Long-term outdoor localisation with battery-powered devices remains an unsolved challenge, mainly due to the high energy consumption of GPS modules. The use of inertial sensors and short-range radio can reduce reliance on GPS to prolong the operational lifetime of tracking devices, but they only provide coarse-grained control over GPS activity. An alternative yet promising approach is to use context-sensitive mobility models to guide scheduling and sampling decisions in localisation algorithms. In this talk, I will present our work towards continental-scale long-term tracking of flying foxes, as part of the National Flying Fox Monitoring Program, using a model-driven approach. At the core of our approach is the multimodal GPS-enabled Camazotz sensor node platform that has been designed at CSIRO for flying fox collars, with a cumulative weight of below 30g. The talk will cover our recent experience with trialling these platforms in the field on live flying foxes to collect multimodal sensor data for developing models of their mobility. I will also discuss the road ahead for designing adaptive model-driven algorithms for energy-efficient localisation.