AI tool 'SuperAnimal' can accurately analyze animal behavior

SuperAnimal, a revolutionary deep learning model, has been developed to detect animal motion across various species and environments.

Understanding animal behavior offers critical insights into their health and motivations. This “foundational model” is set to revolutionize animal conservation, biomedicine, and neuroscience research.

Why analyze animal behavior?

Animal behavior, encompassing interactions with others, the environment, and different organisms, is a crucial field of study. 

This field explores activities such as foraging, mating, parenting, social interactions, and communication, all of which are shaped by genetic and environmental factors. 

Understanding these behaviors provides valuable insights into animal health, welfare, and ecological roles, enabling better conservation efforts and animal care practices. 

Furthermore, research into animal behavior can ultimately improving human-animal interactions and promoting sustainable ecosystems.

Decoding animal emotions through movement

Animals can’t verbally communicate their feelings, but their movements tell a story. Imagine using AI to analyze these movements for a wide range of animals, including cows, dogs, cats, and mice.

This would eliminate observer bias and enhance the accuracy and efficiency of behavioral analysis.

A team at the École Polytechnique Fédérale de Lausanne (EPFL), led by Dr. Mackenzie Mathis, has introduced a groundbreaking tool for posture analysis in behavioral phenotyping.

Detailed in a recent Nature Communications article, this open-source tool, named SuperAnimal, requires no human annotations to track animal movements.

It can automatically identify keypoints (joints) in over 45 animal species, including mythical ones, without human intervention.

“The current pipeline requires human effort to identify keypoints on each animal, creating a training set,” explains Dr. Mathis.

“This results in duplicated labeling efforts and inconsistent semantic labels, complicating the training of large foundation models. Our new method standardizes this process and makes labeling 10 to 100 times more efficient than current tools.”

Advancing from DeepLabCut to SuperAnimal

SuperAnimal is an evolution of a pose estimation technique previously known as DeepLabCut.

The new tool compiles a large set of annotations from various databases, training the model to learn a harmonized language — a process called pre-training the foundation model.

“Users can deploy our base model or fine-tune it with their data for further customization,” says Shaokai Ye, a PhD student and first author of the study.

Enhancing SuperAnimal with natural language interfaces

SuperAnimal has a broad range of applications. Veterinarians and biomedical researchers, especially those studying laboratory mice, will find it invaluable.

Its potential also extends to neuroscience and analyzing athletic performance in animals. Future versions of the model aim to include birds, fish, and insects.

“We plan to integrate these models with natural language interfaces to create more accessible next-generation tools,” states Dr. Mathis.

“For instance, we recently developed AmadeusGPT, which allows for video data queries through written or spoken text. Expanding this capability for complex behavioral analysis is very exciting.”

Now available to researchers worldwide through its open-source distribution, SuperAnimal promises to transform the field of automated animal behavior analysis.

Potential applications of SuperAnimal

SuperAnimal has diverse applications across multiple fields. In veterinary medicine, it can help monitor animal health and detect early signs of illness. Conservationists can study endangered species’ behavior to develop better protection strategies.

Additionally, neuroscientists may benefit by analyzing animal models to understand brain functions and behaviors.

In agriculture, farmers can use it to monitor livestock, improving welfare and productivity.

Sports scientists can analyze athletic performance in animals, leading to better training methods.

In biomedical research, SuperAnimal can be used to enhance the accuracy of experiments with laboratory animals, reducing human error and improving data reliability, ultimately advancing various scientific and medical fields.

Learning more about Earth’s other animals

In summary, the integration of AI into behavioral studies represents a significant leap forward. Traditional methods rely heavily on human observation, which can introduce biases and inconsistencies.

SuperAnimal eliminates these issues by providing an objective, automated analysis of animal movements. This capability is especially valuable in large-scale studies where manual tracking would be impractical.

With careful oversight, SuperAnimal could pave the way for a new era of ethical and effective animal research.

The full study was published in the journal Nature Communications.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–