Hey all! I've been helping the Seattle Aquarium's Costal Climate Resilience program which uses ROVs to conduct surveys to understand kelp forrests and then several different machine learning models to enhance those images and then identify kelp and other species. We are starting to publish more of our work and datasets and code on github / huggingface if anyone is interested in learning more:

• Main program github: https://github.com/Seattle-Aquarium/Coastal_Climate_Resilience
• The training scripts / GUI program I've been heavily involved in developing for enhancing underwater images: https://github.com/keenanjohnson/underwater-auto-image-encoder
• Datasets and models: https://huggingface.co/Seattle-Aquarium
  
   

Specifically I have been really focused on how to best train a ML model to enhance the underwater images we are taking and always looking for feedback or ideas! The whole dataset and training scripts and everything in the repos above. As the project grows, I'll continue posting updates, but always happy to chat with anyone about it. 

There is a continously growing list of problems that we are always looking for open-source collaborators with. Things like the image enhancement I mentioned above, but lots more like how to track the bull kelp (described more here).