- -

Ensemble random forest filter: An alternative to the ensemble Kalman filter for inverse modeling

RiuNet: Institutional repository of the Polithecnic University of Valencia

Share/Send to

Cited by

Statistics

  • Estadisticas de Uso

Ensemble random forest filter: An alternative to the ensemble Kalman filter for inverse modeling

Show simple item record

Files in this item

dc.contributor.author A. Godoy, Vanessa es_ES
dc.contributor.author Napa-García, Gian F. es_ES
dc.contributor.author Gómez-Hernández, J. Jaime es_ES
dc.date.accessioned 2023-05-26T18:02:07Z
dc.date.available 2023-05-26T18:02:07Z
dc.date.issued 2022-12 es_ES
dc.identifier.issn 0022-1694 es_ES
dc.identifier.uri http://hdl.handle.net/10251/193647
dc.description.abstract [EN] The ensemble random forest filter (ERFF) is presented as an alternative to the ensemble Kalman filter (EnKF) for inverse modeling. The EnKF is a data assimilation approach that forecasts and updates parameter estimates sequentially in time as observations are collected. The updating step is based on the experimental covariances computed from an ensemble of realizations, and the updates are given as linear combinations of the differences between observations and forecasted system state values. The ERFF replaces the linear combination in the update step with a non-linear function represented by a random forest. This way, the non-linear relationships between the parameters to be updated and the observations can be captured, and a better update produced. The ERFF is demonstrated for log-conductivity identification from piezometric head observations in several scenarios with varying degrees of heterogeneity (log-conductivity variances going from 1 up to 6.25 (ln m/d)2), number of realizations in the ensemble (50 or 100), and number of piezometric head observations (18 or 36). In all scenarios, the ERFF works well, reconstructing the log-conductivity spatial heterogeneity while matching the observed piezometric heads at selected control points. For benchmarking purposes, the ERFF is compared to the restart EnKF to find that the ERFF is superior to the EnKF for the number of ensemble realizations used (small in typical EnKF applications). Only when the number of realizations grows to 500 the restart EnKF can match the performance of the ERFF, albeit at more than double the computational cost. es_ES
dc.description.sponsorship The authors acknowledge grant PID2019-109131RB-I00 funded by MCIN/AEI/10.13039/501100011033 and project InTheMED, which is part of the PRIMA Programme supported by the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 1923. es_ES
dc.language Inglés es_ES
dc.publisher Elsevier es_ES
dc.relation.ispartof Journal of Hydrology es_ES
dc.rights Reconocimiento - No comercial - Sin obra derivada (by-nc-nd) es_ES
dc.subject Groundwater flow es_ES
dc.subject Inverse modeling es_ES
dc.subject Random forest es_ES
dc.subject Bayesian methods es_ES
dc.subject.classification INGENIERIA HIDRAULICA es_ES
dc.title Ensemble random forest filter: An alternative to the ensemble Kalman filter for inverse modeling es_ES
dc.type Artículo es_ES
dc.identifier.doi 10.1016/j.jhydrol.2022.128642 es_ES
dc.relation.projectID info:eu-repo/grantAgreement/AEI//PID2019-109131RB-I00//APRENDIZAJE AUTOMATICO PARA HIDROGEOLOGOS FORENSES/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/AEI//PRE2020-093145//APRENDIZAJE AUTOMATICO PARA HIDROGEOLOGOS FORENSES/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/EC//1923/ es_ES
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Instituto Universitario de Ingeniería del Agua y del Medio Ambiente - Institut Universitari d'Enginyeria de l'Aigua i Medi Ambient es_ES
dc.contributor.affiliation Universitat Politècnica de València. Escuela Técnica Superior de Ingenieros de Caminos, Canales y Puertos - Escola Tècnica Superior d'Enginyers de Camins, Canals i Ports es_ES
dc.description.bibliographicCitation A. Godoy, V.; Napa-García, GF.; Gómez-Hernández, JJ. (2022). Ensemble random forest filter: An alternative to the ensemble Kalman filter for inverse modeling. Journal of Hydrology. 615:1-13. https://doi.org/10.1016/j.jhydrol.2022.128642 es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion https://doi.org/10.1016/j.jhydrol.2022.128642 es_ES
dc.description.upvformatpinicio 1 es_ES
dc.description.upvformatpfin 13 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 615 es_ES
dc.relation.pasarela S\477743 es_ES
dc.contributor.funder European Commission es_ES
dc.contributor.funder AGENCIA ESTATAL DE INVESTIGACION es_ES
dc.contributor.funder Universitat Politècnica de València es_ES


This item appears in the following Collection(s)

Show simple item record