Technical Note: Data assimilation and autoregression for using near-real-time streamflow observations in long short-term memory networks
Grey Nearing, Daniel Klotz, Alden Keefe Sampson, Frederik Kratzert, Martin Gauch, Jonathan Frame, Guy Shalev, Sella Nevo
Abstract
Abstract. Ingesting near-real-time observation data is a critical component of many operational hydrological forecasting systems. In this paper we compare two strategies for ingesting near-real-time streamflow observations into Long Short-Term Memory (LSTM) rainfall-runoff models: autoregression (a forward method) and variational data assimilation. Autoregression is both more accurate and more computationally efficient than data assimilation. Autoregression is sensitive to missing data, however an appropriate (and simple) training strategy mitigates this problem.
Topics & Concepts
Data assimilationAutoregressive modelVector autoregressionStreamflowComputer scienceTerm (time)EconometricsMeteorologyMathematicsGeographyDrainage basinQuantum mechanicsPhysicsCartographyHydrology and Watershed Management StudiesHydrological Forecasting Using AIMeteorological Phenomena and Simulations