Litcius/Paper detail

Post-Processing a Conceptual Rainfall-Runoff Model with an LSTM

Grey Nearing, Alden Keefe Sampson, Frederik Kratzert, Jonathan Frame

202030 citationsDOIOpen Access PDF

Abstract

Machine learning is becoming an increasingly important part of streamflow forecasting, but as these models to date lack a physical basis, there is a potential that they may produce values that are not realistic. We tested a simple post-processing strategy that uses the outputs from a calibrated conceptual model (the Sacramento Soil Moisture Accounting Model with Snow-17; SAC-SMA) as inputs into a a Long Short Term Memory Network (LSTM). Overall, the SAC-SMA model was improved substantially, while post-processing offered only minor improvements relative to the standalone LSTM. SAC-SMA performance was improved in catchments with more snow. The standalone LSTM was improved in terms of long-term bias, which is likely because the LSTM is not constrained by conservation principles.

Topics & Concepts

SMA*StreamflowComputer scienceSurface runoffSnowArtificial intelligenceHydrology (agriculture)Machine learningMeteorologyAlgorithmDrainage basinEngineeringGeotechnical engineeringCartographyBiologyGeographyEcologyPhysicsHydrology and Watershed Management StudiesHydrological Forecasting Using AICryospheric studies and observations