Machine Learning Students Monitor and Safeguard Whale Populations

In the heart of the University of Pennsylvania, two ambitious students, Chinmay Govind and Nihar Ballamudi, have been making waves in the world of marine conservation. As part of the Penn Undergraduate Research Mentoring Program (PURM), they've been working tirelessly to develop artificial intelligence (AI) models that can accurately locate and count whales using acoustic data and machine learning.

Their mentors, John Spiesberger, a visiting scholar in the Department of Earth & Environmental Science, and his son, Ari Spiesberger, a recent Penn graduate with expertise in machine learning models, have been instrumental in guiding the duo's research. John Spiesberger has emphasised the importance of realistic simulations and variation to mirror ocean settings and produce meaningful data, while Ari Spiesberger has provided additional mentorship on AI models, simulations, and predicting unknown variables.

The AI models, once developed, could potentially be used to retroactively pinpoint the precise location of each whale. Govind has already made significant strides in this area, able to record the origin points of whale calls with a "median error of 20 milliseconds" using machine learning.

Govind's focus has been on locating whales using acoustic data from NOAA receivers and a machine learning model to estimate the origin points of whale calls. Meanwhile, Ballamudi has been working on censusing whales, approximating the size and distribution of whale populations to more effectively monitor their movements.

The findings of Govind and Ballamudi's research could have far-reaching implications. They could help inform policymakers and environmental groups on policies involving whales, and potentially extend to other sea animals as well. The results of this endeavor could be a significant step forward in marine conservation efforts.

The project's goal is to leverage whale sound data and artificial intelligence to map the locations of whales and determine the number living in any given target area. The research funding for this project is provided by the German Research Foundation (Deutsche Forschungsgemeinschaft, DFG).

John Spiesberger has also been coaching Govind and Ballamudi on science communication skills, especially given the environmental policy implications of their work. The duo has already made impressive strides, recently presenting their results to U.S. Navy sponsors, discussing the implications for policymakers, and exploring opportunities for expanding their research.

As the summer research program comes to a close, John Spiesberger aims to secure grants for Govind and Ballamudi to continue their impactful work. The AI models used in the PURM project continually optimize and improve their precision, showing promise for future steps the students could take with this research.

With their innovative AI models and dedication to marine conservation, Govind and Ballamudi are poised to make a significant impact in the field. Their work is a testament to the power of collaboration, mentorship, and the pursuit of knowledge.