The Physical Limit of Neural Hypoxia Detection in the Black Sea from Satellite Observations

TL;DR

This study explores the limits of satellite-based neural network methods to detect hypoxia in the Black Sea, revealing current capabilities and challenges in subsurface oxygen estimation.

Contribution

It introduces a deep generative neural network approach to infer Black Sea hypoxia states from satellite data, highlighting the physical and methodological limits.

Findings

Accurate hypoxia detection is limited to the mixed layer due to surface homogeneity.

The method detects 38% of hypoxic events with 47% precision during summer.

Improving detection may require longer data assimilation or sub-surface observations.

Abstract

Coastal hypoxia (O_2 < 63 [mmol / m^3]) threatens ocean health worldwide. On continental shelves, summer stratification prevents bottom oxygen consumed by respiration from being renewed, making monitoring essential to protect vulnerable ecosystems and reduce biodiversity loss. Although satellite observations are increasingly available, their potential to infer subsurface oxygen remains largely unexplored. This can be framed as a Bayesian inverse problem relating surface observations to the complete Black Sea states. Here, we solve it using a deep generative neural network trained on numerical model outputs, providing a tractable and computationally efficient approximation of the true posterior distribution of sea states. We find that accurate state estimation is limited to the mixed layer, because its homogeneity makes surface conditions representative of subsurface states. During summer, we detect 38% of all hypoxic events shelf-wide with a precision of 47%. Improving results will likely require longer assimilation windows or sub-surface observations.