Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloChoosing between linear and nonlinear models and avoiding overfitting for short and long term groundwater level forecasting in a linear system
Anno di pubblicazione2019
FormatoElettronico
Autore/iZanotti C.; Rotiroti M.; Sterlacchini S.; Cappellini G.; Fumagalli L.; Stefania G.A.; Nannucci M.S.; Leoni B.; Bonomi T.
Affiliazioni autoriDepartment of Earth and Environmental Sciences, University of Milano-Bicocca, Piazza della Scienza, 1, Milano, 20126, Department of Earth and Environmental Sciences, University of Milano-Bicocca, Piazza della Scienza, 1, 20126 Milano, Italy, , Italy; National Research Council, Institute of Environmental Geology and Geoengineering, Piazza della Scienza, 1, Milano, 20126, National Research Council, Institute for the Dynamics of Environmental Processes, Piazza della Scienza, 1, 20126 Milano, Italy, , Italy; Regione Toscana, Direzione Ambiente ed Energia, Settore Servizi Pubblici Locali, Via San Gallo 34/a, Firenze, 50129, Regione Toscana, Direzione Ambiente ed Energia, Settore Servizi Pubblici Locali, Via San Gallo 34/a, 50129 Firenze, Italy, , Italy
Autori CNR e affiliazioni
  • SIMONE STERLACCHINI
Lingua/e
  • inglese
AbstractGroundwater level forecasting is a useful tool for a more efficient and sustainable groundwater resource management. Developing models that can accurately reproduce groundwater level response to meteorological conditions can lead to a better understanding of the groundwater resource availability. Here an autoregressive neural network (NNARx) approach is proposed and compared with autoregressive linear models with exogenous input (ARx) in order to forecast groundwater level in an aquifer system where a linear groundwater level response to recharge by rainfall is observed. A well known problem regarding neural networks consists in the high risk of overfitting. Here, three NNARx model were trained using different methods to avoid overfitting: Early stopping, Bayesian regularization and a combination of both. The results show that on the short term forecasting (up to 15 days) the performance of NNARx and ARx are comparable but the ARx model generalizes better, while the NNARx trained with Bayesian regularization outperforms the linear models and the other NNARx models on longer scenarios on the test set. As linear models are less time demanding and do not require high computational power, they can be considered as suitable tools for short term groundwater level forecasting in linear systems while when longer scenarios are needed neural networks can be considered more reliable, and training them with Bayesian regularization allows to minimize the risk of overfitting.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da-
Pagine a-
Pagine totali11
RivistaJournal of hydrology (Amst.)
Attiva dal 1963
Editore: Elsevier - Oxford ;
Paese di pubblicazione: Paesi Bassi
Lingua: inglese
ISSN: 0022-1694
Titolo chiave: Journal of hydrology (Amst.)
Titolo proprio: Journal of hydrology. (Amst.)
Titolo abbreviato: J. hydrol. (Amst.)
Titoli alternativi:
  • Journal of hydrology (Lausanne) (Amst.)
  • Journal of hydrology (New York) (Amst.)
  • Journal of hydrology (Oxford) (Amst.)
  • Journal of hydrology (Shannon) (Amst.)
  • Journal of hydrology (Tokyo) (Amst.)
Numero volume della rivista578
Fascicolo della rivista-
DOI10.1016/j.jhydrol.2019.124015
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-85071718139)
Parole chiaveBayesian regularization Groundwater level forecasting Linear model Neural networks Overfitting
Link (URL, URI)http://www.scopus.com/record/display.url?eid=2-s2.0-85071718139&origin=inward
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione03/08/2019
Note/Altre informazioni-
Strutture CNR
  • IGAG — Istituto di geologia ambientale e geoingegneria
Moduli/Attività/Sottoprogetti CNR-
Progetti Europei-
Allegati
Choosing between linear and nonlinear models and avoiding overfitting for short and long term groundwater level forecasting in a linear system (documento privato )
Descrizione: Pdf della pubblicazione
Tipo documento: application/pdf