Arizona State University is continuous the legacy of scientist, conservationist and ethologist Jane Goodall by bringing many years of analysis into the digital age utilizing AI.
In March 2022, the Jane Goodall Institute began a collaboration with ASU primatologist Ian Gilby to host over 60 years of Gombe analysis information on the Institute of Human Origins. The archive incorporates handwritten and digital supplies that embody every day observations of wild chimpanzees in Gombe National Park, associated ecological information and quite a few artifacts. The many years of paper are housed in fire- and waterproof cupboards, all funded by beneficiant donors.
Now, a group of ASU school, pupil researchers and AI engineers are exploring methods to remodel the handwritten field notes from Tanzania into searchable, analyzable digital information recordsdata. This effort will complement and contribute to the brand new Gombe AI Research Platform, underneath improvement by the Jane Goodall Institute.
“There’s a lot of value to these data,” stated Gilby, a analysis scientist on the Institute of Human Origins and an affiliate professor on the School of Human Evolution and Social Change.
“They help us understand more about human origins, and more about the complex nature of chimpanzee behavior and ecology. A better understanding of their biology and behavior gives a better chance of protecting this iconic endangered species,” Gilby stated.
Translating the info from paper sheets to digital data, nevertheless, has proved time-intensive. That’s the place Gilby turned to ASU Enterprise Technology’s AI Acceleration group for help.
Accelerating conservation analysis with AI
For over six many years, the group on the Jane Goodall Institute’s Gombe Stream Research Center in Tanzania has collected every day information data on a checkbox-style doc referred to as a Tiki sheet. The researchers comply with a single, “focal” chimpanzee all day and file information factors that embody the arrival and departure instances of different chimpanzees into the focal chimpanzee’s subgroup, feeding bouts and encounters with different species.
Over the years, a whole lot of 1000’s of data have been collected and are saved within the Jane Goodall Institute’s Gombe Research Archive on ASU’s Tempe campus.
A group of pupil researchers has been manually getting into the knowledge collected within the sheets into the challenge’s database. In fall 2025, Gilby turned to the college’s AI Acceleration group for help.
Senior AI improvement engineer Krishna Sriharsha Gundu, half of the AI Acceleration group at ASU, took on the problem.
He labored towards a resolution that will mix machine studying with imaging methods referred to as “vision” to assessment the monitoring sheet and analyze the info on the web page. The group coined the challenge “Gombe AI.”
Taking a scanned picture of the Tiki sheet, the pc imaginative and prescient software program straightens the picture and extracts the info factors. The software program is then capable of digitize the picture into easy rows and columns on Excel spreadsheets. These information can be included into the challenge’s relational database for evaluation.
“We combined this traditional AI technology with newer large language models to review and analyze the handwritten notes written in the margins on the sheets,” Gundu stated.
Gundu developed the code wanted to extract information from the Tiki sheets, information which pupil researcher and information science undergraduate Joesh Jhaj then takes and focuses on the challenge’s interpretation and translation.
“Computer vision translates an image that the computer can then pick up on,” Jhaj stated. “The use of generative AI in this project is to read and translate the handwriting.”
Building on Gundu’s computer-vision preprocessing, Jhaj wrote the interpretation and interpretation code that turns contextual marks into structured analysis information, utilizing GPT’s API to confirm unclear handwriting or ambiguous symbols when wanted.
After the info is digitized, college students who work with the Gombe chimpanzee archive will verify and evaluate the outcomes towards the unique handwritten information sheets.
Jhaj is within the early levels of working with the brand new Gombe AI resolution. The group hopes the software will enhance accuracy in its analyses and be much less time-consuming for information entry. The software may even allow researchers to extra successfully join, handle and replace the Tiki sheet information with the opposite handwritten protocols, video and geospatial information digitized as half of the Gombe AI Research Platform.
“It’s awesome to be able to work with teams across the university and develop unique AI solutions that advance research like this,” Gundu stated.