Machine learning assisted hybrid models can improve streamflow simulation in diverse catchments across the conterminous US

Research output: Contribution to journalArticlepeer-review

119 Scopus citations

Abstract

Incomplete representations of physical processes often lead to structural errors in process-based (PB) hydrologic models. Machine learning (ML) algorithms can reduce streamflow modeling errors but do not enforce physical consistency. As a result, ML algorithms may be unreliable if used to provide future hydroclimate projections where climates and land use patterns are outside the range of training data. Here we test hybrid models built by integrating PB model outputs with an ML algorithm known as long short-term memory (LSTM) network on their ability to simulate streamflow in 531 catchments representing diverse conditions across the Conterminous United States. Model performance of hybrid models as measured by Nash–Sutcliffe efficiency (NSE) improved relative to standalone PB and LSTM models. More importantly, hybrid models provide highest improvement in catchments where PB models fail completely (i.e. NSE < 0). However, all models performed poorly in catchments with extended low flow periods, suggesting need for additional research.

Original languageEnglish
Article number104022
JournalEnvironmental Research Letters
Volume15
Issue number10
DOIs
StatePublished - Oct 2020

Keywords

  • Long short-term memory (LSTM) network
  • Machine learning (ML)
  • Process-based hydrologic models
  • Sacramento soil moisture accounting model (SAC)

Fingerprint

Dive into the research topics of 'Machine learning assisted hybrid models can improve streamflow simulation in diverse catchments across the conterminous US'. Together they form a unique fingerprint.

Cite this