Do you hear what I hear? Soundscapes Along a Gradient of Urbanization in Clinton County, NY
Bibliographic record
Abstract
Soundscapes are a compilation of sounds emanating from a landscape which creates an acoustic pattern across time and space. Wildlife behaviors are easily influenced by sound and can be reflected in periods of intense vocalization and silence. Urban landscapes are heavily influenced by anthrophony (human-produced sound) which can limit or enhance biophony (wildlife-produced sound). In fall 2024, the Wildlife Ecology and Management class arrayed five autonomous recording devices (AudioMoths) along an urbanization gradient (urban, urban interface, exurban golf course, rural riparia, and forested beaver pond). Audiomoths were programmed to record sound during peak hours of wildlife activity from 17:00-8:00 on two consecutive days during a warm spell. Data were downloaded and BirdNet-Analyzer was used to identify species using artificial intelligence (AI) algorithms associated with eBird. Output files were appended in R Studio and soundscape patterns were analyzed across sites. Biophony richness was highest at the exurban golf course (41), followed by urban (38), beaver pond (20), rural riparia (18), and urban interface (16). The most frequent callers at the urban site were American crow, dogs, squirrels, blue jays, Canada geese, and Carolina wren. At the urban interface, Canada geese, Carolina wren, and northern cardinals were highly vocal. At the exurban golf course, spring peeper, white-throated sparrows, barred owls, American crows, hairy woodpecker, and katydids were heard as compared to the rural riparia's eastern towhees, great-horned owls, and hairy woodpeckers. In contrast, anthrophonic call frequency was high and most similar at the urban (981) and and exurban golf course (891), intermediate at the urban interface (136), followed by the beaver pond (39), and rural riparia (33) with sounds including engines, humans, and power tools. At dawn the urban, exurban golf course, and beaver pond exhibited a high biophonic call frequency, while at dusk urbanized sites experienced extremely high calling rates compared to rural sites. Urban and exurban golf course communities were the most similar (51%), while the urban interface and the beaver pond were the least (22%). Soundscape ecology is a relatively new field that is growing in popularity due to the affordability of sensors and advances in AI. Our class learned that although these technologies have numerous benefits, there is still a need to perform supplemental surveys using traditional techniques or experts should be onboarded to help better identify misidentified calls.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.014 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".