Station Specific QA/QC Thresholds for Sensor Stations
Develop an AI/ML-based tool to assist in setting station-specific QA/QC thresholds for sensors (including water level, shore stations, etc.). The tool would establish thresholds and possibly quantify the confidence of those values. The tool could utilize historical sensor timeseries data, sensor characteristics, sensor metadata, nearby stations, and site-specific context, if available.
Expected Outcomes
- Prototype AI/ML tool generating station-specific QARTOD thresholds
- Documented workflow that can be used with the prototype tool to test it on multiple stations
Skills required
- Python
- Machine learning / AI
- Familiarity with QARTOD tests
Expertise
Intermediate
Topic Lead(s)
Aaron Mau, Marta Wolfshorndl
Relevant links
- https://cdn.ioos.noaa.gov/attachments/2025/AI-Enabled%20Water%20Level%20Data%20Quality%20Control.pdf
- https://ioos.noaa.gov/project/qartod/
Functioning Prototype
TBD
Workflow
Tasks:
- Find example training datasets
- Choose potential models
- Create training workflow and reproduce results
- Scale up to more datasets
Deliverables:
auto_threshmodule inioos_qc- This includes example model weights and coeffs, training code to export coeffs
- Walkthrough Jupyter notebook for building your own model
- In
docs/examples
- In
Updates