Using a spatio-temporal dynamic state-space model with the EM algorithm to patch gaps in daily riverflow series

A spatio-temporal linear dynamic model has been developed for patching short gaps in daily river runoff series. The model was cast in a state-space form in which the state variable was estimated using the Kalman smoother (RTS smoother). The EM algorithm was used to concurrently estimate both parameter and missing runoff values. Application of the model to daily runoff series in the Volta Basin of West Africa showed that the model was capable of providing good estimates of missing runoff values at a gauging station from the remaining time series at the station and at spatially correlated stations in the same sub-basin.