The Indonesian Throughflow (ITF) is a key component of the ocean thermohaline circulation, crucial for the transport of materials and heat in the global ocean and atmosphere. Due to the complex hydrodynamic conditions and current patterns in the Indonesian seas, accurate predictions of the ITF face multiple challenges including the lack of long-term, simultaneous observations across various straits. In this study, we employ a deep-learning approach to examine to what degree known sea level variations can determine the main in- and outflows through the Indonesian seas and which strait is most critical to the determination of ITF variability. The approach is first validated using model simulations and reanalysis data. Our results indicate that an improved Convolutional Neural Network (CNN) combined with a Recurrent Neural Network (RNN) model helps to effectively represent the temporal variations of throughflows across the Indonesian seas. The skills can be significantly improved if aided by time series of transport from a small number of passages. Overall, the OSSEs suggest that a better realization of transport variability in the Maluku Strait could benefit the comprehensive assessment of the ITF.

ITF transport simulation, deep learning, sea level reflect transport