Robustness Verification of an Autonomous Underwater Vehicle-based Plankton Classifier

2026-07-05

AI Summary

This study addresses the susceptibility of existing AI-based plankton classifiers to noise and non-biological artifacts in dynamic underwater environments, which frequently leads to misclassifications and necessitates extensive manual verification. To overcome this limitation, the authors propose a robustness verification framework that integrates Neural Ordinary Differential Equations (Neural ODEs) with reachability analysis. Leveraging high-resolution in situ imaging data from the SilCam system, this approach enables, for the first time, formal verification of plankton classification models under environmental perturbations. The resulting method provides autonomous underwater vehicle (AUV) platforms with a provably reliable automated filtering mechanism, significantly reducing the need for post-deployment human intervention while ensuring sampling stability.

Abstract

The assessment of planktonic standing stocks and microorganism structures is critical for understanding upper ocean biological processes. Currently, autonomous underwater vehicles (AUVs) equipped with in-situ optical imaging and artificial intelligence (AI) methods offer a promising solution for persistent surveillance, mapping and monitoring of planktonic life. However, current AI methods often lack robustness in dynamic, unstructured environments, where environmental noise and non-biological artifacts lead to frequent misclassifications. Standard convolutional neural network (CNN) classifiers often struggle with such conditions, leading to misclassifications that require time-consuming manual validation by marine biologists. To address this issue, we propose a novel robustness verification framework for in-situ plankton classifiers based on reachability analysis. We also introduce a continuous-time neural ordinary differential equation (neural ODE) classification model leveraging the high-resolution imaging capabilities of the SilCam particle imager. In this paper, we demonstrate the effectiveness of the proposed framework by formally verifying the robustness of the neural ODE model against environmental perturbations. We demonstrate that our verification framework acts as an automated filter providing formal guarantees of model stability against ambiguous data, thereby improving the reliability of autonomous sampling and reducing the post-processing workload.

Problem

• robustness
• plankton classification
• autonomous underwater vehicle
• environmental perturbations
• misclassification

Innovation

• robustness verification
• neural ODE
• reachability analysis
• autonomous underwater vehicle
• in-situ plankton classification