Upper Waiakea Forest Reserve Passive Acoustic Recordings of Hawaiian Forest Birds

Provider
Imageomics Institute and ABC Global Center (Banerji N., Provost K. et al.)
License
CC-BY-4.0 (source)
Size
1,698 files
Format
WAV, CSV (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/imageomics/upper-waiakea-PAM)
Access
Free and public. No account with the data provider is needed.
Category
Speech & Audio
Source
https://huggingface.co/datasets/imageomics/upper-waiakea-PAM

About this dataset

About 1,623 hours of unlabelled passive acoustic monitoring (PAM) audio from 19 SongMeter Micro 2 recorders in the Upper Waiakea Forest Reserve on Hawaii Island, collected in January 2025 during the Imageomics Institute and ABC Global Center Experiential Introduction to AI and Ecology course. The soundscapes capture native Hawaiian forest birds in kipuka (forest islands surrounded by lava flows), for unsupervised audio analysis, running existing classifiers such as BirdNET or Perch, and relating song activity to habitat. Each recorder folder holds hourly WAV files named recorder_YYYYMMDD_HHMMSS and a summary text file; kipuka_metadata.csv gives recorder, SD card and point ids, deployment and retrieval dates and latitude and longitude; check.py summarises coverage. Measured: 1,698 files, 1,672 WAV, about 281 GB. No species labels; splits must be made by the user. Licensed CC BY 4.0 by the curators; cite the dataset.

How to load this dataset in Python

import pandas as pd
df = pd.read_csv("hf://datasets/imageomics/upper-waiakea-PAM/kipuka_metadata.csv")
df.head()

Data structure

File types in sampled files: WAV, CSV

Files

Example file: kipuka_metadata.csv

Analyze this dataset without downloading it

On Scigantic, Upper Waiakea Forest Reserve Passive Acoustic Recordings of Hawaiian Forest Birds opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Speech & Audio datasets