...

• System applies ML to detect potential anomalies in displacement time-series, and publishes detected results back to GRQ catalog.

• User logs into system to browse potential anomalies.
  Science story: Anomaly detection will inform scientists of possible volcanoes to monitor closely.

Processing Pipeline

Draft diagram of Processing Pipeline - to be refined as more information is learned:

...

This diagram branches off from the larger system diagram on Standard Product S1-GUNW Processing Pipeline.

...

From a high-level, the main steps of this pipeline are:

1. The production of a S1-GUNW from within a defined volcanic AOI triggers the AOI track evaluator to run.

2. Once the AOI track evaluator detects that the full track of GUNWs has been produced, the evaluator creates a JSON file containing metadata about the data products, and stores it on S3.

3. The creation of the JSON file triggers the time-displacement PGE to run.

4. The PGE takes the JSON file as input, as well as a custom configuration file, and outputs an HDF-EOS5 format file containing the displacement time-series for the AOI.

Implementation Notes (Alex Dunn )

...