An integrated passive acoustic monitoring and deep learning pipeline for black‐and‐white ruffed lemurs (Varecia variegata) in Ranomafana National Park, Madagascar

• Published in: American journal of primatology Vol. 86; no. 4; pp. e23599 - n/a
• Main Authors: Batist, Carly H., Dufourq, Emmanuel, Jeantet, Lorène, Razafindraibe, Mendrika N., Randriamanantena, Francois, Baden, Andrea L.
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01-04-2024
• Subjects: Acoustic tracking; Acoustics; Animal populations; Animals; Artificial neural networks; Audio data; Automation; Biodiversity; Biodiversity loss; Birds; Conservation; convolutional neural network; Data analysis; Dawn chorus; Deep Learning; Diel activity; ecoacoustics; Effectiveness; Humans; Learning algorithms; Lemur; Lemuridae; Machine learning; Madagascar; Mammals; Marine mammals; Mating; Money; Monitoring; National parks; Neural networks; Nocturnal; Parks, Recreational; Primates; Primatology; Rainforests; Recall; Strepsirhini; strepsirrhine; Transfer learning; Varecia variegata; Vocal behaviour; Vocalization behavior; Wildlife; Madagascar; ecoacoustics; conservation; strepsirrhine; machine learning; convolutional neural network
• DOI: 10.1002/ajp.23599
• EISSN: 1098-2345
• ISSN: 0275-2565

The urgent need for effective wildlife monitoring solutions in the face of global biodiversity loss has resulted in the emergence of conservation technologies such as passive acoustic monitoring (PAM). While PAM has been extensively used for marine mammals, birds, and bats, its application to primates is limited. Black‐and‐white ruffed lemurs (Varecia variegata) are a promising species to test PAM with due to their distinctive and loud roar‐shrieks. Furthermore, these lemurs are challenging to monitor via traditional methods due to their fragmented and often unpredictable distribution in Madagascar's dense eastern rainforests. Our goal in this study was to develop a machine learning pipeline for automated call detection from PAM data, compare the effectiveness of PAM versus in‐person observations, and investigate diel patterns in lemur vocal behavior. We did this study at Mangevo, Ranomafana National Park by concurrently conducting focal follows and deploying autonomous recorders in May–July 2019. We used transfer learning to build a convolutional neural network (optimized for recall) that automated the detection of lemur calls (57‐h runtime; recall = 0.94, F1 = 0.70). We found that PAM outperformed in‐person observations, saving time, money, and labor while also providing re‐analyzable data. Using PAM yielded novel insights into V. variegata diel vocal patterns; we present the first published evidence of nocturnal calling. We developed a graphic user interface and open‐sourced data and code, to serve as a resource for primatologists interested in implementing PAM and machine learning. By leveraging the potential of this pipeline, we can address the urgent need for effective primate population surveys to inform conservation strategies.
The transfer learning pipeline we used to train a convolutional neural network to distinguish between ruffed lemur and nonlemur calls.
Highlights
We conducted a passive acoustic monitoring concurrently with behavioral observations to assess each method's effectiveness in detecting black‐and‐white ruffed lemurs in Ranomafana National Park.
We developed a deep learning model that enabled automated and accurate analysis of 2300 h of audio data, surpassing manual processing limitations, saving time and money, and yielding re‐analyzable data for lemur conservation efforts.
We found that ruffed lemurs have consistent calling activity throughout the day (no dawn chorus), and also present the first published evidence of nocturnal calling, which peaked during the mating period.