*Title 1*
Long-term Biodiversity Monitoring at Scale
*Abstract 1*
Comprehensive data on global biodiversity patterns is only obtainable through in-situ distributed sensor networks. However, these multi-device networks are constrained by battery lifetimes, must gather rich data from power-hungry sensors, and yet must be deployed in remote environments for long periods. We look at the feasibility of a prototype multi-sensor device using on-device reinforcement learning for power management.
*Bio 1*
Josh Millar is a PhD based at the NetSys Lab at Imperial-X.
His current research interests include:
- energy-aware ML
- IoT and on-device ML
- applied ML for sustainability
*Title 2*
Collecting Deep Population Data for Amphibians with a Simple Phone and an ML Vision
*Abstract 2*
Climate change is already impacting species ecology and demography yet our understanding remains often dependent on shallow data collection across large areas or short-lived, localised projects elsewhere. Citizen science offers opportunities for survey innovation that can radically change this and deepen our understanding of how species react to climate change and what we could do to enable adaptation. I will present a simple tool using existing technology for monitoring amphibians and a vision for a better tool to build.
*Bio 2*
Silviu Petrovan is a Senior Research Associate at the University of Cambridge working on evidence synthesis and biodiversity conservation, often with a focus on citizen science
