tinyML Talks: Efficient AI for Wildlife Conservation

We require systems to monitor species in real time and in greater detail to quickly understand which conservation and sustainability efforts are most effective and take corrective action. Current ecological monitoring systems generate data far faster than researchers can analyze it, making scaling up impossible without automated data processing. However, ecological data collected in the field presents a number of challenges that current methods, like deep learning, are not designed to tackle. These include strong spatiotemporal correlations, imperfect data quality, fine-grained categories, and long-tailed distributions. Beyond this, many of the areas we seek to monitor are remote, which requires us to work within the constraints of limited bandwidth, power, storage, and computational capacity. I’ll discuss several open challenges in environmental monitoring where more robust, efficient, and adaptable models are needed, and where progress has significant potential for impact.

Date

January 31, 2023

Location

Virtual

Contact us

Discussion

Schedule

Timezone: PST

Efficient AI for Wildlife Conservation

Sara M. BEERY, Visiting Researcher

Google

Sara M. BEERY, Visiting Researcher

Google

Sara Beery is currently a Visiting Researcher at Google where she works on automating urban forest monitoring, and will join MIT as an assistant professor in the Faculty of AI and Decision Making in September 2023. Beery received her PhD in computing and mathematical sciences from Caltech, where she was advised by Pietro Perona and awarded the Amori Doctoral Prize for her thesis. Her research focuses on building computer vision methods that enable global-scale environmental and biodiversity monitoring. She partners with nongovernmental organizations and government agencies to deploy her methods in the wild worldwide and works toward increasing the diversity and accessibility of academic research in AI through interdisciplinary capacity building and education.

Schedule subject to change without notice.