Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386214063> ?p ?o ?g. }
- W4386214063 endingPage "130107" @default.
- W4386214063 startingPage "130107" @default.
- W4386214063 abstract "Deep learning (DL) models have demonstrated exceptional performance in hydrological modeling; however, they are limited by their inability to output untrained hydrological variables and lack of interpretability compared to process-based hydrological models. We propose a hybrid approach that combines the conceptual EXP-Hydro model with embedded neural networks (ENNs), replacing its internal modules while maintaining adherence to hydrological knowledge. The resulting hybrid model can predict untrained hydrological variables without requiring post-processing or pre-training procedures. We tested 15 hybrid models that replace different internal modules across 569 basins in the contiguous United States using the CAMELS dataset. Additional experiments were conducted to generalize hydrological relationships within ENNs and further use them to improve the EXP-Hydro model's performance. Results show that all hybrid scenarios outperform the ordinary EXP-Hydro model, with an optimal median Nash-Sutcliffe efficiency (NSE) of 0.701 in the evaluation period– comparable to state-of-the-art LSTM and conceptual hydrological model featuring an error-correcting post-processor. Reasonable patterns of runoff and snow-related processes are captured by ENNs in respective hybrid models. We further used the runoff (snow-related) pattern to improve the ordinary EXP-Hydro model with median NSE increasing from 0.496 to 0.567 (raising median NSE from 0.601 to 0.677 in snow-influenced region). . Our study highlights the potential for using ENNs in enhancing process-based hydrological models' performance while maintaining interpretability within a novel hybrid framework." @default.
- W4386214063 created "2023-08-29" @default.
- W4386214063 creator A5014808385 @default.
- W4386214063 creator A5065956745 @default.
- W4386214063 creator A5068525466 @default.
- W4386214063 creator A5078806046 @default.
- W4386214063 date "2023-10-01" @default.
- W4386214063 modified "2023-09-27" @default.
- W4386214063 title "Enhancing process-based hydrological models with embedded neural networks: A hybrid approach" @default.
- W4386214063 cites W1498436455 @default.
- W4386214063 cites W1533757126 @default.
- W4386214063 cites W1649947482 @default.
- W4386214063 cites W1986397813 @default.
- W4386214063 cites W2001317094 @default.
- W4386214063 cites W2033904036 @default.
- W4386214063 cites W2037460094 @default.
- W4386214063 cites W2064675550 @default.
- W4386214063 cites W2137926215 @default.
- W4386214063 cites W2143514530 @default.
- W4386214063 cites W2145507149 @default.
- W4386214063 cites W2169744906 @default.
- W4386214063 cites W2603766970 @default.
- W4386214063 cites W2791711478 @default.
- W4386214063 cites W2800819102 @default.
- W4386214063 cites W2951276077 @default.
- W4386214063 cites W2954648193 @default.
- W4386214063 cites W2969716342 @default.
- W4386214063 cites W2995149074 @default.
- W4386214063 cites W3024402844 @default.
- W4386214063 cites W3034385753 @default.
- W4386214063 cites W3039558631 @default.
- W4386214063 cites W3044346761 @default.
- W4386214063 cites W3092026988 @default.
- W4386214063 cites W3099909056 @default.
- W4386214063 cites W3123180269 @default.
- W4386214063 cites W3137921226 @default.
- W4386214063 cites W3140862400 @default.
- W4386214063 cites W3144909764 @default.
- W4386214063 cites W3150823440 @default.
- W4386214063 cites W3151387141 @default.
- W4386214063 cites W3164913159 @default.
- W4386214063 cites W3177080499 @default.
- W4386214063 cites W3191476701 @default.
- W4386214063 cites W3196659304 @default.
- W4386214063 cites W3206402571 @default.
- W4386214063 cites W3206795426 @default.
- W4386214063 cites W3207392840 @default.
- W4386214063 cites W4205535841 @default.
- W4386214063 cites W4211008135 @default.
- W4386214063 cites W4214747788 @default.
- W4386214063 cites W4226546282 @default.
- W4386214063 cites W4283078118 @default.
- W4386214063 cites W4283160683 @default.
- W4386214063 cites W4296344227 @default.
- W4386214063 cites W4304191791 @default.
- W4386214063 cites W4322732085 @default.
- W4386214063 doi "https://doi.org/10.1016/j.jhydrol.2023.130107" @default.
- W4386214063 hasPublicationYear "2023" @default.
- W4386214063 type Work @default.
- W4386214063 citedByCount "0" @default.
- W4386214063 crossrefType "journal-article" @default.
- W4386214063 hasAuthorship W4386214063A5014808385 @default.
- W4386214063 hasAuthorship W4386214063A5065956745 @default.
- W4386214063 hasAuthorship W4386214063A5068525466 @default.
- W4386214063 hasAuthorship W4386214063A5078806046 @default.
- W4386214063 hasConcept C111919701 @default.
- W4386214063 hasConcept C119857082 @default.
- W4386214063 hasConcept C121332964 @default.
- W4386214063 hasConcept C126197015 @default.
- W4386214063 hasConcept C127313418 @default.
- W4386214063 hasConcept C153294291 @default.
- W4386214063 hasConcept C154945302 @default.
- W4386214063 hasConcept C187320778 @default.
- W4386214063 hasConcept C18903297 @default.
- W4386214063 hasConcept C197046000 @default.
- W4386214063 hasConcept C2781067378 @default.
- W4386214063 hasConcept C39432304 @default.
- W4386214063 hasConcept C41008148 @default.
- W4386214063 hasConcept C49204034 @default.
- W4386214063 hasConcept C50477045 @default.
- W4386214063 hasConcept C50644808 @default.
- W4386214063 hasConcept C76886044 @default.
- W4386214063 hasConcept C86803240 @default.
- W4386214063 hasConcept C98045186 @default.
- W4386214063 hasConceptScore W4386214063C111919701 @default.
- W4386214063 hasConceptScore W4386214063C119857082 @default.
- W4386214063 hasConceptScore W4386214063C121332964 @default.
- W4386214063 hasConceptScore W4386214063C126197015 @default.
- W4386214063 hasConceptScore W4386214063C127313418 @default.
- W4386214063 hasConceptScore W4386214063C153294291 @default.
- W4386214063 hasConceptScore W4386214063C154945302 @default.
- W4386214063 hasConceptScore W4386214063C187320778 @default.
- W4386214063 hasConceptScore W4386214063C18903297 @default.
- W4386214063 hasConceptScore W4386214063C197046000 @default.
- W4386214063 hasConceptScore W4386214063C2781067378 @default.
- W4386214063 hasConceptScore W4386214063C39432304 @default.
- W4386214063 hasConceptScore W4386214063C41008148 @default.
- W4386214063 hasConceptScore W4386214063C49204034 @default.