Optimizing a rotating thermal-IR system to automatically detect marine mammals in Atlantic Canada

We are interested in making a comparison of three methods to detect marine mammals at sea offshore of Atlantic Canada: marine mammal observers (MMOs) making visual observations, MMOs assisted by a thermal-IR (infrared) automatic detection system, and passive acoustic monitoring (PAM). Prior to making this comparison, the detection and classification algorithms for the thermal-IR system required optimization for use in the thermal regime offshore Atlantic Canada. In summer 2015, we made visual observations concurrent with the collection of thermal-IR data at a shore-based observation site at Cape Race, Newfoundland. A total of 1114 location fixes on marine mammals were made using a theodolite: humpback whales (n = 967), minke whales (n = 112), harbour porpoises (n = 10), unidentified baleen whales (n = 16), and unidentified whales (n = 9). Thermal imagery data were retrospectively scanned and thermal anomalies that could be identified as marine mammals were found to match 700 of the 1114 fixes. Of the remaining 414 fixes, 366 were not found in the images, and 48 were undetermined. This dataset was used to optimize the detection and classification algorithms prior to the 2016 field season. In general, ≥70% of marine mammal sightings made by MMOs within 3 km of the shore-based observation site were discernible in thermal-IR imagery during periods when the Beaufort wind force was ≤ 6, for all sighting cues (e.g., blow, body) and species combined. The three detection methods will be compared during a research cruise in summer 2017. The results should be useful in the development of best practice guidelines for marine mammal mitigation monitoring during seismic surveys in Canada.