Acoustic phenology of tropical resident birds differs between native forest species and parkland colonizer species

Most birds are characterized by a seasonal phenology closely adapted to local climatic conditions, even in tropical habitats where climatic seasonality is slight. In order to better understand the phenologies of resident tropical birds, and how phenology may differ among species at the same site, we used ~70,000 hours of audio recordings collected continuously for two years at four recording stations in Singapore and nine custom-made machine learning classifiers to determine the vocal phenology of a panel of nine resident bird species. We detected distinct seasonality in vocal activity in some species but not others. Native forest species sang seasonally. In contrast, species which have had breeding populations in Singapore only for the last few decades exhibited seemingly aseasonal or unpredictable song activity throughout the year. Urbanization and habitat modification over the last 100 years have altered the composition of species in Singapore, which appears to have influenced phenol..., This is an acoustic phenology dataset. Soundscape recordings were collected 24/7 in Singapore over the course of 2 years. The machine learning software Kaleidoscope Pro was used to make species classifiers for 9 species of birds. Species classifiers are able to automatically detect all occurrences of the target species' song within the 2-year-long dataset. Automatic outputs were manually verified to ensure accuracy.
In addition to the cleaned species detection dataset, we also provide the Kaleidoscope species classifiers. These classifiers can be used to detect the 9 focal species in your own audio data., Each .csv file contains the results of one species classifier summarised by input file. Each row represents one unique audio file with a ~30min (29:55) duration and tells the number of times the target species can be heard within that file.
SeasonalityAnalysisExampleCode.R generates a calendar plot, radar plot, and vector-based seasonality index for Little Spiderhunters. Changing the loaded .csv file can generate these plots for the other species., Raw species detection data, R code for data processing, and Kaleidoscope species classifiers are available.

## Species Detection Data

Each .csv file contains the results of one species classifier summarised by input file.
Each row represents one unique audio file with a ~30min (29:55) duration and tells the
number of times the target species can be heard within that file.

**Site Names:**
CCNR - Central Catchment Nature Reserve, Singapore (1.355488, 103.804549)
DAFA - Dairy Farm Nature Park, Singapore (1.358419, 103.777492)
SBWR - Sungei Buloh Wetland Reserve, Singapore (1.441586, 103.735308)
NUS - National University of Singapore Campus, Singapore (1.295020, 103.779385)

**Species Names:**
LSpider - Little Spiderhunter - Arachnothera longirostra
DCuck - Drongo-cuckoo - Surniculus lugubris
RTTail - Rufous-tailed Tailorbird - Orthotomus sericeus
PSTB - Pin-striped Tit-babbler - Mixornis gularis
STBab - Short-tailed Babbler - Pellorneum malaccense
BNO - Black-naped Oriole - Oriolus chin...