Applying the adjoint-free 4dVar assimilation to modeling the Kuroshio south of Japan

Operational ocean nowcast/forecast systems require real-time sampling of oceanic data for representing realistic oceanic conditions. Satellite altimetry plays a key role in detecting mesoscale variability of the ocean currents. The 10-day sampling period and horizontal gaps between the altimetry tracks of 100 km cause difficulties in capturing shorter-term/smaller-scale ocean current variations. Operational systems based on a three-dimensional variational method (3dVar) do not take into account temporal variability of the data within data assimilation time windows. Four-dimensional data assimilation technique is considered as a possible tool for more efficient utilization of the observations arriving from satellite altimeters by the dynamically constrained interpolation. In this study, we develop and test the performance of the adjoint-free four-dimensional variational method (a4dVar) for operational use in regional models. Numerical experiments targeting the Kuroshio path variations south of Japan demonstrate that the a4dVar scheme dynamically corrects the initial condition so as to effectively reduce the satellite altimetry data misfit during a 9-day time window. The corrected initial condition further contributes to improvements in the skill of reconstruction of the Kuroshio path variation in a 30-day lead hindcast run.