Variability of the Indian Ocean (IO) shallow overturning circulation during 1958–2017 was investigated, which consisted of a cross‐equator cell (CEC) and a southern subtropical cell (SSTC). Structures of these shallow cells were examined through the velocity sections and the transport steamfunction patterns based on the newly released Ocean Reanalysis System 5 data set, and the results showed that the returning flows, at the subsurface, of the shallow cells mainly presented at the western boundary while absented in the ocean interior. Strengths of the IO shallow cells were then determined according to the annual‐mean meridional streamfunction profiles. Both the CEC and the SSTC exhibited significant variability on interannual to decadal timescales during 1958–2017, and this variability mainly resulted from changes in both meridional Ekman transports and meridional geostrophic flows in the upper layer, and each component could dominate the shallow cells' variations in certain years. Contributions of the geostrophic currents to the shallow cells were likely opposite to that of the Ekman transport in the South Indian Ocean during years when the latter reached the extremes. The CEC and the SSTC were negatively correlated during the research period. The CEC exhibited a decadal weakening during 2000–2015, contributing to the decadal increasing of the IO heat content, while the SSTC only experienced very little strengthening. Here this paper presents a comprehensively study of the interannual to decadal variability of the IO shallow cells and the corresponding reasons and influences and tried to link these variations with other variations in the IO.

Observation of the ocean is crucial to the studies of ocean dynamics, climate change, and biogeochemical cycle. However, current oceanic observations are patently insufficient, because the in situ observations are of difficulty and high cost while the satellite remote‐sensed measurements are mainly the sea surface data. To make up for the shortage of ocean interior data and make full use of the abundant satellite data, here we develop a data‐driven deep learning model to estimate ocean subsurface and interior variables from satellite‐observed sea surface data. Exclusively and simply using satellite data, three‐dimensional ocean temperature and salinity fields are successfully reconstructed, which are at 26 level depths from 0 to 2,000 m. We further design a scheme to increase the horizontal resolution from 1° to 1/4°, which is higher than the Argo gridded data. Estimations from our model are accurate, reliable, and stable for a wide range of research areas and periods. Dynamic height fields that are derived from the estimated temperature and salinity, as well as the associated ocean geostrophic flows, are also calculated and analyzed, which indicates the potentials of our model for reconstructing the ocean circulation fields as well. This study enriches oceanic observations with respect to vertical dimension and horizontal resolution, which can largely make up for the paucity of the subsurface and deep ocean observation, both before and during Argo era. This work also provides some new foundations for and insights into geoscience and climate change fields.