Lily Xu knew from a young age how important the environment and conservation were to her.
At 9 years old, she had already decided to eat vegetarian because, as she said, “I didn’t want to hurt the animals”.
Xu grew up believing that his passions would always be separated from his professional interest in IT. Then she became a graduate student at Milind Tambe’s Teamcore Lab, and everything changed.
Xu is currently conducting award-winning research into the use of machine learning and artificial intelligence to help conservation and anti-poaching efforts around the world. His recent article, “Learning, optimization and planning under uncertainty for wildlife conservation”, won the 2021 INFORMS Doing Good with Good OR Student Paper Competition.
“From our first conversations, it was clear that Lily was very passionate about sustainability, conservation and the environment,” said Tambe, Gordon McKay professor of computer science at Harvard John A. Paulson School of Engineering and Applied Sciences ( SEAS). “It was also the reason our wavelengths matched and I did everything I could to recruit her and make sure she joined my group.”
In the Teamcore Lab, Xu helped develop Protection Assistant for Wildlife Security (PAWS), an artificial intelligence system that interfaces with a database used by park rangers to record illegal poaching sightings and predict which areas are likely to be poaching hot spots. The system makes it easier for rangers to choose the best locations to patrol.
In 2019, Xu and Teamcore Lab have partnered with Srepok Wildlife Sanctuary in Cambodia to test the effectiveness of PAWS. At the time, the sanctuary had only 72 rangers to patrol an area slightly larger than the state of Rhode Island.
“Our work with Cambodia has been the most intensive collaboration with a park that we have had,” said Xu. “We’ve had several months of meetings, and our interactions with them and the feedback they gave us on the process really shaped the design of our algorithms. ”
Xu played a leading role in the implementation of the PAWS program field tests. Thanks to Tambe, Xu, and his lab comrades, Srepok’s rangers dramatically increased the number of poacher traps they removed throughout the sanctuary.
“Lily led and took PAWS from a small research concept to a global impact research effort leading to the removal of thousands of deadly animal traps, saving endangered wildlife globally,” said Tambe. “Lily led a global effort that made PAWS software available worldwide in hundreds of national parks. This is a true global impact, aimed at saving endangered wildlife around the world.
Xu has always loved nature, but didn’t have the opportunity to experience it growing up in the Maryland suburb of Washington, DC After arriving at Dartmouth College as an undergraduate student in 2014 , she was finally able to immerse herself in the outdoors.
“I first went hiking and camping as part of my first year orienteering trip, just fell in love with it, and then spent as much time as possible at the outside, ”she said. “It made me even more aware of the value of the natural environment and how much I want to do my part to preserve it.”
She eventually began to help organize the Dartmouth freshman trip and took on leadership roles with the second trip and the school’s canoe club. Xu didn’t just want to experience nature, she wanted others to care about it too.
This continued at Harvard, where she has mentored four students since the summer of 2020 and served on several mentoring teams.
“I care a lot about mentoring at all levels, whether it’s taking people out of their comfort zone, encouraging them to explore the outdoors and realizing that it’s a place for them.” , Xu said. “The outdoor community is traditionally wealthy and traditionally white. I’m neither of those things, and I really want to encourage others and show them that this can be their space too. Likewise, from a computational point of view, this is a traditionally male dominated field, and especially in AI research, it has traditionally been the people of the western world.
Xu has published several award-winning publications through his work on PAWS. An article presented to the 35th Association for the Advancement of Artificial Intelligence, “Dual-Mandate Patrols: Multi-Armed Bandits for Green Security”, was named the winner of the award for best article among the top six articles out of nearly 1 700 articles accepted. , while another publication, “Enhancing Poaching Predictions for Under-Resourced Wildlife Conservation Parks Using Remote Sensing Imagery,” won the award for best lightning article at the Machine Learning for Development workshop at the 34th Conference on neural information processing systems in 2020.
Xu strives to address these disparities as a member of Mechanism Design for Social Good (MD4SG), a multi-school, multidisciplinary research initiative that organizes working groups and symposium series to meet the needs of poor communities. served and marginalized around the world. . Xu joined MD4SG in 2020 as a co-organizer of the group’s environmental working group, and last March became a co-organizer of the entire organization.
“I thought to myself, ‘Oh, this sounds like a phenomenal opportunity, because I don’t really know a strong community of computer scientists working on environmental challenges, and I would love to help foster a community,” said Xu. “Our task force, for example, was really able to bring in people from all over the world.”
“It’s fantastic to work with her in all of these areas,” said Bryan Wilder, PhD ’21, former member of the Teamcore lab and member of the MD4SG leadership team. “She has the combination of being incredibly engaged and energetic and really making a difference, while just being a nice person to work with.”
For Xu, research isn’t just about publishing – it’s about building relationships and fostering community engagement.
“We’re researchers who don’t just try to get your datasets, publish an article and then walk away,” Xu said. “We’re here for the long haul. We are determined. We want to get curatorial results as much as we want to get academic publications. “