Two algorithms based on machine learning neural networks are proposed—the shallow learning (S‐L) and deep learning (D‐L) algorithms—that can potentially be used in atmosphere‐only typhoon forecast models to provide flow‐dependent typhoon‐induced sea surface temperature cooling (SSTC) for improving typhoon predictions. The major challenge of existing SSTC algorithms in forecast models is how to accurately predict SSTC induced by an upcoming typhoon, which requires information not only from historical data but more importantly also from the target typhoon itself. The S‐L algorithm composes of a single layer of neurons with mixed atmospheric and oceanic factors. Such a structure is found to be unable to represent correctly the physical typhoon‐ocean interaction. It tends to produce an unstable SSTC distribution, for which any perturbations may lead to changes in both SSTC pattern and strength. The D‐L algorithm extends the neural network to a 4 × 5 neuron matrix with atmospheric and oceanic factors being separated in different layers of neurons, so that the machine learning can determine the roles of atmospheric and oceanic factors in shaping the SSTC. Therefore, it produces a stable crescent‐shaped SSTC distribution, with its large‐scale pattern determined mainly by atmospheric factors (e.g., winds) and small‐scale features by oceanic factors (e.g., eddies). Sensitivity experiments reveal that the D‐L algorithms improve maximum wind intensity errors by 60–70% for four case study simulations, compared to their atmosphere‐only model runs.

The Maritime Continent (MC) plays a vitally important role in the Earth's climate system from both oceanic and atmospheric perspectives. While the critical role of ocean‐atmosphere coupled dynamics over the MC has long been recognized, development of two‐way coupled regional climate models for this region is still in its early stages. In this work, the authors review recent progress in two‐way coupled ocean‐atmosphere regional climate modeling. Development of coupled models and their applications in the MC are summarized. Model performances are discussed with a focus on regional oceanic and atmospheric characteristics. Through a critical review of modeling advances and limitations in simulating sea surface temperature, precipitation, and oceanic throughflows, the authors identify deficiencies of current models and discuss possible reasons. The review shows that model biases mainly stem from unresolved physical processes, inadequate model representations of the coupled system, and uncertainties in model configurations. The study reveals large‐scale coupled modes of variability, local air‐sea interactions, atmospheric dynamics, and oceanic processes play various roles in the observed modeling biases. Lastly, the authors offer suggestions on emerging opportunities for improving regional coupled modeling over the MC.

The Indonesian Throughflow (ITF) inflow through the Sulawesi, Maluku, and Halmahera Seas and the ITF outflow into the eastern tropical Indian Ocean, based on reanalysis and model data, are used to investigate the interannual to decadal response of the ITF vertical profile to Indo‐Pacific forcing. The thermocline (upper 300 m) inflow, driven by the North Pacific Ocean, negatively responds to El Niño‐Southern Oscillation (ENSO) with almost no lag; while the thermocline outflow lags by 5–7 months. The sub‐thermocline (300–760 m) inflow, which is influenced by both the North and South Pacific, positively responds to ENSO and Interdecadal Pacific Oscillation (IPO) indices with 13 months lag and displays a long‐term trend tracking the IPO index. Influenced by eastern Indian Ocean variations, the sub‐thermocline outflow positively correlates with the ENSO and IPO indices with about 7–9 months lag, a shorter lag time than the inflow.

Climatological high resolution coupled climate model simulations for the maritime continent have been carried out using the regional climate model (RegCM) version 3 and the finite volume coastal ocean model (FVCOM) specifically designed to resolve regions characterized by complex geometry and bathymetry. The RegCM3 boundary forcing is provided by the EMCWF-ERA40 re-analysis. FVCOM is embedded in the Global MITgcm which provides boundary forcing. The domain of the coupled regional model covers the entire South China Sea with its through-flow, the entire Indonesian archipelago with the Indonesian through-flow (ITF) and includes a large region in the western Pacific and eastern Indian oceans. The coupled model is able to provide stable and realistic climatological simulations for a specific decade of atmospheric–oceanic variables without flux correction. The major focus of this work is on oceanic properties. First, the coupled simulation is assessed against ocean-only simulations carried out under two different sets of air–sea heat fluxes. The first set, provided by the MITgcm, is proved to be grossly deficient as the heat fluxes are evaluated by a two-dimensional, zonally averaged atmosphere and the simulated SST have anomalous cold biases. Hence the MITgcm fluxes are discarded. The second set, the NCEP re-analysis heat fluxes, produces a climatological evolution of the SST with an average cold bias of ~−0.8 °C. The coupling eliminates the cold bias and the coupled SST evolution is in excellent agreement with the analogous evolution in the SODA re-analysis data. The detailed comparison of oceanic circulation properties with the International Nusantara Stratification and Transport observations shows that the coupled simulation produces the best estimate of the total ITF transport through the Makassar strait while the transports of three ocean-only simulations are all underestimated. The annual cycle of the transport is also very well reproduced. The coupling also considerably improves the vertical thermal structure of the Makassar cross section in the upper layer affected by the heat fluxes. On the other hand, the coupling is relatively ineffective in improving the precipitation fields even though the coupled simulation captures reasonably well the precipitation annual cycle at three land stations in different latitudes.

Sea surface temperature cooling (SSTC) induced by tropical cyclones (TCs) could produce a significant impact on the TC intensity. Although a coupled atmosphere‐ocean model could provide such SSTC, various challenges associated with coupled modeling often lead many TC researchers to continue to use atmosphere‐only models. Therefore, the main goal of this study is to develop a fast, robust, and effective parameterization scheme for TC‐induced SSTC that can be used in atmosphere‐only TC models. The following three steps are taken to achieve this goal: (i) Results from an idealized ocean simulation, together with theoretical and temperature budget analyses, are analyzed to isolate each major mechanism causing TC‐induced SSTC, which is then used as a basis for the parameterization; (ii) building upon the idealized ocean simulation, a new SSTC parameterization scheme including vertical mixing, advection, and SST recovery processes under the influences of sea surface height anomalies and ocean subsurface temperature is developed; and (iii) this SSTC parameterization scheme is evaluated through numerical simulations of Typhoon Matsa (2005) and validated against remote sensing data. Results show significant improvements in the simulated TC intensity and SST changes after applying this parameterization scheme. Although further testing with more TC cases is needed, these results are promising, and the parameterization scheme should be compatible with any TC weather prediction model.

Relatively weak hurricane‐induced cooling (<1°C) is often observed in the Loop Current, while observed sea surface temperature (SST) cooling is much stronger in the Kuroshio. This was previously attributed to strong advection effects by the Loop Current. Based on a budget analysis, this study quantitatively diagnoses the dynamic and thermal responses of the Kuroshio to typhoon Megi and four additional tropical cyclones (TCs), which produce up to ~3°C SST cooling within the Kuroshio itself. The results show that the surface thermal response of the Kuroshio is a wind‐induced temperature cooling primarily due to vertical mixing (up to 96%). The dynamic response of the Kuroshio depends not only on TC conditions (intensity and wind direction) but also on prestorm ocean conditions (e.g., ocean mixed layer depth, baroclinicity, and current velocity). Differently from the open ocean where the ocean gains kinetic energy mainly from wind stress work, the Kuroshio can obtain greater kinetic energy from its baroclinic pressure work, especially in the upper ocean. The strong SST cooling observed in the Kuroshio region is therefore likely associated with the kinetic energy extracted from the Kuroshio baroclinic potential energy, which greatly enhances local vertical mixing.