Aerial surveys of fish in estuaries: a case study in Chesapeake Bay

The performance of a near-nadir, airborne lidar was compared with that of an airborne imagery (video) system for surveys of Atlantic menhaden (Brevoortia tyrannus) in Chesapeake Bay, USA. Lidar had a greater probability of detecting a school (0.93 vs. 0.73) as a result of its greater depth penetration, a lesser probability of false identification (0.05 vs. 0.13) because it was less dependent on surface conditions and ambient illumination, and less variability [coefficient of variability of 0.34 vs. 0.73] in repeated coverage of the same area. Video had a lower statistical uncertainty in school detection [relative standard error 0.04 vs. 0.07] as a result of its greater swath width. The average depth penetration of lidar was 12 m, and the average depth of detected schools was 3 m. The performance of both techniques decreased with increasing windspeed, although the effect was smaller for lidar. The school area inferred by the two techniques was nearly the same. An examination of the missed schools and false identifications in lidar and video suggest that a combination of the two techniques would reduce most of the uncertainty associated with the use of either technique alone.