Microsoft AI for Good Lab — open-source AI for biodiversity monitoring and conservation.
Our journey started with MegaDetector — a camera-trap animal detection model that became a widely adopted tool in the conservation community. Building on that foundation, we created PyTorch-Wildlife as a unified platform to host all of our AI for biodiversity work, bringing together detection, classification, and eventually much more.
Over time, our scope grew well beyond camera-trap imagery. We now have active work in bioacoustics, overhead animal detection, edge computing for remote field deployments, and a dedicated desktop UI — SPARROW Studio — that runs every model we produce. As the ecosystem expanded, it became clear that keeping everything inside a single repository was working against us. Code was harder to find, harder to maintain, and harder to extend.
So we made a deliberate decision: break the work into focused, dedicated repositories — one per project — where the code in each repo is concentrated, the ownership is clear, and future contributors know exactly where to go. This repository is the hub that ties them together. PyTorch-Wildlife now lives at microsoft/PytorchWildlife, MegaDetector at microsoft/MegaDetector, and everything else is linked in the table below.
| Repo | Purpose |
|---|---|
| microsoft/MegaDetector | AI model for detecting animals, people, and vehicles in camera-trap imagery |
| microsoft/SPARROW | Solar-Powered Acoustic and Remote Recording Observation Watch — AI edge device |
| microsoft/PytorchWildlife | Collaborative deep learning framework for conservation |
| microsoft/Bioacoustics | Bioacoustic AI for biodiversity monitoring |
| microsoft/WildlifeClassification | Species classification models |
| microsoft/Bongo | (Owner-populated) |
| microsoft/OwlBioacoustics | (Owner-populated) |
| /SPARROW-Studio | SPARROW Studio — desktop installer, packaging, signed releases |
When citing work that uses any of the repositories under this umbrella, please cite:
- Hernandez et al. 2024 — Pytorch-Wildlife: A Collaborative Deep Learning Framework for Conservation — for any use of the PyTorch-Wildlife framework or models accessed through it
- Beery, Morris, Yang 2019 — Efficient Pipeline for Camera Trap Image Review — for any use of MegaDetector specifically
A citation.cff file is included in this repository for automated citation tools.
We welcome community contributions. See our Contribution Guidelines for how to participate.
For questions about MegaDetector and PyTorch-Wildlife, reach the team via Discord:
A list of organizations using MegaDetector across global conservation work — six years of partnerships, from national parks to research universities to NGOs — is maintained on the microsoft/MegaDetector repository.
Maintained by Microsoft AI for Good Lab.