ABSTRACT
Soundscape ecology is a promising area that studies landscape patterns based on their acoustic composition. It focuses on the distribution of biotic and abiotic sounds at different frequencies of the landscape acoustic attribute and the relationship of said sounds with ecosystem health metrics and indicators (e.g., species richness, acoustic biodiversity, vectors of structural change, gradients of vegetation cover, landscape connectivity, and temporal and spatial characteristics). To conduct such studies, researchers analyze recordings from Acoustic Recording Units (ARUs). The increasing use of ARUs and their capacity to record hours of audio for months at a time have created a need for automatic processing methods to reduce time consumption, correlate variables implicit in the recordings, extract features, and characterize sound patterns related to landscape attributes. Consequently, traditional machine learning methods have been commonly used to process data on different characteristics of soundscapes, mainly the presence-absence of species. In addition, it has been employed for call segmentation, species identification, and sound source clustering. However, some authors highlight the importance of the new approaches that use unsupervised deep learning methods to improve the results and diversify the assessed attributes. In this paper, we present a systematic review of machine learning methods used in the field of ecoacoustics for data processing. It includes recent trends, such as semi-supervised and unsupervised deep learning methods. Moreover, it maintains the format found in the reviewed papers. First, we describe the ARUs employed in the papers analyzed, their configuration, and the study sites where the datasets were collected. Then, we provide an ecological justification that relates acoustic monitoring to landscape features. Subsequently, we explain the machine learning methods followed to assess various landscape attributes. The results show a trend towards label-free methods that can process the large volumes of data gathered in recent years. Finally, we discuss the need to adopt methods with a machine learning approach in other biological dimensions of landscapes.
ABSTRACT
Noise is one of the fastest growing and most ubiquitous type of environmental pollution, with prevalence in cities. The COVID-19 confinement in 2020 in Colombia led to a reduction in human activities and their associated noise. We used this unique opportunity to measure the impacts of noise on urban soundscapes, and explore the effects of urbanization intensity independently of human activity. We launched a community science initiative inviting participants to collect audio recordings from their windows using smartphones. Recordings were taken during severe mobility restrictions (April), and during a period of lightened restrictions (May-June). From the data collected, we measured changes in sound pressure levels (SPL), acoustic structure (soundscape spectro-temporal characteristics), and human perception between the two periods. A 12% increase in human activities had a detectable acoustic footprint, with a significant increase of SPL (2.15 dB, 128% increase), a shift towards dominance of low-frequency broadband signals, and a perceived dominance of human-made over wildlife sounds. Measured changes in SPL and acoustic structure were directly proportional to urbanization; however, perception of these changes was not. This gap may be associated with a masking effect generated by noise or a disconnect of humans from nature in large cities. The mobility restrictions created a chance to better understand the impacts of urbanization and human activities on the soundscape, while raising public awareness regarding noise pollution effects on people and wildlife. Information analyzed here might serve in urban planning in developing countries where urban expansion is occurring in a rapid, unplanned fashion.