DORS: A Global 1º×1º Monthly Ocean Subsurface Temperature Dataset Using Satellite Observations and Deep Learning (1993-2020)

The reconstruction of the ocean’s 3D thermal structure is essential to the study of the ocean interior processes and global climate change. Satellite remote sensing technology can collect large-scale, high-resolution ocean observation data, but is only at the surface layer. Based on artificial intelligence models, deep ocean remote sensing techniques allow us to retrieve and reconstruct the 3D ocean temperature structure by combining surface remote sensing observations with in-situ float observations. Here, we proposed a new Convolutional Long Short-Term Memory (ConvLSTM) neural network, which combines multisource remote sensing observations and Argo gridded data to reconstruct and produce a new long time-series global ocean subsurface temperature (ST) dataset for the upper 2000 m from 1993 to 2020, which is named Deep Ocean Remote Sensing (DORS) product. The data-driven ConvLSTM model can learn the spatiotemporal features of ocean observation data, and significantly improves the model’s robustness and generalization ability. The validation results show our DORS dataset has high accuracy and quality. Furthermore, the ST structure between DORS and Argo has good consistency in the 3D spatial morphology and distribution pattern, indicating that the DORS dataset has high quality and strong reliability, and well fills the pre-Argo data gaps. From a remote sensing standpoint, the DORS product can provide new and robust data support for ocean interior process and climate change studies. Here, the DORS dataset contains 23 depth layers (from 30 m to 2000 m depth) and is a monthly dataset from 1993 to 2020 with a spatial resolution of 1° × 1°.