PL EN


Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Powiadomienia systemowe
  • Sesja wygasła!
  • Sesja wygasła!
Tytuł artykułu

Forecasting suspended sediment load using regularized neural network: Case study of the Isser River (Algeria)

Treść / Zawartość
Identyfikatory
Warianty tytułu
PL
Prognozowanie ładunku zawiesiny z zastosowaniem regularyzowanej sieci neuronowej: przykład rzeki Isser w Algierii
Języki publikacji
EN
Abstrakty
EN
In the management of water resources in different hydro-systems it is important to evaluate and predict the sediment load in rivers. It is difficult to obtain an effective and fast estimation of sediment load by artificial neural network without avoiding over-fitting of the training data. The present paper comprises the comparison of a multi-layer perception network once with non-regularized network and the other with regularized network using the Early Stopping technique to estimate and forecast suspended sediment load in the Isser River, upstream of Beni Amran reservoir, northern Algeria. The study was carried out on daily sediment discharge and water discharge data of 30 years (1971–2001). The results of the Back Propagation based models were evaluated in terms of the coefficient of determination (R2) and the root mean square error (RMSE). Results of the comparison indicate that the regularizing ANN using the Early Stopping technique to avoid over-fitting performs better than non-regularized networks, and show that the overtraining in the back propagation occurs because of the complexity of the data introduced to the network.
PL
Ocena i przewidywanie ładunku zawiesiny w rzekach są istotne w zarządzaniu zasobami wodnymi w różnych hydrosystemach. Trudno jest uzyskać efektywne i szybkie oszacowanie ładunku zawiesiny za pomocą sztucznych sieci neuronowych bez uniknięcia przepełnienia danymi. W niniejszej pracy porównano wyniki zastosowania wielowarstwowej sieci w dwóch wariantach – sieci nieregularyzowanej i sieci regularyzowanej z użyciem techniki Early Stopping do oceny i prognozowanie ładunku zawiesiny w rzece Isser powyżej zbiornika Beni Amran w północnej Algierii. Badania bazowały na notowaniach dobowego odpływu zawiesiny i danych dotyczących odpływu wody w ciągu 30 lat (1971–2001). Wyniki modeli opartych na metodzie wstecznej propagacji oceniono za pomocą współczynnika determinacji (R2) i pierwiastka ze średniego błędu kwadratowego. Porównanie wyników dowodzi, że sieć neuronowa regularyzowana przy pomocy techniki Early Stopping celem uniknięcia przeładowania sprawdza się lepiej niż sieć nieregularyzowana. Wyniki wskazują, że przeładowanie wstecznej propagacji ma miejsce z powodu złożoności danych wprowadzonych do sieci.
Wydawca
Rocznik
Tom
Strony
75--81
Opis fizyczny
Bibliogr. 31 poz., rys., tab.
Twórcy
autor
  • University Hassiba Ben Bouali Chlef, Laboratory of Water and Energy, Hay Salem National Road Nr 19, 02000, Chlef, Algeria
autor
  • University Badji Mokhtar Annaba, Laboratory of Hydraulics and Hydraulic Construction, BP12 -23000-Annaba, Algeria
autor
  • University Hassiba Ben Bouali Chlef, Laboratory of Water and Energy, Hay Salem National Road Nr 19, 02000, Chlef, Algeria
autor
  • University Badji Mokhtar, Department of Hydraulics, Annaba, Algeria
  • University Badji Mokhtar Annaba, Laboratory of Hydraulics and Hydraulic Construction, BP12 -23000-Annaba, Algeria
Bibliografia
  • ABRAHART R.J., WHITE S.M. 2001. Modelling sediment transfer in Malawi: Comparing back propagation neural network solution against a multiple linear regression benchmark using small data sets. Physics and Chemistry of the Earth. Part B: Hydrology, Oceans and Atmosphere. Vol. 26. Iss. 1 p. 19–24.
  • ACHITE M., MEDDI M. 2004. Estimation du transport solide dans le basin-versant de l’oued Haddad (Nord-Ouset algérien) [Estimation of sediment transport in the catchment area of Wadi Haddad (North West Algeria)]. Sécheresse. Vol. 15. No. 4 p. 367–373.
  • ASCE. Task Committee on Application of Artificial Neural Networks in Hydrology 2000. Artificial neural networks in hydrology. I: Preliminary concepts. Journal of Hydrologic Enginering. Vol. 5. Iss. 2 p. 115–123.
  • ASCE. Task Committee on Application of Artificial Neural Networks in Hydrology 2000. Artificial neural networks in hydrology. II: Hydrologic applications. Journal of Hydrologic Enginering. Vol. 5. Iss. 2 p. 124–137.
  • AYTEK A., KISI O. 2008. A genetic programming approach to suspended sediment modelling. Journal of Hydrology. Vol. 351. No. 3 p. 288–298.
  • BAE D.H., JEONG D.M., KIM G. 2007. Monthly dam inflow forecasts using weather forecast information and neurofuzzy technique. Hydrological Sciences Journal. Vol. 52. Iss. 1 p. 99–113.
