• Background
• Part 1. Installing BirdNET on a Windows machine
  • 1. Activate WSL
  • 2. Install an Ubuntu Distribution
  • 3. Install BirdNET-Lite
• Part 2. Using BirdNET-Lite from R with Reticulate
  • 1. Set up a conda environment
  • 2. Set up an R script from which to interface with BirdNET
  • 3. Modify the BirdNET analyze script
  • 4. Run BirdNET from RStudio

This position is now closed.

I have three recent publications to share, all of which have me reflecting on my past few years of work.

I’m sharing a recording of my recent presentation, Toward a national perspective for climate change refugia conservation, which I presented at the 2020 North American Congress for Conservation Biology (NACCB). This was an excellent event and I enjoyed getting to meet so many people virtually. Consider this an invitation to stay in touch (or get in touch!) if you are interested in any of this work.

New open-access paper out in Methods in Ecology and Evolution: AMMonitor: Remote monitoring of biodiversity in an adaptive framework with R. This paper gives an overview of our software package AMMonitor. It’s public and available for free under provisional release from the U.S. Geological Survey Gitlab repository here: https://code.usgs.gov/vtcfwru/ammonitor. See the Wiki for documentation.

AMMonitor – the R software package my collaborators and I been working on for the past several years – is finally public, and available for free under provisional release from the U.S. Geological Survey Gitlab repository here: https://code.usgs.gov/vtcfwru/ammonitor. A brief software paper documenting this work is currently in review.

My third publication from my PhD work is out: Temporally adaptive acoustic sampling to maximize detection across a suite of focal wildlife species, published as an open access article in Ecology and Evolution. The Github repository accompanying the paper is located at https://github.com/cbalantic/temporally-adaptive-sampling.

My second publication from my PhD work is out: Statistical learning mitigation of false positives from template-detected data in automated acoustic wildlife monitoring, published as an open access article in Bioacoustics. The Github repository accompanying the paper is located at https://github.com/cbalantic/false-positive-mitigation.

My first publication from my PhD work is out: Dynamic wildlife occupancy models using automated acoustic monitoring data, published as an open access article in Ecological Applications.

I gave my PhD dissertation seminar last Friday (09/21/2018), and successfully passed my defense! It’s official: thrillingly, AAAS is no longer mistaken when they print “Dr. Cathleen Balantic” on their mailers to me.

Earlier this week, I shared some of my research at the annual Northeast Association of Fish & Wildlife Agencies (NEAFWA) conference. I had a blast talking with other attendees about the challenges of monitoring wildlife, and the opportunities (and additional challenges!) acoustic monitoring offers in this arena. My first presentation reviewed some of our work using maching learning to minimize the number of false alarms automated detection systems can produce. My second presentation shared our approach to a temporally-adaptive acoustic sampling scheme for situations with constraints on how much audio you can record.

To teach myself something new, I created a silly R Shiny app for logging auditory observations of birds singing in the background of my favorite show, Game of Thrones. I envisioned a fun distribution map, but quickly became overwhelmed with how many different bird species there are singing on the show (in certain locations). I don’t know most of them! I’m happy to have an excuse to rewatch GOT, and I love using my ears to learn and ID new birds. I don’t have much data yet, but if this interests you at all, please check out the app and contribute your observations!