Table 1. Performance measures for the worldwide trawl dataset.

NF stands for probable non-fishing and F for probable fishing events. Sensitivity is related with non-fishing detection, and specificity with fishing detection. The column Stat. Diff. Fish Effort shows the t-test statistical comparison (p-value) between the predicted fishing effort time calculated from the algorithm’s labels and the expert’s labels. The asterisk indicates a significant difference.

Track ID	Track Size	Accuracy	Prediction (F)	Prediction (NF)	Sensitivity	Specificity	% of Fish Activity	Stat. Diff. Fish Effort
1	38258	0.75	0.47	0.96	0.90	0.71	0.42	0.84
2	254323	0.84	0.83	0.85	0.93	0.69	0.70	0.21
3	93670	0.83	0.82	0.95	0.99	0.40	0.89	0.11
4	56287	0.87	0.89	0.80	0.94	0.69	0.77	0.04*
5	55034	0.92	0.51	0.98	0.82	0.93	0.14	0.21
6	285407	0.57	0.28	0.93	0.84	0.51	0.55	0.09
7	101499	0.76	0.01	1.00	1.00	0.76	0.24	0.32
Median±SD		0.83±0.11	0.51±0.32	0.95±0.07	0.93±0.07	0.68±0.17