Earth Species Project develops sophisticated AI technologies like Nature-LM audio, the world’s first and leading audio-language machine learning algorithm with various capabilities. It has the potential to help our environment by bolstering conservation efforts and research in countless ways. For a transcript, please visit https://climatebreak.org/earth-species-with-aza-raskin
What is the Earth Species Project?
Can we talk to animals, or at least understand what they are saying to each other? That’s a question that researchers hope to answer with the help of AI. Earth Species Project, a non-profit that develops sophisticated AI technologies, hopes its software can help. Specifically, they have developed Nature-LM audio which is an audio-language machine learning algorithm with the potential to decipher animal communications.
How does it work?
By gathering and evaluating huge amounts of audio information from different species, Nature-LM audio can identify “individuals in recordings”, and evaluate patterns. For software users, it does not require the user to have any programming skills. Specifically “analyzing animal sounds… [allows for] decoding complex communication and behaviors to monitor the health of entire ecosystems.”
This AI model was trained on “bioacoustic archives like Xeno-canto, iNaturalist, the Watkins Marine Mammal Sound Database, and the Animal Sound Archive” along with “general audio, human speech, and music data” while connecting this ”audio encoder to a leading language model.”
Benefits of this approach
NatureLM “can classify or detect thousands of species across diverse taxa including birds, whales, and aurans–without the need to retrain the model for each task.”. It has other capabilities like “predicting life-stage and simple call-types of birds, and captioning bioacoustic audio” which are useful when trying to analyze the behavior of different species and their associated cues. The software enables evaluation of large amounts of animal sounds and allows evaluation of that data “freely via human language text”.
According to a benchmark that they established, called the Beans-zero, which “provides a standardized way to measure… performance across various bioacoustic tasks, enabling consistent comparisons and fostering progress in the field”, NatureLM-audio “achieves state-of-the-art performance on most tasks”. This is especially true in regards to bird and marine mammal sounds, which they are able to identify without fine-tuning–an extremely gruesome task in machine learning to change pre-existing models which better fit your data and train it for specific tasks.
Potential Drawbacks
Like all AI models, Nature LM-audio could impact employment opportunities, in this case for animal biologists and researchers, and by using substantial amounts of energy to run the model. And, like all AI programs, any conclusions and decisions made through the program need to be carefully evaluated. It will take time and effort to determine how valuable the model is.
Conclusion
Raskin believes that the creation of NatureLM has many positive implications because it allows humans to listen to the voices of animals. It gives us an understanding of their behavior to not only learn more about them, but also by giving insights on how to help them with conservation efforts. Moreover, it can alert researchers to what exactly is endangering certain species, prevent these efforts, and create a lot of more data necessary to analyze trends.
About our guest
Aza Raskin is a trained mathematician and a dark matter physicist and Co-Founder/President of the Earth Species Project.
Resources
Further Reading
For a transcript, please visit https://climatebreak.org/earth-species-with-aza-raskin
Raskin: We're at the frontier of using AI to translate animal communication. And the goal is not just the science, but the goal is, can we have a renewed relationship with nature?// And so this is not about giving animals a voice. This is about being able to listen to the voice that they already have.
Ethan: Nature LM is already uncovering new insights and patterns across species.
Raskin: There's a group that's using, our tools to understand how orangutan vocalizations change due to forest fire smoke // There's another group that's using our tools to understand movements // of Pumas in Yellowstone National Park. So we're starting to see already that the tools are helping biologists and pathologists and social biologists // understand conservation // better.
Ethan: Though this technology is still developing, Raskin says its potential to help scientists more effectively target conservation efforts is very promising.
Raskin: You can upload all of your data and then start to ask it questions, like, tell me when there is some illegal logging happening in areas of high endangered species activity. Nature LM will enable things like that very soon.
Ethan: For Raskin, the biggest breakthrough of Nature LM isn’t technological, but rather the opportunity it will give humans to learn from and empathize with other species.
Raskin: When we make life better for all the other species of earth, we'll make life better for everyone.
Ethan: To learn more about how AI can help us better protect the natural world from the impacts of humans, visit climatebreak.org.