ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided Diffusion

TL;DR

ReconMOST is a novel diffusion-based framework that leverages historical simulation data and observational guidance to accurately reconstruct multi-layer sea temperatures globally, even with over 92.5% missing data.

Contribution

This work introduces a physically consistent, data-driven diffusion model for multi-layer sea temperature reconstruction, extending ML methods to a global scale with high accuracy and robustness.

Findings

Achieved low MSE of 0.049 on guidance data

Maintained high reconstruction accuracy with MSE of 0.680

Demonstrated robustness across different datasets and missing data levels

Abstract

Accurate reconstruction of ocean is essential for reflecting global climate dynamics and supporting marine meteorological research. Conventional methods face challenges due to sparse data, algorithmic complexity, and high computational costs, while increasing usage of machine learning (ML) method remains limited to reconstruction problems at the sea surface and local regions, struggling with issues like cloud occlusion. To address these limitations, this paper proposes ReconMOST, a data-driven guided diffusion model framework for multi-layer sea temperature reconstruction. Specifically, we first pre-train an unconditional diffusion model using a large collection of historical numerical simulation data, enabling the model to attain physically consistent distribution patterns of ocean temperature fields. During the generation phase, sparse yet high-accuracy in-situ observational data are utilized as guidance points for the reverse diffusion process, generating accurate reconstruction results. Importantly, in regions lacking direct observational data, the physically consistent spatial distribution patterns learned during pre-training enable implicitly guided and physically plausible reconstructions. Our method extends ML-based SST reconstruction to a global, multi-layer setting, handling over 92.5% missing data while maintaining reconstruction accuracy, spatial resolution, and superior generalization capability. We pre-train our model on CMIP6 numerical simulation data and conduct guided reconstruction experiments on CMIP6 and EN4 analysis data. The results of mean squared error (MSE) values achieve 0.049 on guidance, 0.680 on reconstruction, and 0.633 on total, respectively, demonstrating the effectiveness and robustness of the proposed framework. Our source code is available at https://github.com/norsheep/ReconMOST.