Machine Learning for Conservation main content.

Machine Learning for Conservation

Machine learning has gone from a relatively niche field of academic research in the 80’s and 90’s to powering everyday services, self-driving cars, and data analyses. Since 2012, the explosion of machine learning has largely been facilitated by advances in the graphics processing units (GPUs) and the availability of massive labeled datasets.

The CBC is committed to advancing and promoting the use of machine learning for the understanding and conservation of biodiversity by:

  • Cultivating a network of conservation practitioners and machine learning experts to advance the use of machine learning for the understanding and conservation of biodiversity.
  • Developing open source tools and workflows to facilitate the use of state of the art methods and machine learning libraries for the understanding and conservation of biodiversity.
  • Developing guides, tutorials, and workshops to introduce and demonstrate, to conservation practitioners, the utility and power of machine learning for the understanding and conservation of biodiversity.       

We recently launched the collaborative Animal Detection Network with the aim to advance the use of machine learning and developing opensource tools and workflows for the automated identification and counting of animal species in images, video, and audio. Annotating images from camera traps, the team completed a simple proof-of-concept for near real-time detection and counting of birds visiting a feeder as part of the network's flagship project Species Identification and Localization in Camera Trap Images.

        

Learn more about our machine learning projects and initiatives:

Contact us: If you have any questions about these projects, please contact Ned Horning and Peter Ersts.