The AIREO Best Practice Guidelines outline how to generate and document AIREO-compliant datasets following the AIREO specifications. The guidelines consider best practice from both the EO and AI/ML communities, as well as specific recommendations relevant to the AIREO specifications. The innovations introduced in the AIREO specification are described in more detail in the Guidelines from a data providers perspective.
The document is organised into sections broadly following the various stages of TDS development, from designing an EO TDS, sourcing and aggregating the data, ensuring data quality, adhering to FAIR principles, implementing EO TDS metadata according to the AIREO specifications and distributing/sharing an EO TDS.
These best practice guidelines are not intended to be a summary of general purpose machine learning or EO data best practices, but rather those specific to EO and ML applications and in particular generating and working with the AIREO TDS specifications and innovations. The report also includes illustrative examples from the set of pilot TDS developed as part of the activity.
To subscribe to the AIREO network or to contact the AIREO Team please email email@example.com