  • BENKHALED A., REMINI B. 2003. Analyse de la relation de puissance: débit solide débit liquide à l’échelle du bassin versant de l’Oued Wahrane (Algérie) [Analysis of the power relationship: solid and liquid flow rate across the watershed of Oued Wahrane]. Revue Science de L'eau. Vol. 16. No. 3 p. 333–356.
  • BOUCHELKIA A., BELARBI F., REMINI B. 2013. Quantification of suspended sediment load by double correlation in the watershed of Chellif (Algeria). Soil and Water Research. Vol. 8. No. 2 p. 63–70.
  • FISCHER M.M. 1998. Computational Neural Networks: A new paradigm for spatial analysis. Environment and Planning A. Vol. 30. No. 10 p. 1873–1891.
  • HAYKIN S. 1999. Neural Networks: A Comprehensive Foundation. New York, USA. Macmillan College Publishing Co. pp. 823.
  • KISI O. 2005. Suspended sediment estimation using neurofuzzy and neural network approaches. Hydrological Sciences Journal. Vol. 50. No. 4 p. 683–696.
  • LARFI B., REMINI B. 2006. Le transport solide dans le bassin versant de l’oued Isser impact sur l’envasement du barrage de Beni Amrane (Algerie) [Sediment transport in the drainage basin of the Oued Isser, impact on siltation dam Beni Amrane]. Larhyss Journal. No. 5 p. 63–73.
  • LEFKIR A., BENKACI T., DECHEMI N. 2006. Quantification du transport solide par la technique floue, application au barrage de Beni Amrane (Algérie) [Quantification of sediment transport by the fuzzy technique, application in the dam of Beni Amrane]. Revue Science de L'eau. Vol. 19 No. 3 p. 247–257.
  • LIU Y., STARZYK J.A., ZHU Z. 2008. Optimized approximation algorithm in neural networks without overfitting. IEEE Transactions on Neural Networks. Vol. 19. Iss. 6 p. 983–995.
  • MARQUARDT D.W. 1963. An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial and Applied Mathematics. Vol. 11 No. 2 p. 431–441.
  • MORIASI D.N., ARNOLD J.G., VANLIEW M.W., BINGNER R.L., HARMEL R.D., VEITH T.L. 2006. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE. Vol. 50. Iss. 3 p. 885−900.
  • PNUD 1987. Projet. Érosion et transport solide en zones semi-arides. Projet RAB/80/011.
  • PIOTROWSKI A.P., NAPIORKOWSKI J.J. 2013. A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modeling. Journal of Hydrology. Vol. 476 p. 97–111.
  • PIOTROWSKI A.P., OSUCH M., NAPIORKOWSKI M.J. ROWINSKI P.M., NAPIORKOWSKI J.J. 2014. Comparing large number of metaheuristics for artificial neural networks training to predict water temperature in a natural river. Computers and Geosciences. Vol. 64 p. 136–151.
  • PRECHLET L. 1998. Automatic early stopping using crossvalidation: quantifying the criteria. Neural Network. Vol. 11. Iss. 4 p. 761–777.
  • REMINI B. 2004. Sédimentation des barrages en algérie [The sedimentation in Algerian dams]. Revue Internationale La Houille Blanche. No. 1 p. 1–5.
  • REMINI B., AALOUCH W., ACHOUR B. 2009. L’Algerie: plus d’un siecle d’envasement des barrages (Chapitre 8) [Algeria: more than a century of siltation dam (Chaptre 8)]. Ouvrage Intitule: Etat des resources en eau au Maghreb en 2009. Rabat. UNESCO p. 123–142.
  • SANTHI C., ARNOLD J.G., WILLIAMS J.R., HAUCK L.M. DUGAS W.A. 2001. Application of a watershed model to evaluate management effects on point and nonpoint source pollution. Transactions of the American Society of Agricultural Engineers. Vol. 44. No. 6 p. 1559–1570.
  • SAVIC A.D., WALTERS A.G., DAVIDSON J.W. 1999. A genetic programming approach to rainfall-runoff modeling. Water Resources Management. Vol. 13 p. 219–231.
  • SERBAH B. 2011. Etude et valorisation des sédiments de dragage du barrage Bakhadda Tiaret. These de Magister. Telemcen. Univ. Abou Baker Belkaid pp. 44.
  • SINGH V.P., WOOLHISER D.A. 2002. Mathematical modeling of watershed hydrology. Journal of Hydrologic Engineering. Vol. 7. No. 4 p. 270–292.
  • SOLOMATINE D.P., DULAL K.N. 2003. Model trees as an alternative to neural networks in rainfall–runoff modelling. Hydrological Sciences Journal. Vol. 48. Iss. 3 p. 399–411.
  • TERFOUS A., MEGNOUNIF A., BOUANANI A. 2001. Study of the suspended load at the river Mouilah (North West Algeria). Journal of Water Science. Vol. 14 p. 173–185.
  • VAN LIEW M.W., ARNOLD J.G, GARBRECHT J.D. 2003. Hydrologic simulation on agricultural watersheds: Choosing between two models. Transaction of American Society of Agricultural Engineers. Vol. 46 No. 6 p. 1539–1551.
  • ZHU Y.M., LU X.X., ZHOU Y. 2007. Suspended sediment flux modelling with artificial neural network: An example of the Longchuanjiang River in the Upper Yangtze Catchment, China. Journal of Geomorphology. Vol. 84 p. 111–125.
  • ZUR R.M., JIANG Y.L., PESCE L.L., DRUKKER K. 2009. Noise injection for training artificial neural networks: A comparison with weight decay and early stopping. Med Phys. Vol. 36. Iss. 10 p. 4810–4818.
Uwagi
PL
Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-aa9ee9e2-e325-4904-8585-6556f83be471
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.