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

2026-04-13

AI Summary

Satellite-derived sea surface temperature (SST) often fails to accurately represent the sub-surface thermal environment experienced by corals, leading to overestimation of heat stress. To address this limitation, this study proposes a physics-informed neural network (PINN) that integrates satellite SST with sparse in situ temperature observations. For the first time, a one-dimensional vertical heat conduction equation is embedded within the model to jointly invert for the effective thermal diffusivity and light attenuation coefficient, while enforcing satellite SST as a hard boundary condition. Evaluated at four Great Barrier Reef sites, the method achieves depth-resolved temperature prediction root-mean-square errors (RMSE) of 0.25–1.38°C using only sparse observational data, significantly outperforming both statistical and purely physics-based baselines. The approach successfully reconstructs vertical heat stress profiles consistent with in situ measurements.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Constraint Satisfaction and Optimization: Satisfiability
• Search and Optimization: Heuristic Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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°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°C RMSE at unseen depths. Under extreme sparsity (three training depths), the PINN maintains 0.27°C RMSE at the 5 metre holdout and 0.32°C at the 9.1 metre holdout, where statistical baselines collapse to >1.8°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.

Problem

• coral reef
• thermal stress
• sea surface temperature
• depth-resolved temperature
• in-situ loggers

Innovation

• physics-informed neural networks
• depth-resolved thermal field
• coral reef temperature
• satellite SST fusion
• thermal stress attenuation