ICICLE will build and prove its system around three application domains: Smart Foodsheds, Digital Agriculture, and Animal Ecology. The team will use edge devices such as drones and remote sensing platforms to map, monitor, and design the underlying topology, species composition, and function of a landscape to co-design an AI-enabled Cyberinfrastructure which, in turn, will enhance food security, allow superior digital management of agricultural production, and help us better understand the movement and behavior of animals in the context of habitats.
Smart Foodsheds integrate the many functions in our complex food systems including production, processing, distribution, preparation, and diet-related health in ways that simultaneously improve environmental, social and economic outcomes for everyone from producers to consumers. Cyberinfrastructure and data from throughout a foodshed, including production, supply chain networks, waste streams, public health and healthcare systems, and more will allow AI approaches for predicting practices that increase resilience and assessing tradeoffs among policy scenarios.
Digital Agriculture aims to develop prescriptive and trustworthy models for crop care and water management. Data for both in-field and regional decisions would come from a variety of in situ (e.g., IoT field sensors), land-based (e.g., agricultural field machinery), and remote (e.g., UAV and satellite) sensors designed to assess biotic and abiotic crop stressors. Real-time sensor data will be combined with historical weather and cropping patterns to generate actionable management information at multiple scales.
An Animal Ecologist may study animal social behavior and movement across landscapes, working at scales ranging from individuals to entire groups, while examining changes due to habitat context and conditions. To derive data-enriched scientific inferences, the ecologist must combine data from a variety of sources including images from satellites, drones, camera traps, and hand-held cameras, point cloud scans, and GPS tracks from on-body animal sensors, working in highly distributed asynchronous iterative settings.