Navegar

Colección

Datos Estadísticas

Artículo

La versión final de este artículo es de uso interno. El editor solo permite incluir en el repositorio el artículo en su versión post-print. Por favor, si usted la posee enviela a
Consulte el artículo en la página del editor
Consulte la política de Acceso Abierto del editor

Abstract:

Daily weather generators are used in many applications and risk analyses. The present paper explores the potential of neural network architectures to design daily weather generator models. Focusing this first paper on precipitation, we design a collection of neural networks (multi-layer perceptrons in the present case), which are trained so as to approximate the empirical cumulative distribution (CDF) function for the occurrence of wet and dry spells and for the precipitation amounts. This approach contributes to correct some of the biases of the usual two-step weather generator models. As compared to a rainfall occurrence Markov model, NNGEN-P represents fairly well the mean and standard deviation of the number of wet days per month, and it significantly improves the simulation of the longest dry and wet periods. Then, we compared NNGEN-P to three parametric distribution functions usually applied to fit rainfall cumulative distribution functions (Gamma, Weibull and double-exponential). A data set of 19 Argentine stations was used. Also, data corresponding to stations in the United States, in Europe and in the Tropics were included to confirm the results. One of the advantages of NNGEN-P is that it is non-parametric. Unlike other parametric function, which adapt to certain types of climate regimes, NNGEN-P is fully adaptive to the observed cumulative distribution functions, which, on some occasions, may present complex shapes. On-going works will soon produce an extended version of NNGEN to temperature and radiation. © Springer-Verlag 2006.

Registro:

Documento: Artículo
Título:Neural network based daily precipitation generator (NNGEN-P)
Autor:Boulanger, J.-P.; Martinez, F.; Penalba, O.; Segura, E.C.
Filiación:LODYC, UMR CNRS/IRD/UPMC, UPMC, 4 Place Jussieu, Paris Cedex 05 75252, France
Departamento de Computación, Facultad de Ciencias Exactas y Naturales, University of Buenos Aires, Buenos Aires, Argentina
Departamento de Ciencias de la Atmósfera y los Océanos, Facultad de Ciencias Exactas y Naturales, University of Buenos Aires, Buenos Aires, Argentina
Palabras clave:artificial neural network; data set; empirical analysis; Markov chain; precipitation (climatology); rainfall; simulation
Año:2007
Volumen:28
Número:2-3
Página de inicio:307
Página de fin:324
DOI: http://dx.doi.org/10.1007/s00382-006-0184-y
Título revista:Climate Dynamics
Título revista abreviado:Clim. Dyn.
ISSN:09307575
Registro:https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_09307575_v28_n2-3_p307_Boulanger

Referencias:

