Whitt et al. Future of Autonomous Ocean Observations reductions. Cost reductions could enable order-of-magnitude increases in platform operations and increase sampling resolution for a given level of investment. Energy harvesting technologies should be integral to the system design, for sensors, platforms, vehicles, and docking stations. Connections are needed between the marine energy and ocean observing communities to coordinate among funding sources, researchers, and end users. Regional teams should work with global organizations such as IOC/GOOS in governance development. International networks such as emerging glider operations (EGO) should also provide a forum for addressing governance. Networks of multiple vehicles can improve operational efficiencies and transform operational patterns. There is a need to develop operational architectures at regional and global scales to provide a backbone for active networking of autonomous platforms.

Many animals rely on long-form communication, in the form of songs, for vital functions such as mate attraction and territorial defence. We explored the prospect of improving automatic recognition performance by using the temporal context inherent in song. The ability to accurately detect sequences of calls has implications for conservation and biological studies. We show that the performance of a convolutional neural network (CNN), designed to detect song notes (calls) in short-duration audio segments, can be improved by combining it with a recurrent network designed to process sequences of learned representations from the CNN on a longer time scale. The combined system of independently trained CNN and long short-term memory (LSTM) network models exploits the temporal patterns between song notes. We demonstrate the technique using recordings of fin whale ( Balaenoptera physalus ) songs, which comprise patterned sequences of characteristic notes. We evaluated several variants of the CNN + LSTM network. Relative to the baseline CNN model, the CNN + LSTM models reduced performance variance, offering a 9–17% increase in area under the precision–recall curve and a 9–18% increase in peak F1-scores. These results show that the inclusion of temporal information may offer a valuable pathway for improving the automatic recognition and transcription of wildlife recordings.

Understanding the ecology and evolution of animal communication systems requires detailed data on signal structure and variation across species. Here, we describe the male acoustic signals of 50 species of Neotropical katydids (Orthoptera: Tettigoniidae) from Panama, with the goal of providing data and recordings for future research on katydid communication, evolution, ecology, and conservation. Male katydids were recorded individually using an ultrasound-sensitive microphone and high-sampling rate data acquisition board to capture both audible and ultrasonic components of calls. Calls varied enormously in duration, temporal patterning, peak frequency, and bandwidth both across and within subfamilies. We confirm previous studies showing that katydid species within the subfamily Pseudophyllinae produced short calls (<250 ms) at long intervals and we confirm that this is true for species in the subfamily Phaneropterinae as well. Species in the Conocephalinae, on the other hand, typically produced highly repetitive calls over longer periods of time. However, there were exceptions to this pattern, with a few species in the Conocephalinae producing very short calls at long intervals, and some species in the Phaneropterinae producing relatively long calls (1–6 s) or calling frequently. Our results also confirm previous studies showing a relationship between katydid size and the peak frequency of the call, with smaller katydids producing higher frequency calls, but the slope of this relationship differed with subfamily. We discuss the value of documenting the diversity in katydid calls for both basic studies on the ecology, evolution, and behavior of these species as well as the potential conservation benefits for bioacoustics monitoring programs.