The International Union of Biological Sciences (IUBS) was established in 1919 as a non- governmental and non-profit organization comprising of National Academies and international scientific Associations and Societies. Since then IUBS is functioning as a global platform of scientists from all disciplines and nationalities for cooperation, interaction and collaboration to promote research, training, and education in biological sciences.
To commemorate completion of 100 years of promoting excellence in biological sciences, IUBS has launched a Webinar Series bringing the best of all disciplines to discuss evolution, taxonomy, ecology, biodiversity, and other topics that represent unified biology and the topics of prime importance to address contemporary problems such as climate change, endangered species, food and nutrition, health etc.
Our esteemed speakers have included Rattan Lal, 2020 World Food Prize Laureate, discussing “Forgetting How to Tend the Soil”; Sean B. Carroll, renowned biologist and science communicator, on “The Serengeti Rules: The Regulation and Restoration of Biodiversity”; Dr. Jane Goodall, DBE, sharing insights on “Gombe and Beyond”; Yvon Le Maho, presenting “New Technology to Investigate Antarctic Penguins Without Disturbance”, Christine H. Foyer offering expertise in plant metabolism and “how will plants adapt to high CO2 world?” and Prof Luisa Orsini, delivering “The Time Machine Chronicles – Unveiling How the Past Shapes the Future”.
The seventh lecture of the Webinar Series will be delivered by Dr Sara Beery
“Challenges and Opportunities at the Intersection of AI and Biodiversity“
Moderated by Dr Tanya Berger-Wolf
Moderated by Dr Kaustubh Ray
Seventh Lecture of Webinar Series
“Challenges and Opportunities at the Intersection of AI and Biodiversity”
by Dr Sara Beery
Date: 10 October 2024
Time: UTC: 15.00, IST: 20.30 CAT/CET: 17.00, EDT: 11.00, EAT: 18.00
Event Flyer : feel free to share our webinar poster here and spread the word
Video
About the Speaker
Dr Sara Beery is an Assistant Professor at MIT in the EECS department’s Faculty of AI and Decision Making and CSAIL. Previously, she was a visiting researcher at Google, where she worked on Auto Arborist. With a deep passion for the natural world, she focuses on using technology to address conservation and sustainability challenges. Her research develops computer vision methods for global-scale environmental and biodiversity monitoring, tackling issues like domain shift, imperfect data, and long-tailed distributions.
She completed her PhD in Computing and Mathematical Sciences at Caltech, advised by Pietro Perona, and received the Amori Doctoral Prize for her dissertation. She has been awarded the NSF Graduate Research Fellowship, PIMCO Data Science Fellowship, and Amazon AI4Science Fellowship. Her work has received support from NSF, Google, Microsoft, and others.
Committed to bridging gaps between fields, she founded the AI for Conservation slack community and leads the Biodiversity Community for Climate Change AI. She also collaborates with Microsoft AI for Good, Google Research, and Wildlife Insights to turn her research into practical tools for the ecological community.
An advocate for diversity in STEM, her experiences have shaped her commitment to increasing inclusion through mentorship and outreach, recognized by Caltech with several DEI awards.
About the Lecture
We are currently witnessing an unprecedented loss of biodiversity, yet biodiversity is vital to sustainable development, public health, and mitigating climate change. To better understand and hopefully mitigate this loss, natural-world data is being collected at unprecedented scales from networks of ground-level sensors, satellites, drones, DNA collections, and community science platforms. There is valuable scientific information stored in these raw data, the vast majority of which are as-yet inaccessible due to the time and resources needed to process the data by small groups of relevant human experts. AI will prove crucial to facilitate efficient extraction of scientific insight from quickly-growing repositories of natural world data, but in order to realize the goal of global-scale, near-real-time biodiversity monitoring we must shift the AI research paradigm beyond highly curated datasets to capture the complexities of the real world, including strong spatiotemporal correlations, imperfect data quality, fine-grained categories, and long-tailed distributions. Beyond the inherent challenges of the data itself, the target is also moving – taxonomies are constantly debated and in flux, data infrastructure and protocols aren’t standardized, and there are ongoing and important discussions about data ownership, sovereignty, and the risks of sharing data, particularly for at-risk species. I will discuss the implications of these challenges and the impactful new avenues of research they outline at the intersection of AI and Biodiversity, and highlight exciting recent efforts towards AI-enabled biodiversity monitoring that operate within and overcome these constraints.
About the moderator
Tanya Berger-Wolf