Deep Learning-Enabled Dissolved Oxygen Sensing in Biofouling Environments for Ocean Monitoring

TL;DR

This paper presents a novel camera-based dissolved oxygen sensor combined with a ViT-PINN model that effectively mitigates biofouling effects, enabling accurate long-term ocean monitoring.

Contribution

It introduces a physics-informed neural network with a visual transformer that enhances dissolved oxygen sensing under biofouling conditions.

Findings

Reduced MAE by 92% and 89% compared to classical methods.

Achieved approximately 2 umol/L absolute error in measurements.

Enabled self-diagnostic sensing through deep ensemble uncertainty quantification.

Abstract

The escalating climate crisis and ecosystem degradation demand intelligent, low-cost sensors capable of robust, long-term monitoring in real-world environments. Absolute dissolved oxygen (DO) concentration is a key parameter for predicting climate tipping points. Inexpensive optoelectronic sensors based on microstructured polymer films doped with phosphorescent dyes could be readily deployable; however, signal drift and marine biofouling remain major challenges. Here, we introduce a sensing paradigm that combines camera-based DO sensors with a visual transformer (ViT)-based physics-informed neural network (PINN) for high-fidelity sensing under biofouling conditions. Training and testing data were obtained from an algae-laden water tank over 14 days to capture accelerated biofouling. The ViT-PINN, which embeds the Stern-Volmer (SV) equation into the loss function, reduces mean average error (MAE) by 92% and 89% compared to classical statistical and ML approaches, achieving ~2 umol/L absolute error. A deep ensemble further quantifies predictive uncertainty, enabling self-diagnostic sensing.