The Xiamen Symposium on Marine Environmental Sciences (XMAS 2025)

In 1987, Klaus Wyrtki proposed that the Indonesian Throughflow is governed by a strong pressure gradient. He examined this hypothesis by comparing the modelled ITF transport and observed sea level difference between Davao in the Philippines and Darwin in Australia. He concluded that ENSO has “little influence on the sea level difference”, but also pointed out that “a determination of” the mechanism of the through flow “will have to await direct measurements”. In this presentation, we will summarize previous studies about the ITF, present the mechanism of ITF’s interannual variability. We have estimated the time series of ITF transport using sea level measurements from satellites and compared it with direct observations. Following Wyrtki’s idea, we used a deep-learning approach with the convolutional neural network (CNN) model to reproduce ITF transport with sea surface height. A test of the training results showed that the CNN model with SSH is able to reproduce approximately 90% of the total variance of ITF transport. A time series of ITF transport, verified by Monitoring the ITF (MITF) and International Nusantara Stratification and Transport (INSTANT) measurements of ITF, was then produced by the model using satellite observations from 1993 to 2021. We further found that the CNN model can make a valid prediction with a lead time of 7 months, implying that the ITF transport can be predicted using the deep-learning approach with SSH data.

Indonesian Throughflow (ITF),Indo-Pacific,Wind-driven circulation