Fig. 4.

Overall agreement between observer (manual) and machine (networks) estimations of abundance (cover). Agreement is here discretised in two metrics: (a) Correlation between machine and observer annotations, and (b) bias (Bland-Altman plot). Each filled circle in these panels represents the estimated cover for each label classified by both, the machine and the observer in a given transect. The correlation shows that estimations of benthic abundance by expert observations are significantly represented by the automated estimations (R² = 0.97). The Bland-Altman plot shows that overall the differences (Bias) between machine and observer tend to mean of zero (grey continuous line), and a homogenous error around the mean, defined by Critical Difference (Critical diff.) or the 95% Confidence Interval of the difference between observers and machines (dashed grey lines). Figure originally published in González-Rivero et al.²³ (as Figure A1).