  • Adamowsky, K., Smith, A.F., Stochastic generation of rainfall (1972) J Hydraul Eng ASCE, 98, pp. 1935-1945
  • Akaike, A., New look at the statistical model identification (1974) IEEE Trans Automatic Control, 19, pp. 716-723
  • Allen, D.M., Haan, C.T., Stochastic simulation of daily rainfall (1975), Res. Rep. No. 82, Water Resource Inst., University Kentucky, Lexington,Kentucky, USA; Buishand, T.A., Some methods for testing the homogeneity of rainfall records (1982) J Hydrol
  • Buishand, T.A., Some remarks on the use of daily rainfall models (1978) J Hydrol, 36, pp. 295-308
  • Caballero, R., Jewson, S., Brix, A., Long memory in surface air temperature: Detection, modeling and application to weather derivative calculation (2001) Clim Res
  • Charles, S.P., Bates, B.C., Hughes, J.P., A spatiotemporal model for downscaling precipitation occurrence and amounts (1999) J Geophys Res, 104, pp. 31657-31669
  • Foufoula-Georgiou, E., Lettenmaier, D.P., A Markov renewal model for rainfall occurrences (1987) Water Resour Res, 23, pp. 875-884
  • Frich, P., Alexander, L.V., Della-Marta, P., Gleason, B., Haylock, M., Klein Tank, A.M.G., Peterson, T., Observed coherent changes in climatic extremes during the second half of the twentieth century (2002) Clim Res, 19, pp. 193-212
  • Geng, S., Penning De Vries, F.W.T., Supit, I., A simple method for generating daily rainfall data (1986) Agric For Meteorol, 36, pp. 363-376
  • Hansen, J.W., Ines, A.V.M., Stochastic disaggregation of monthly rainfall data for crop simulation studies (2005) Agric For Meteorol
  • Hay, L.E., McCabe Jr., G.J., Wolock, D.M., Ayres, M.A., Simulation of precipitation by weather type analysis (1991) Water Resour Res, 27, pp. 493-501
  • Hutchinson, M.F., Methods of generation of weather sequences (1986) Agric Env CAB, pp. 149-157. , In: Bunting AH (ed) International, Wallingford
  • Hutchinson, M.F., Stochastic space-time weather models from ground-based data (1995) Agric For Meteorol, 73, pp. 237-265
  • Jewson, S., Weather derivative pricing and the potential accuracy of daily temperature modeling (2004), http://ssrn.com/abstract=535122; Katz, R.W., Precipitation as a chain-dependent process (1977) J Appl Meteor, 16, pp. 671-676
  • Lall, U., Rajagopalan, B., Traboton, D.G., A non-parametric wet/dry spell model for resampling daily precipitation (1996) J Clim, 11, pp. 591-601
  • MacKay, D.J.C., Bayesian interpolation (1992) Neural Comput, 4, pp. 415-447
  • Nabney, I.T., Netlab (2002) Algorithms for Pattern Recognition, Advances in Pattern Recogniction, p. 420. , Springer, Berlin Heidelberg New York
  • Racsko, P., Szeidl, L., Semenov, M., A serial approach to local statistic weather models (1991) Ecol Modeling, 57, pp. 27-41
  • Rajagopalan, B., Lall, U., A k-nearest-neighbor simulator for daily precipitation and other weather variables (1999) Water Resour Res, 35, pp. 3089-3101
  • Rajagopalan, B., Lall, U., Tarboton, D.G., A nonhomogeneous Markov model for daily precipitation simulation (1996) J Hydrol Eng-ASCE, 1, pp. 33-40
  • Richardson, C.W., Stochastic simulation of daily precipitation, temperature, and solar radiation (1981) Water Resour Res, 17, pp. 182-190
  • Roldan, J., Woolhiser, D.A., Stochatic daily precipitation models. 1. A comparison of occurrence processes (1982) Water Resour Res, 18, pp. 1451-1459
  • Schwartz, G., Estimating the dimension of a model (1978) Ann Statistics, 6, pp. 641-644
  • Selker, J.S., Haith, D.A., Development and testing of single-parameter precipitation distributions (1990) Water Resour Res
  • Semenov, M.A., Barrow, E.M., Use of stochastic weather generator in the development of climate change scenarios (1997) Clim Change, 35, pp. 397-414
  • Sharpley, A.R., Willians, J.R., (1990) EPIC an Erosion/Productivity Impact Calculator: 2. User Manual, , U.S. Department of Agriculture, ARS Tech Bull No 1768
  • Siriwarden, (2002); Srikanthan, R., McMahon, T.A., Stochastic simulation of daily rainfall for Australian stations (1983) Trans ASAE, 26, pp. 754-759. , 766
  • Srikanthan, R., McMahon, T.A., Stochastic generation of rainfall and evaporation data (1985), p. 301. , Canberra Australian Water Resources Council, Tech. Paper No. 84, AGPS; Srikanthan, R., McMahon, T.A., Stochastic generation of annual, monthly and daily climate data: A review (2001) Hydrol Earth Syst Sci, 5, pp. 653-670
  • Stern, R.D., Coe, R., A model fitting analysis of daily rainfall data (1984) J Roy Stat Soc, A147, pp. 1-34
  • Wilks, D.S., Conditioning stochastic daily precipitation models on total monthly precipitation (1989) Water Resour Res, 25, pp. 1429-1439
  • Wilks, D.S., Adapting stochastic weather generation algorithms for climate change studies (1992) Clim Change, 22, pp. 67-84
  • Wilks, D.S., Multisite generalization of a daily stochastic precipitation generation model (1998) J Hydrol, 210, pp. 178-191
  • Wilks, D.S., Simultaneous stochastic simulation of daily precipitation, temperature and solar radiation at multiple sites in complex terrain (1999) Agric For Meteor, 96, pp. 85-101
  • Wilks, D.S., Interannual variability and extreme-value characteristics of several stochastic daily precipitation models (1999) Agric For Meteor, 93, pp. 153-169
  • Wilson, L.L., Lettenmaier, D.P., Skyllinggstad, E., A hierarchic stochastic model of large-scale atmospheric circulation patterns and multiple station daily precipitation (1992) J Geophys Res, D3, pp. 2791-2809
  • Woolhiser, D.A., Roldan, J., Stochastic daily precipitation models. 2. A comparison of distribution amounts (1982) Water Resour Res, 18, pp. 1461-1468
  • Woolhiser, D.A., Pegram, G.S., Maximum likelihood estimation of Fourier coefficients to describe seasonal variation of parameters in stochastics daily precipitation models (1979) J Appl Meteor, 18, pp. 34-42
  • Woolhiser, D.A., Roldan, J., Seasonal and regional variability of parameters for stochastic daily precipitation models (1986) Water Resour Res, 22, pp. 965-978
  • Woolhiser, D.A., Modeling daily precipitation: B. Progress and problems (1992) Statistics in the Env. And Earth Sciences, pp. 71-89. , In: Walden AT, Guttorp P (eds) John Wiley, New York

Citas:

---------- APA ----------
Boulanger, J.-P., Martinez, F., Penalba, O. & Segura, E.C. (2007) . Neural network based daily precipitation generator (NNGEN-P). Climate Dynamics, 28(2-3), 307-324.
http://dx.doi.org/10.1007/s00382-006-0184-y
---------- CHICAGO ----------
Boulanger, J.-P., Martinez, F., Penalba, O., Segura, E.C. "Neural network based daily precipitation generator (NNGEN-P)" . Climate Dynamics 28, no. 2-3 (2007) : 307-324.
http://dx.doi.org/10.1007/s00382-006-0184-y
---------- MLA ----------
Boulanger, J.-P., Martinez, F., Penalba, O., Segura, E.C. "Neural network based daily precipitation generator (NNGEN-P)" . Climate Dynamics, vol. 28, no. 2-3, 2007, pp. 307-324.
http://dx.doi.org/10.1007/s00382-006-0184-y
---------- VANCOUVER ----------
Boulanger, J.-P., Martinez, F., Penalba, O., Segura, E.C. Neural network based daily precipitation generator (NNGEN-P). Clim. Dyn. 2007;28(2-3):307-324.
http://dx.doi.org/10.1007/s00382-006-0184-y