/2, Credit:
DownloadDownload
TerraSAR-X and TanDEM-X satellites transmit telemetry data
Anomaly detection plays a crucial role when monitoring satellite telemetry – as depicted here with TerraSAR-X and TanDEM-X – or when analysing Earth observation data.
Image: 2/2, Credit:
DownloadDownload

Anomaly detection is essential for several areas of application at the German Aerospace Center (Deutsches Zentrum für Luft- und Raumfahrt; DLR). Anomaly detection plays a crucial role, for example, when monitoring satellite telemetry or analysing Earth observation data from satellites and climate models. Similarly, the continuous and automated monitoring of the condition of rails and railway switches is important to enable timely maintenance of transport infrastructure. In aviation, data is also continuously collected and used to monitor aircraft systems.

Another potential area of application is the examination of log data in information and communications technology (ICT) systems. Here, suspicious usage and attack patterns can be detected in locations such as the log files produced during the flight of an uncrewed aircraft. In the event of deviations from expected patterns, users can intervene to stop or adjust the procedures. When an anomaly is detected, it can indicate that the monitored system has entered a certain state, such as in the event of damage, which can be recognised and remedied through such intervention. However, understanding the causes of such anomalies is particularly important to model and predict the necessary procedures before the state of the system changes.

The CausalAnomalies project aims to develop new, causally explicable algorithms that detect anomalies. Finding abnormal states in time series data is a goal whenever sequential data is recorded and analysed. These data are often high-dimensional, error-prone, incomplete or not labelled. Furthermore, it is frequently unclear which abnormal behaviour within the data is relevant. Therefore, the first project goal is to explore different AI methods for anomaly detection. The next goal is to make these methods explicable in order to overcome the 'black box' nature of many AI methods. For this purpose, causal methods will be used and adapted. The developed methods will then be applied to various use cases at DLR and will be tested and optimised.

These use cases include:

  • Anomaly detection in satellite telemetry data
  • Detection of regimes of causal relationships in Earth system model data
  • Detection of anomalies and attack patterns in ICT systems
  • Condition monitoring of control and safety systems in transport infrastructure
  • Identification of causes of abnormal behaviour or incorrect decision making in the log files of uncrewed aircraft
  • Extension of condition monitoring functions for aircraft systems

The CausalAnomalies project is part of DLR’s research in 'Artificial intelligence'.

Participating DLR institutes and facilities

German Remote Sensing Data Center (DFD)

With its national and international ground stations, the German Remote Sensing Data Center (DFD) provides direct access to the data from Earth observation satellites, processes the data into information products, distributes them to the users and stores all the data in the German Satellite Data Archive (D-SDA) on a long-term basis.

Institute of Atmospheric Physics

The Institute of Atmospheric Physics is located at the DLR site in Oberpfaffenhofen. It focusses on the research of the physical and chemical processes of the troposphere and lower stratosphere.

Institute of Data Science

The main focus of the Institute of Data Science in Jena relies on finding solutions for the new challenges of the digitalisation era. Research is being conducted into topics related to Data Management, IT Security and Smart Systems (Industry 4.0).

Institute of Flight Systems

The Institute of Flight Systems (FT) has been active in the topics of flight mechanics and measurement and system technology of all flying systems at the DLR site Braunschweig since 1953.

Institute of Transportation Systems

In today’s economy and society mobility is of high significance. People want to arrive at their destinations comfortably and quickly. Goods have to be moved economically over long and short distances.

Space Operations and Astronaut Training

DLR Space Operations is the central institution for spaceflight operations in Germany. This responsibility includes satellite missions for Earth observation, science and communication missions as well as the exploration of the Solar System and human spaceflight missions.

Contact

Tobias Schneiderhan

Acting Board Member for Digitalization
German Aerospace Center (DLR)
Linder Höhe, 51147 Cologne