Spatio-Temporal neighbors adaptive learning with two-point differences for ocean subsurface temperature reconstruction from 1960 to 2022

Long time series and accurate subsurface temperature data in the global ocean are essential for ocean warming and climate change studies. The sparse in situ observations in the pre-Argo era hinder the reconstruction of long-time series observational data for the global ocean. This study proposes a novel Adaptive Spatio-TEmporal Neighbors with two-point differences (ASTEN) method for subsurface temperature reconstruction, which adaptively learns and adjusts spatio-temporal neighbors depending on the distribution of in situ observations to ensure robust gaps-filling performance across four dimensions. By integrating geoscience domain knowledge and utilizing spatiotemporal autocorrelation, ASTEN simultaneously learns the spatial pattern and temporal variation of subsurface temperature, and significantly enhances the interpretability and accuracy of ocean temperature reconstructions over a long time series compared to the DINCAE and DINEOF. The ASTEN reconstructed temperature data for the upper 1000 m from 1960 to 2022 can effectively track the ocean warming process for more than six decades. This study demonstrates the ASTEN method is well suited for subsurface temperature reconstruction, and holds great potential in the gaps-filling of sparse ocean observations with high missing rates over a large scale. The new reconstruction of subsurface temperature can effectively reduce the uncertainty of subsurface ocean warming analysis.