Compact models for adaptive sampling in marine robotics

Finding high-value locations for in situ data collection is of substantial importance in ocean science, where diverse bio-physical processes interact to create dynamically evolving phenomena. These cover a variable spatial extent, and aresparse and difficult to predict. Autonomous robotic platforms can sustain themselves in harsh conditions with persistentpresence, but require deployment at the correct place and time. To that end, we consider the use of remote sensing datafor building compact models that can improve skill in predicting sub-mesoscale features and inform onboard sampling.The model enables prediction of regional patterns based on sparse in situ data, a capability that is essential in regionswhere use of satellite remote sensing in real time is often limited by cloud cover. Our model is based on classification ofsea-surface temperature (SST) images, but the technique is general across any remotely sensed parameter. Images havingsimilar magnitude and spatial patterns are grouped into a compact set of conditional means representing the dominantstates. The classification is unsupervised and uses a combination of dictionary learning and hierarchical clustering. Themethod is demonstrated using SST images from Monterey Bay, California. The consistency of the classification result isverified and compared with oceanographic forcing using historical wind measurements. The established model is thenshown to work in a real application using measurements from an autonomous surface vehicle (ASV), together with fore-cast and sampling strategies. Finally an analysis of the model prediction error is presented and compared across differentpaths and survey duration