Abstract
Aiming to the fact that it is still difficult to reasonably forecasting the karstic collapse, the model based on GP machine learning is proposed for forecasting of karstic collapse. According to few learning samples, the nonlinear mapping relationship between karstic collapse and its influencing factors is established by GP model. The model was applied to a real engineering. The results of case study show that GP model is feasible, effective and simple to implement for forecasting of karstic collapse. Compared with artificial neural networks and support vector machine, it has attractive merits of self-adaptive parameters determination and excellent capacity for solving non-linear small samples problems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Zhang, L.-F., Zeng, X.-S., Yao, Y.-S., Liao, W.-L.: Review on karst collapse in China. The Chinese Journal of Geological Hazard and Control 18(3), 126–130 (2007)
Liu, Z.-K., Liang, J.-C.: The influence on construction site for karst cave and soil cave in the karst area. The Geological Press, Beijing (2006)
Qin, L.-W., Shi, J.: Evaluation and prediction of karst collapse in Guangxi. The Chinese Journal of Geological Hazard and Control 8(suppl.), 43–53 (1997)
Qiu, X.-R.: Grey fuzzy synthetic assessment for stability of karst collapse. Hydrogeology & Engineering Geology 31(4), 58–61 (2004)
Bao, H.-M., Hu, C.-S.: Neural network prediction of karstic ground collapse. Journal of Engineering Geology 10(3), 299–304 (2002)
Lai, Y.-B., Qiao, C.-S.: Intelligent model of karstic collapse prediction based on SVM. Journal of Beijing Jiaotong University 32(1), 36–39, 43 (2008)
Xiong, Z.-H., Zhang, J.-C., Shao, H.-H.: GP-based soft sensor modeling. Journal of System Simulation 17(4), 793–794 (2005)
Seeger, M.: Gaussian processes for machine learning. International Journal of Neural System 14(2), 69–106 (2004)
Girolami, M., Rogers, S.: Variational Bayesian multinomial probit regression with Gaussian process priors. Neural Computation 18(8), 1790–1817 (2006)
Sofiane, B.-B., Amine, B.: Gaussian process for nonstationary times series prediction. Computational Statistics & Data Analysis 47(4), 705–712 (2004)
Gramacy, R.-B.: tgp: An R package for Bayesian nonstationary, semiparametric nonlinear regression and design by treed Gaussian process models. Journal of Statistical Software 19(19), 1–46 (2007)
Su, G.-S., Song, Y.-C., Yan, L.-B.: A new method for forecasting of blasting effect in rock mass. Chinese Journal of Rock Mechanics and Engineering 26(suppl. 1), 3509–3514 (2007)
Zhang, Y., Su, G.-S., Yan, L.-B.: Study on Gaussian process machine learning method for identifying the distribution structure of reservoir. Advances in Science and Technology of Water Resources 29(2), 13–15 (2009)
Su, G.-S., Zhang, Y., Zhang, X.-F.: Application of Gaussian Process machine learning to the prediction of groundwater level. China Rural Water and Hydropower 54(12), 48–50 (2008)
Rasmussen, C.-E., Williams, C.-K.-I.: Gaussian Processes for Machine Learning. The MIT Press, Cambridge (2006)
Wen, X., Zhou, L., Li, X.: MATLAB neural network simulation and application. Science Press, Beijing (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, Y., Su, G., Yan, L. (2011). Gaussian Process Machine Learning Model for Forecasting of Karstic Collapse. In: Zeng, D. (eds) Applied Informatics and Communication. ICAIC 2011. Communications in Computer and Information Science, vol 224. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23214-5_48
Download citation
DOI: https://doi.org/10.1007/978-3-642-23214-5_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23213-8
Online ISBN: 978-3-642-23214-5
eBook Packages: Computer ScienceComputer Science (R0)