Performance validation

of the Aquatic Imager was conducted on data from a 7-minute transect collected around Indian Key in Tampa Bay, Florida, on October 24, 2023.

Classifications assigned by application of our proprietary software were compared to validated classifications assigned by our zooplankton taxonomist. The method involves running a classification using the original (unvalidated) images, determining the accuracy of that run by comparing with the validated images, then adding additional validated images to the training library and conducting a reclassification using the additional information.

Our goal is at least 80% accuracy, and we have achieved that for most of the tabulated taxonomic groups following 8-10 reclassifications. The number of images added to the training library was dependent on class size within the sample, for more information, check out the additional tables.

Our classification accuracy (and likely taxonomic resolution) will improve as we expand the training library used by the software for classification (as shown by the large training library size of noise and bubbles).