Computational methods for detecting insect vibrational signals in field vibroscape recordings
Year: 2025
Type: article
Abstract: The ecological significance of vibroscape has been largely overlooked, excluding an important part of the available information from ecosystem assessment. Insects rely primarily on substrate-borne vibrational signaling in their communication, which is why the majority of terrestrial insects are excluded from passive acoustic monitoring. The ability to monitor the biological component of the natural vibroscape has been limited so far due to lack of data, as well as methods to analyze the data. In this paper, we evaluate the use of deep learning models to automatically detect and classify vibrational signals from field recordings obtained by laser vibrometry. We created a dataset of 91 hours of annotated vibroscape recordings from meadow habitats, containing vibrational signals categorized as pulses, harmonic signals, pulse trains and complex signals. Using the dataset, we compare different deep neural network architectures for the detection and classification of vibrational signals, including convolutional and transformer models. The PaSST transformer architecture, fine-tuned from a pre-trained checkpoint demonstrated the highest performance on all tasks, achieving an average precision of 0.79 in signal detection. For signals with more than one hour of annotated data, the classification models achieved instance-based F1-scores above 0.8, enabling automated analysis of activity patterns. In our case study, where 24-hour field recordings were analyzed, the trained models (even those with lower precision) revealed interesting activity patterns of different species. The presented study, together with the dataset we publish with this paper, lays the foundation for further analyses of the vibroscape and the development of automated methods for ecotremological monitoring, complementing passive acoustic monitoring to provide a comprehensive approach for ecosystem assessment.
Source: Ecological Informatics
Institutions: University of Ljubljana, National Institute of Biology
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,770
OpenAlex ID: W4406570460