Data-driven robotic sampling for marine ecosystem monitoring

TLDR

Robotic sampling is increasingly used in earth sciences, and in marine ecosystem monitoring it enables laboratory analysis of plankton while real‑time sensor data can guide sample collection. The study proposes a data‑driven, opportunistic sampling strategy that minimizes cumulative regret for batches of plankton samples collected by an autonomous underwater vehicle across multiple surveys. After each survey, collected samples are labeled and used to update a probabilistic model that informs online, irrevocable sampling decisions for the next survey; the approach was validated through extensive simulations and a one‑day field trial that began with a prior model from earlier data. The field trial demonstrated, for the first time, a fully data‑driven “closed‑loop” sampling system that achieved high abundance of a target plankton species and empowered marine ecologists to set mission objectives at a high level.

Abstract

Robotic sampling is attractive in many field robotics applications that require persistent collection of physical samples for ex-situ analysis. Examples abound in the earth sciences in studies involving the collection of rock, soil, and water samples for laboratory analysis. In our test domain, marine ecosystem monitoring, detailed understanding of plankton ecology requires laboratory analysis of water samples, but predictions using physical and chemical properties measured in real-time by sensors aboard an autonomous underwater vehicle (AUV) can guide sample collection decisions. In this paper, we present a data-driven and opportunistic sampling strategy to minimize cumulative regret for batches of plankton samples acquired by an AUV over multiple surveys. Samples are labeled at the end of each survey, and used to update a probabilistic model that guides sampling during subsequent surveys. During a survey, the AUV makes irrevocable sample collection decisions online for a sequential stream of candidates, with no knowledge of the quality of future samples. In addition to extensive simulations using historical field data, we present results from a one-day field trial where beginning with a prior model learned from data collected and labeled in an earlier campaign, the AUV collected water samples with a high abundance of a pre-specified planktonic target. This is the first time such a field experiment has been carried out in its entirety in a data-driven fashion, in effect “closing the loop” on a significant and relevant ecosystem monitoring problem while allowing domain experts (marine ecologists) to specify the mission at a relatively high level.