Matches in SemOpenAlex for { <https://semopenalex.org/work/W1666936902> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W1666936902 abstract "This study investigates how machine learning methods can be used to improve hydraulic head predictions by integrating different types of data, including data from numerical models, in a hierarchical approach. A suite of four machine learning methods (decision trees, instance‐based weighting, inverse distance weighting, and neural networks) are tested in several hierarchical configurations with different types of data from the 317/319 area at Argonne National Laboratory–East. The best machine learning model had a mean predicted head error 50% smaller than an existing MODFLOW numerical flow model, and a standard deviation of predicted head error 67% lower than the MODFLOW model, computed across all sampled locations used for calibrating the MODFLOW model. These predictions were obtained using decision trees trained with all historical quarterly data; the hourly head measurements were not as useful for prediction, most likely because of their poor spatial coverage. The results show promise for using hierarchical machine learning approaches to improve predictions and to identify the most essential types of data to guide future sampling efforts. Decision trees were also combined with an existing MODFLOW model to test their capabilities for updating numerical models to improve predictions as new data are collected. The combined model had a mean error 50% lower than the MODFLOW model alone. These results demonstrate that hierarchical machine learning approaches can be used to improve predictive performance of existing numerical models in areas with good data coverage. Further research is needed to compare this approach with methods such as Kalman filtering." @default.
- W1666936902 created "2016-06-24" @default.
- W1666936902 creator A5052801957 @default.
- W1666936902 creator A5054388255 @default.
- W1666936902 creator A5079686302 @default.
- W1666936902 creator A5080041337 @default.
- W1666936902 creator A5080317480 @default.
- W1666936902 date "2005-03-01" @default.
- W1666936902 modified "2023-10-17" @default.
- W1666936902 title "Integrating data sources to improve hydraulic head predictions: A hierarchical machine learning approach" @default.
- W1666936902 cites W1971665758 @default.
- W1666936902 cites W1982356910 @default.
- W1666936902 cites W2001676017 @default.
- W1666936902 cites W2024136381 @default.
- W1666936902 cites W2034270874 @default.
- W1666936902 cites W2041364715 @default.
- W1666936902 cites W2083134367 @default.
- W1666936902 cites W2091396986 @default.
- W1666936902 cites W2102134046 @default.
- W1666936902 cites W2121192737 @default.
- W1666936902 cites W2139212933 @default.
- W1666936902 cites W2520351572 @default.
- W1666936902 cites W3018770027 @default.
- W1666936902 cites W4236137412 @default.
- W1666936902 doi "https://doi.org/10.1029/2003wr002802" @default.
- W1666936902 hasPublicationYear "2005" @default.
- W1666936902 type Work @default.
- W1666936902 sameAs 1666936902 @default.
- W1666936902 citedByCount "9" @default.
- W1666936902 countsByYear W16669369022019 @default.
- W1666936902 countsByYear W16669369022020 @default.
- W1666936902 countsByYear W16669369022021 @default.
- W1666936902 countsByYear W16669369022022 @default.
- W1666936902 countsByYear W16669369022023 @default.
- W1666936902 crossrefType "journal-article" @default.
- W1666936902 hasAuthorship W1666936902A5052801957 @default.
- W1666936902 hasAuthorship W1666936902A5054388255 @default.
- W1666936902 hasAuthorship W1666936902A5079686302 @default.
- W1666936902 hasAuthorship W1666936902A5080041337 @default.
- W1666936902 hasAuthorship W1666936902A5080317480 @default.
- W1666936902 hasBestOaLocation W16669369021 @default.
- W1666936902 hasConcept C119857082 @default.
- W1666936902 hasConcept C124101348 @default.
- W1666936902 hasConcept C126838900 @default.
- W1666936902 hasConcept C127413603 @default.
- W1666936902 hasConcept C131227075 @default.
- W1666936902 hasConcept C154945302 @default.
- W1666936902 hasConcept C183115368 @default.
- W1666936902 hasConcept C187320778 @default.
- W1666936902 hasConcept C41008148 @default.
- W1666936902 hasConcept C71924100 @default.
- W1666936902 hasConcept C75622301 @default.
- W1666936902 hasConcept C76177295 @default.
- W1666936902 hasConcept C78302586 @default.
- W1666936902 hasConcept C84525736 @default.
- W1666936902 hasConceptScore W1666936902C119857082 @default.
- W1666936902 hasConceptScore W1666936902C124101348 @default.
- W1666936902 hasConceptScore W1666936902C126838900 @default.
- W1666936902 hasConceptScore W1666936902C127413603 @default.
- W1666936902 hasConceptScore W1666936902C131227075 @default.
- W1666936902 hasConceptScore W1666936902C154945302 @default.
- W1666936902 hasConceptScore W1666936902C183115368 @default.
- W1666936902 hasConceptScore W1666936902C187320778 @default.
- W1666936902 hasConceptScore W1666936902C41008148 @default.
- W1666936902 hasConceptScore W1666936902C71924100 @default.
- W1666936902 hasConceptScore W1666936902C75622301 @default.
- W1666936902 hasConceptScore W1666936902C76177295 @default.
- W1666936902 hasConceptScore W1666936902C78302586 @default.
- W1666936902 hasConceptScore W1666936902C84525736 @default.
- W1666936902 hasIssue "3" @default.
- W1666936902 hasLocation W16669369021 @default.
- W1666936902 hasOpenAccess W1666936902 @default.
- W1666936902 hasPrimaryLocation W16669369021 @default.
- W1666936902 hasRelatedWork W2081026125 @default.
- W1666936902 hasRelatedWork W2351044827 @default.
- W1666936902 hasRelatedWork W2353774927 @default.
- W1666936902 hasRelatedWork W2377198601 @default.
- W1666936902 hasRelatedWork W2381980924 @default.
- W1666936902 hasRelatedWork W2620245586 @default.
- W1666936902 hasRelatedWork W3036095178 @default.
- W1666936902 hasRelatedWork W3134840015 @default.
- W1666936902 hasRelatedWork W4366979180 @default.
- W1666936902 hasRelatedWork W4384470695 @default.
- W1666936902 hasVolume "41" @default.
- W1666936902 isParatext "false" @default.
- W1666936902 isRetracted "false" @default.
- W1666936902 magId "1666936902" @default.
- W1666936902 workType "article" @default.