Simulation of algal bloom dynamics in a river with the ensemble Kalman filter

Abstract A simulation framework of algal bloom in a river channel with data assimilation (DA) was developed by employing two numerical models coupled to simulate a watershed and the embedded river channel. The Hydrological Simulation Program-Fortran (HSPF) model simulates flow discharge and water quality from the subwatersheds and the Environmental Fluid Dynamics Code (EFDC) model takes the subwatershed model outputs at the watershed-river confluence points as boundary forcing to simulate river hydrodynamics and water quality. The ensemble Kalman filter (EnKF) was used for assimilation of water quality variables in the framework, linking uncertainty of model simulation and observation. The simulation uncertainty of the HSPF was quantified at the confluence points as simple stochastic error models developed by comparing the model simulation and the observation. The error models reflect uncertainty of both hydrologic and water quality simulation, including uncertainty associated with point and non-point pollution sources in the watershed. The outputs of the HSPF at the confluence points were perturbed with the error models before used in the following ensemble simulation of the EFDC for the main river. DA was conducted with weekly chlorophyll- a data observed along the river to update chlorophyll- a concentrations of the EFDC model grids. The results showed that the model performance was improved by the assimilation: the root mean square error (RMSE) and the mean continuous probability rank score (CPRS) significantly decreased compared to the open-loop simulation. The updated spatial distribution of chlorophyll- a concentration along the river channel was in reasonable agreement with the observation. Although only chlorophyll- a data was involved in the assimilation, phosphate was selected among other water quality variables for update in order to evaluate the effect of chlorophyll- a assimilation on those variables. It turned out that the phosphate simulation was not much improved by the chlorophyll- a data, which was due to weak correlation between the two variables in the model ensemble. Lastly, chlorophyll-a simulation uncertainty in the river attributed to the simulation uncertainty of each variable in the watershed was evaluated. For that, two additional simulations were made, with perturbation only to flow and phosphate respectively at the confluence points. The spread of chlorophyll- a ensemble of each case became significantly narrower than the original case, indicating that the difference is attributed to the uncertainty of the other unperturbed variables.