Depth-Resolved Coral Reef Thermal Fields from Satellite SST and Sparse In-Situ Loggers Using Physics-Informed Neural Networks

arXiv cs.LG / 4/16/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper argues that satellite sea surface temperature (SST) products can overestimate coral bleaching thermal stress because they reflect only the ocean skin, while coral habitats span depths that can be 1–3°C cooler than the surface.
It proposes a physics-informed neural network (PINN) that fuses NOAA Coral Reef Watch SST with sparsely sampled in-situ temperature loggers by solving the 1D vertical heat equation and enforcing SST as a hard boundary condition.
The PINN jointly learns effective thermal diffusivity and light attenuation, and is validated on four Great Barrier Reef sites using 30 holdout experiments with reported RMSEs of 0.25–1.38°C at unseen depths.
Even under extreme sparsity (training using only three depths), the method maintains low error at holdout depths (0.27°C at 5 m and 0.32°C at 9.1 m), outperforming a physics-only finite-difference baseline in 90% of trials.
Depth-resolved Degree Heating Day (DHD) profiles show thermal stress attenuates with depth (e.g., Davies Reef DHD declines from 0.29 at the surface to zero by 10.7 m), but the PINN may underestimate shallow, short-duration peaks—so its DHD should be treated as a conservative lower bound for threshold exceedances.

Abstract

Satellite sea surface temperature (SST) products underpin global coral bleaching monitoring, yet they measure only the ocean skin. Corals inhabit depths from the shallows to beyond 20 metres, where temperatures can be 1-3{\deg}C cooler than the surface; applying satellite SST uniformly to all depths therefore overestimates subsurface thermal stress. We present a physics-informed neural network (PINN) that fuses NOAA Coral Reef Watch SST with sparse in-situ temperature loggers within the one-dimensional vertical heat equation, enforcing SST as a hard surface boundary condition and jointly learning effective thermal diffusivity (\k{appa}) and light attenuation (Kd). Validated across four Great Barrier Reef sites (30 holdout experiments), the PINN achieves 0.25-1.38{\deg}C RMSE at unseen depths. Under extreme sparsity (three training depths), the PINN maintains 0.27{\deg}C RMSE at the 5 metre holdout and 0.32{\deg}C at the 9.1 metre holdout, where statistical baselines collapse to >1.8{\deg}C; it outperforms a physics-only finite-difference baseline in 90% of experiments. Depth-resolved Degree Heating Day (DHD) profiles show that thermal stress attenuates with depth: at Davies Reef, DHD drops from 0.29 at the surface to zero by 10.7 metres, consistent with logger observations, while satellite DHD remains constant at 0.31 across all depths. However, the PINN underestimates absolute DHD at shallow depths because its smooth predictions attenuate the short-duration peaks that drive threshold exceedances; PINN DHD values should be interpreted as conservative lower bounds on depth-resolved stress. These results demonstrate that physics-constrained fusion of satellite SST with sparse loggers can extend bleaching assessment to the depth dimension using existing observational infrastructure.