Regularized kriging as a generalization of simple, universal, and bayesian kriging
作者： J. M. Matías , W. González-Manteiga
DOI: 10.1007/S00477-005-0019-0
关键词:
摘要: In this article the properties of regularized kriging (RK) are studied. RK is obtained as a result relaxing universal (UK) non-bias condition by using support vectors methodology. More specifically, we demonstrate how continuum solutions in function regularizing parameter, which includes particular and extreme cases, simple (SK) UK, an intermediate case, Bayesian (BK). Likewise, expressions for mean, variance mean squared error (MSE), also expression corresponding estimator coefficients mean. Finally, investigate relationship between vector machines. By means simulations compare MSE with those BK different association models, levels noise, differently sized coefficients. The results prove to be improvement on UK results, and, moreover, these improvements proportionally greater noise.
springer.com
sci-hub.se 参考文章(27)
D. J. C. Mackay, Introduction to Gaussian processes NATO advanced study institute on generalization in neural networks and machine learning. pp. 133- 165 ,(1998)
Michael L. Stein, Interpolation of Spatial Data Springer New York. ,(1999) , 10.1007/978-1-4612-1494-6
José M. Matías, Wenceslao González-Manteiga, Regularized kriging: the support vectors method applied to kriging international conference on artificial neural networks. pp. 209- 216 ,(2003) , 10.1007/3-540-44989-2_26
George Christakos, Random Field Models in Earth Sciences ,(1992)
C. K. I. Williams, Prediction with Gaussian processes: from linear regression to linear prediction and beyond Proceedings of the NATO Advanced Study Institute on Learning in graphical models. pp. 599- 621 ,(1999) , 10.1007/978-94-011-5014-9_23
J. M. Matías, A. Vaamonde, J. Taboada, W. González-Manteiga, Comparison of Kriging and Neural Networks With Application to the Exploitation of a Slate Mine Mathematical Geosciences. ,vol. 36, pp. 463- 486 ,(2004) , 10.1023/B:MATG.0000029300.66381.DD
Federico Girosi, Michael Jones, Tomaso Poggio, Regularization theory and neural networks architectures Neural Computation. ,vol. 7, pp. 219- 269 ,(1995) , 10.1162/NECO.1995.7.2.219
Henning Omre, Bayesian kriging—Merging observations and qualified guesses in kriging Mathematical Geosciences. ,vol. 19, pp. 25- 39 ,(1987) , 10.1007/BF01275432
Martin Schlather, Tilmann Gneiting, Stochastic Models That Separate Fractal Dimension and the Hurst Effect Siam Review. ,vol. 46, pp. 269- 282 ,(2004) , 10.1137/S0036144501394387
J.M. Mat�as, A. Vaamonde, J. Taboada, W. Gonz�lez-Manteiga, Support vector machines and gradient boosting for graphical estimation of a slate deposit Stochastic Environmental Research and Risk Assessment. ,vol. 18, pp. 309- 323 ,(2004) , 10.1007/S00477-004-0185-5