Table 1. Summary of the two datasets used to evaluate the model under the acoustic monitoring scenario: CLO-WTSP and CLO-SWTH.

For each dataset a breakdown is provided into train data, test data, and total. For each breakdown we provide the number of instances for the positive class (Target) and for the negative class, where the latter is further divided into negative instances containing flight calls other than the target species (FlightCall) and negative instances containing no flight call (Reject). The percentage of positive instances in each set is provided in the %Pos column.

Dataset	Train (fall 2014)				Test (spring 2015)				Total (fall + spring)
	Target	FlightCall	Reject	%Pos	Target	FlightCall	Reject	%Pos	Target	FlightCall	Reject	%Pos
CLO-WTSP	882	1063	3071	21.3%	656	1569	9462	5.9%	1538	2632	12533	10.1%
CLO-SWTH	876	806	6984	11.2%	316	197	169932	0.2%	1192	1003	176916	0.7%