Data‐Driven Method With Numerical Model: A Combining Framework for Predicting Subtropical River Plumes.

Numerical models are of fundamental usage for estuarine and coastal sciences. Although numerical simulations are widely applied, analyzing and improving them are often challenging tasks given their large volume and huge parameter space. In this study, a novel data‐driven framework is introduced to study the Minjiang River Plume (MJRP). The framework combines Self‐Organizing Map (SOM) clustering with a Hidden Markov Model (HMM). A three‐dimensional Regional Ocean Model System for MJRP is first configurated with realistic atmospheric, oceanic, and riverine forcings. By applying SOM clustering to the modeled sea surface salinity (SSS) with ∼2,000 2‐day averaged records from 2010 to 2020, we identify six major patterns of MJRP. Each pattern exhibits distinct circulation and plume structures. These MJRP patterns contain not only seasonal signals, but also rich short‐term variabilities driven by the riverine inputs and oceanic dynamics. Then, the SOM‐HMM method was applied to predict the future of the hidden state (i.e., patterns of MJRP) from the observable states (wind and river runoff). With a hypothetic SSS product from a geostationary satellite as the ground truth, we show that the SOM‐HMM method can predict MJRP patterns considerably high prediction accuracy and computational efficiency. Further, these patterns were translated back to SSS with high forecast skills. Combining a conventional numerical model with a data‐driven method, this approach can be promisingly applied in the short‐term marine forecast to support the utilization and management of other estuaries. Plain Language Summary: Analyzing and improving numerical models for estuaries are challenging tasks given the volume and uncertainties of model simulation. By combining a sophisticated machine‐learning method learned from large‐volume model outputs, we show that the performance and efficiency of forecasting the patterns of a river plume can be improved. The method can be further applied to predict the surface salinity of the river, which is a vital property of the river estuary. The prediction can be rapidly done with considerably high accuracy. This study highlights the potential of combining a numerical model with a data‐driven method as a new method to forecast the complex dynamics of a coastal environment. Key Points: A data‐driven framework combining Self‐Organizing Map with Hidden Markov Model was developed for predicting states of river plumesIt was applied to a representative subtropical estuarine environment: the estuary of Minjiang RiverValidated with hypothetic and model surface salinity, this method can indeed predict river plume states and surface salinity [ABSTRACT FROM AUTHOR]