Southern Adventist University Utilizes AI Model for Paleontology
11 December 2024 |
Southern Adventist University’s Biology and Allied Health Department and School of Computing have partnered to harness artificial intelligence (AI) to classify dinosaur teeth. A specific form of AI called deep learning uses artificial neural networks to learn from data and solve complex problems.
The idea originated in the fall of 2022 through Harvey Alférez, PhD, professor and director of the Center for Innovation and Research in Computing (CIRC) in the School of Computing, and Keith Snyder, PhD, chair of the Biology and Allied Health Department. Traditionally, fossils would be identified manually by calculating the geometry and characteristics of the bones. Utilizing deep learning AI can streamline the process by identifying, classifying, and then organizing the fossils accordingly.
Jacob Bahn, one of Alférez’s graduate students, was instrumental in the project’s development. Initially looking for a master’s thesis topic, Bahn joined the project in October 2022 and got to work inputting a data set of 487 images from Snyder’s collection of microfossilized Pectinodon bakkeri teeth discovered during a dig in Wyoming.
According to a press release from Southern Adventist University:
“Bahn first organized numerical values based on certain features of the dinosaur teeth into a file before running machine-learning algorithms on it. As a result, he was able to create three different groupings of the teeth. Next, these groupings were used to train a deep learning model that would automatically classify the images. Eighty percent of Snyder’s images were used for training, and after a cleaning process, the other 20 percent were used to validate the model.
The deep learning model was trained on the new GPU server in the School of Computing, which was purchased with funds from a research grant provided by the Faith and Science Council of the General Conference of Seventh-day Adventists, as well as donations from Southern’s 2022 Giving Day.”
Though Bahn is a software engineer for the Tennessee Valley Authority, this was his first time working with the AI program, and the results have been rewarding. At this point, the model has 71% accuracy, 71% precision, 70.5% recall, and a 70.5% F1 score, which marks the model’s reliability in its intended context.
This project is the first of its kind for Southern and has opened the door for other departmental partnerships with AI programming.
