Practical Analysis of Big Acoustic Sensor Data for Environmental Monitoring

Abstract

Monitoring the environment with acoustic sensors is an effective method for understanding changes in ecosystems. Through extensive monitoring, large-scale, ecologically relevant, datasets can be produced that can inform environmental policy. The collection of acoustic sensor data is a solved problem; the current challenge is the management and analysis of raw audio data to produce useful datasets for ecologists. This paper presents the applied research we use to analyze big acoustic datasets. Its core contribution is the presentation of practical large-scale acoustic data analysis methodologies. We describe details of the data workflows we use to provide both citizen scientists and researchers practical access to large volumes of ecoacoustic data. Finally, we propose a work in progress largescale architecture for analysis driven by a hybrid cloud-and-local production-grade website.

Comparisons Between Autonomous Acoustic Recordings and Avian Point Counts in Open Woodland Savanna

“…However, research in soundscape ecology is currently booming (Table 1), and this increase is a testament to technical improvements in acoustic recorders and soundscape analysis tools that have been developed over the past 10 yr (Servick 2014). Programmable recorders now allow for simultaneous, long-term, multisite recording (Acevedo andVillanueva-Rivera 2006, Brandes 2008), and data management systems like Pumilio (Villanueva-Rivera and Pijanowski 2012), the Remote Environmental Assessment Laboratory (REAL) digital library (Kasten et al 2012), ARBIMON (Aide et al 2013), and Ecosounds Acoustic Workbench (Truskinger et al 2014) have facilitated data organization. In addition, necessary research on soundscape dataset visualization has recently advanced (Towsey et al 2014b).…”

Toward a Synthetic Acoustic Ecology: Sonically Situated, Evolutionary Agent Based Models of the Acoustic Niche Hypothesis

“…Sound is understood as a core ecological component (resource) and ipso facto, due to structuring by competition, an indicator of ecological status (source of information). The field has been substantially bolstered by the increasing availability and decreasing costs of automated recording devices (Acevedo and VillanuevaRivera, 2006;Farina et al, 2018), cheap storage and developments in acoustic data processing (Truskinger et al, 2014). However, whilst it has drawn from theories of related ecological disciplines including bioacoustics, and landscape ecology (Turner et al, 2001), there is an absence of coherent theory regarding the ecological significance of the macro soundscape.…”

Active learning for classifying long‐duration audio recordings of the environment

“…To determine the acoustic content of each cluster, we adopted the five approaches described in Phillips et al (2018). For the purposes of this study, the most important method was listening to a random selection of ten 1-min recordings from each cluster (a total of 600 min or 10 hr) using the Ecosounds website (Truskinger, Cottman-Fields, Eichinski, Towsey, & Roe, 2014).…”