Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319726067> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4319726067 abstract "Long-term hydrological forecasting based on sea surface temperature (SST) fields faces the large p and small n problem, i.e., too many potential predictors and a limited number of samples. Considering the selection of predictors will also enhance the complexity of models and lead to overfitting, in this study, two strategies are used for building forecasting models for long-term streamflow forecasting. The first strategy is to downsample the SST field and optimize its spatial resolution; the second is to shrink model coefficients based on L1 regularization. We build models based on the downsampled SST fields with different spatial resolutions. It is found that the model based on a proper spatial resolution always performs better than the model based on the raw SST field. This result suggests that it is better to treat the spatial resolution of the predictor field as a hyperparameter, which is similar to hyperparameters for controlling the complexity of many machine learning models. For applying the second strategy, L1 norm regularization models, including (1) least absolute selection and shrinkage operator (LASSO), (2) relaxed LASSO, and (3) two-step approach of LASSO and ordinary least squares regression (LASSO+OLS) are explored. We have found that the relaxed LASSO model always performs better than the ordinary LASSO, indicating that relaxed LASSO is a better shrinkage approach. Furthermore, the skills of the presented models are compared with the stepwise regression, and the lower skill of the stepwise regression based on SST fields with a high spatial resolution suggests that one should not select predictors based on fields with high resolutions considering the limited number of samples." @default.
- W4319726067 created "2023-02-11" @default.
- W4319726067 creator A5002733458 @default.
- W4319726067 creator A5004639223 @default.
- W4319726067 creator A5046050692 @default.
- W4319726067 creator A5065559740 @default.
- W4319726067 creator A5083292040 @default.
- W4319726067 date "2023-04-01" @default.
- W4319726067 modified "2023-10-18" @default.
- W4319726067 title "Two Strategies for Avoiding Overfitting Long-Term Forecasting Models: Downsampling Predictor Fields and Shrinking Coefficients" @default.
- W4319726067 cites W1507985183 @default.
- W4319726067 cites W1537835567 @default.
- W4319726067 cites W1831050183 @default.
- W4319726067 cites W1993019441 @default.
- W4319726067 cites W2018767964 @default.
- W4319726067 cites W2030797143 @default.
- W4319726067 cites W2042509423 @default.
- W4319726067 cites W2056950965 @default.
- W4319726067 cites W2062920605 @default.
- W4319726067 cites W2081819544 @default.
- W4319726067 cites W2082484980 @default.
- W4319726067 cites W2114381891 @default.
- W4319726067 cites W2118290911 @default.
- W4319726067 cites W2119862467 @default.
- W4319726067 cites W2149316706 @default.
- W4319726067 cites W2153685346 @default.
- W4319726067 cites W2170334405 @default.
- W4319726067 cites W2174028526 @default.
- W4319726067 cites W2176670204 @default.
- W4319726067 cites W2179386986 @default.
- W4319726067 cites W2256317226 @default.
- W4319726067 cites W2367112923 @default.
- W4319726067 cites W2395830415 @default.
- W4319726067 cites W2548285523 @default.
- W4319726067 cites W2787894218 @default.
- W4319726067 cites W2950139191 @default.
- W4319726067 cites W3098272239 @default.
- W4319726067 cites W3102205194 @default.
- W4319726067 cites W4229873072 @default.
- W4319726067 cites W4294541781 @default.
- W4319726067 doi "https://doi.org/10.1061/jhyeff.heeng-5864" @default.
- W4319726067 hasPublicationYear "2023" @default.
- W4319726067 type Work @default.
- W4319726067 citedByCount "0" @default.
- W4319726067 crossrefType "journal-article" @default.
- W4319726067 hasAuthorship W4319726067A5002733458 @default.
- W4319726067 hasAuthorship W4319726067A5004639223 @default.
- W4319726067 hasAuthorship W4319726067A5046050692 @default.
- W4319726067 hasAuthorship W4319726067A5065559740 @default.
- W4319726067 hasAuthorship W4319726067A5083292040 @default.
- W4319726067 hasConcept C105795698 @default.
- W4319726067 hasConcept C119857082 @default.
- W4319726067 hasConcept C136764020 @default.
- W4319726067 hasConcept C149782125 @default.
- W4319726067 hasConcept C154945302 @default.
- W4319726067 hasConcept C203868755 @default.
- W4319726067 hasConcept C22019652 @default.
- W4319726067 hasConcept C2776135515 @default.
- W4319726067 hasConcept C33923547 @default.
- W4319726067 hasConcept C37616216 @default.
- W4319726067 hasConcept C41008148 @default.
- W4319726067 hasConcept C50644808 @default.
- W4319726067 hasConcept C81692654 @default.
- W4319726067 hasConcept C83546350 @default.
- W4319726067 hasConcept C8642999 @default.
- W4319726067 hasConcept C93959086 @default.
- W4319726067 hasConceptScore W4319726067C105795698 @default.
- W4319726067 hasConceptScore W4319726067C119857082 @default.
- W4319726067 hasConceptScore W4319726067C136764020 @default.
- W4319726067 hasConceptScore W4319726067C149782125 @default.
- W4319726067 hasConceptScore W4319726067C154945302 @default.
- W4319726067 hasConceptScore W4319726067C203868755 @default.
- W4319726067 hasConceptScore W4319726067C22019652 @default.
- W4319726067 hasConceptScore W4319726067C2776135515 @default.
- W4319726067 hasConceptScore W4319726067C33923547 @default.
- W4319726067 hasConceptScore W4319726067C37616216 @default.
- W4319726067 hasConceptScore W4319726067C41008148 @default.
- W4319726067 hasConceptScore W4319726067C50644808 @default.
- W4319726067 hasConceptScore W4319726067C81692654 @default.
- W4319726067 hasConceptScore W4319726067C83546350 @default.
- W4319726067 hasConceptScore W4319726067C8642999 @default.
- W4319726067 hasConceptScore W4319726067C93959086 @default.
- W4319726067 hasIssue "4" @default.
- W4319726067 hasLocation W43197260671 @default.
- W4319726067 hasOpenAccess W4319726067 @default.
- W4319726067 hasPrimaryLocation W43197260671 @default.
- W4319726067 hasRelatedWork W1998646673 @default.
- W4319726067 hasRelatedWork W2104229089 @default.
- W4319726067 hasRelatedWork W2143313161 @default.
- W4319726067 hasRelatedWork W2488225685 @default.
- W4319726067 hasRelatedWork W2971869563 @default.
- W4319726067 hasRelatedWork W3000463406 @default.
- W4319726067 hasRelatedWork W4210794429 @default.
- W4319726067 hasRelatedWork W4284963956 @default.
- W4319726067 hasRelatedWork W4319726067 @default.
- W4319726067 hasRelatedWork W4366966573 @default.
- W4319726067 hasVolume "28" @default.
- W4319726067 isParatext "false" @default.
- W4319726067 isRetracted "false" @default.
- W4319726067 workType "article" @default.