Atlas schedules satellite links to save power for wildlife cameras
ATLAS: Expert-Guided Sustainable Satellite Backhaul for Off-Grid Wildlife Monitoring
Machine Learning
Summary
Monitoring wildlife in remote areas is hard because cameras need power and ways to send data, but there is no electricity or internet there. The authors created Atlas, a system that listens to expert instructions in plain language and decides which videos to send by satellite when energy is limited. It uses smart models to pick relevant clips and manages power and bandwidth carefully to keep running longer. They tested Atlas in river sites watching salmon and found it sent more useful video clips while staying on longer during cloudy days.
What this means in practice
- •For wildlife conservation teams: Deploy monitoring systems that dynamically select and upload key videos to save energy and use satellite connections efficiently in remote locations.
- •For environmental sensor network operators: Manage scarce satellite bandwidth and solar power by programming data transmission schedules that follow expert instructions in natural language.
Authors
Hao Fang, Miao Zhang, Haoyuan Zhao, Long Chen, Yi Ching Chou, Chi Xu, Cheng Pan, Jiangchuan Liu
Abstract
Remote wildlife monitoring increasingly depends on high-fidelity cameras and sensors deployed far from grid power and terrestrial networks. Low Earth orbit satellite links can provide connectivity in these settings, but their high power draw and variable bandwidth, combined with intermittent on-site solar harvesting, make continuous backhaul infeasible. Current systems therefore filter at the edge, with motion triggers that waste limited energy and bandwidth on environmental artifacts, or fixed vision models that cannot follow evolving expert objectives. We present \textsc{ATLAS}, an expert-guided edge-to-cloud system that treats satellite backhaul as a scarce resource for off-grid wildlife monitoring. \textsc{ATLAS} uses foundation models to compile natural-language expert intent into semantic scoring logic, combines semantic relevance with environmental and energy state, and uses a constrained reinforcement-learning scheduler to decide which clips to upload and when. As a representative case study, we deployed \textsc{ATLAS} for over six months across 18 off-grid salmon-monitoring river sites. \textsc{ATLAS} achieves a mean clip-selection accuracy of $87.4\%$, exceeding mean baseline accuracy by $26.4$ percentage points, while maintaining near-continuous operation through low-solar periods in which baselines incur 16.0\% downtime.