Modelo híbrido para la simulación numérica de la fase de avance del riego por superficie

José Antonio Rodríguez

Resumen

Se presenta un modelo híbrido que combina una solución convencional de balance de volumen con cuatro redes neuronales artificiales de tipo Perceptrón Multicapa para simular la fase de avance del riego por superficie. Las redes neuronales se encargaron de simular los procesos difíciles de asumir por los medios de balance de volumen sin renunciar a la facilidad y agilidad de los cálculos que brindan estas soluciones simplificadas. Así, dos redes se entrenaron para calcular la evolución temporal del volumen de agua almacenado sobre la superficie del suelo y, asimismo, el área del flujo superficial al inicio del campo; mientras que otras dos redes se diseñaron para asimilar el efecto transitorio que genera las fluctuaciones temporales del caudal de riego sobre la fase de avance del riego por superficie. El modelo híbrido fue capaz de predecir la distancia de avance y el calado del flujo superficial con una precisión similar a la alcanzada con un modelo numérico de inercia nula tanto en condiciones de régimen permanente como transitorio. La solución del modelo híbrido es explícita, no necesita discretizar los dominios temporal y espacial para resolver las ecuaciones que gobiernan el sistema y logra una rápida convergencia de los cálculos.

Texto completo:

PDF

Referencias

Al-Azba, A.A., (1999). Explicit volume balance model solution. Journal of Irrigation and Drainage Engineering, ASCE, 125(5), 273–279. https://doi.org/10.1061/(ASCE)0733-9437(1999)125:5(273)

Bassett, D.L., Frangmeier, D.D. y Strelkoff, T., (1980). Hydraulics of surface irrigation systems. En: Design and operation of farm irrigation systems. ASAE Monograph No.3, St. Joseph, Michigan, 829 pp.

Bautista, E., Clemmens, A.J., Strelkoff, T. y Schlegel, J.L., (2009). Modern analysis of surface irrigation systems with WinSRFR. Agricultural Water Management, 96, 1146–1154. https://doi.org/10.1016/j.agwat.2009.03.007

Bishop, M., (1995). Neural Networks for Pattern Recognition. Oxford University Press. https://doi.org/10.1201/9781420050646.ptb6

Brown, M.B. y Forsythe, A.B., (1974). Robust Tests for Equality of Variances. Journal of the American Statistical Association, 69: 364-367. https://doi.org/10.1080/01621459.1974.10482955

Dibike, Y.B., (2002). Developing generic hydrodynamic models using artificial neural networks. Journal of Hydraulic Research, 40(2), 183–190. https://doi.org/10.1080/00221680209499861

Gillies, M.H., Smith, R.J. y Raine, S.R., (2007). Accounting for temporal inflow variation in the inverse solution for infiltration in surface irrigation. Irrigation Science, 25(2): 87-97. https://doi.org/10.1007/s00271-006-0037-9

Hagan, M.T. y Menhaj, M.B., (1994). Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neural Net., 5, 989–993. https://doi.org/10.1109/72.329697

Katopodes, N.D. y Strelkoff, T., (1977). Dimensionless solutions of border-irrigation advance. Journal of Irrigation and Drainage Engineering, ASCE, 103(4), 401–417.

Kleijnen, J.P., Bettonvil, B., y Van Groenendall, W., (1998). Validation of trace-driven simulation models: a novel regression test. Management Science, 44, 812–819. https://doi.org/10.1287/mnsc.44.6.812

Kolmogoroff, A.N., (1933). Sulla determinazione empirica di una legge di distribuzione. Giornale dell’Istituto Italiano degli Attuari, 4, 83–91.

Kostiakov, A.N., (1932). On the dynamics of coefficient of water-percolation in soils and the necessity of studying it from a dynamic point of view for purposes of amelioration. Trans. Com. Int. Soc. Soil Sci. 6th, Mosc ́u, Part A, 267–272.

Mann, H.B. y Whitney, D.R., (1947). On a test of whether one of two random variables is stochastically larger than the other. Annals of Mathematical Statistics, 18, 50–60. https://doi.org/10.1214/aoms/1177730491

Renault, D. y Wallender, W.W., (1996). Initial-inflow variation impacts on furrow irrigation evaluation. Journal of Irrigation and Drainage Engineering, ASCE, 122(1), 7–14. https://doi.org/10.1061/(ASCE)0733-9437(1996)122:1(7)

Rodr ́ıguez, J.A. y Martos, J.C., (2009). SIPAR_ID: Freeware for surface irrigation parameter identification. Environ. Model. Softw. Art ́ıculo en imprenta.

Saint-Venant, A.J.C., (1871). Théorie du mouvement non permanent des eaux, avec application aux des rivères et a l’introduction des marées dans eut lits. Comptes rendus des séances de l’Académies Sciences, 73, 147–154.

Smirnov, N., (1933). Estimate of deviation between empirical distribution functions in two independent samples. Moscow University Mathematics Bulletin, 2, 3–16.

Smith, M., (1993). Neural networks for statistical modeling. Van Nostrand Reinhold, New York.

Tedeschi, L.O., (2006). Assessment of the adequacy of mathematical models. Agricultural Systems, 89, 225–247. https://doi.org/10.1016/j.agsy.2005.11.004

Valiantzas, J.D., (1997a). Surface irrigation advance equation: Variation of subsurface shape factor. Journal of Irrigation and Drainage Engineering, ASCE, 123(4), 300–306. https://doi.org/10.1061/(ASCE)0733-9437(1997)123:4(300)

Valiantzas, J.D., (1997b). Volume balance irrigation advance equation: Variation of surface shape factor. Journal of Irrigation and Drainage Engineering, ASCE, 123(4), 307–312. https://doi.org/10.1061/(ASCE)0733-9437(1997)123:4(307)

Valiantzas, J.D., (1999). Explicit time of advance formula for furrow design. Journal of Irrigation and Drainage Engineering, ASCE, 125(1), 19–25. https://doi.org/10.1061/(ASCE)0733-9437(1999)125:1(19)

Walker, W.R., (1989). Guidelines for designing and evaluating surface irrigation system. FAO Irrigation and Drainage Paper No. 45, Rome, 137pp.

Walker, W.R. y Skogerboe, G.V., (1987). Surface irrigation: Theory and Practice. Prentice-Hall, Englewood Cliffs, New Jersey, 386pp.

Wilcoxon, F., (1945). Individual comparisons by ranking methods. Biometrics Bulletin, 1, 80–83. https://doi.org/10.2307/3001968

Wolpert, D.H., (1996a). The lack of a priori distinctions between learning algorithms. Neural Computation, 8, 1341–1390. https://doi.org/10.1162/neco.1996.8.7.1341

Wolpert, D.H., (1996b). The existence of a priori distinctions between learning algorithms. Neural Computation, 8, 1391–1420. https://doi.org/10.1162/neco.1996.8.7.1391

Abstract Views

726
Metrics Loading ...

Metrics powered by PLOS ALM




Esta revista se publica bajo una licencia de Creative Commons Reconocimiento-NoComercial-CompartirIgual 4.0 Internacional.

Universitat Politècnica de València

Fundación para el Fomento de la Ingeniería del Agua

e-ISSN: 1886-4996  ISSN: 1134-2196

https://doi.org/10.4995/ia