Abstract
Geostatistics has become a preferred tool for the identification of lithofacies from sparse data, such as measurements of hydraulic conductivity and porosity. Recently we demonstrated that the support vector machine (SVM), a tool from machine learning, can be readily adapted for this task, and offers significant advantages. On the conceptual side, the SVM avoids the use of untestable assumptions, such as ergodicity, while on the practical side, the SVM out performs geostatistics at low sampling densities. In this study, we use the SVM within an inverse modeling framework to incorporate hydraulic head measurements into lithofacies delineation, and identify the directions of feuture research.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
- Support Vector Machine
- Hydraulic Conductivity
- Hydraulic Head
- Support Vector Machine Parameterization
- Untestable Assumption
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Alcolea A, Carrera J, Medina A (2006) Pilot points method incorporating prior information for solving the groundwater flow inverse problem. Adv Water Resour 29: 1678–1689
Carrera J, Neuman SP (1986) Estimation of aquifer parameters under transient and steady sate conditions. 3. Application to synthetic and field data. Water Resour Res 22: 228–242
Eppstein MJ, Dougherty DE (1996) Simultaneous estimation of transmissivity values and zonation. Water Resour Res 32: 3321–3336
Guadagnini L, Guadagnini A, Tartakovsky DM (2004) Probabilistic reconstruction of geologic facies. J Hydrol 294: 57–67
Guadagnini A, Wohlberg BE, Tartakovsky DM, De Simoni M (2006) Support vector machines for delineation of geologic facies from poorly differentiated data. In: Proceedings of the CMWR XVI conference, Copenhagen, June 2006
Hernandez AF, Neuman SP, Guadagnini A, Carrera J (2003) Conditioning mean steady state flow on hydraulic head and conductivity through geostatistical inversion. Stoch Environ Res Risk Assess 17: 329–338
Hernandez AF, Neuman SP, Guadagnini A, Carrera J (2006) Inverse stochastic moment analysis of steady state flow in randomly heterogeneous media. Water Resour Res 42: W05425, doi:10.1029/2005WR004449
Kanevski M, Maignan M (2004) Analysis and modelling of spatial environment data. EPFL Press, Marcel Dekker, Inc., Lausanne, Switzerland
Schölkopflkopf B, Smola AJ (2002) Learning with Kernels. The MIT Press, Cambridge, MA, USA
Sun NZ, Yeh WWG (1985) Identification of parameter structure in groundwater inverse problem. Water Resour Res 21: 869–883
Tartakovsky DM, Wohlberg BE (2004) Delineation of geologic facies with statistical learning theory. Geophys Res Lett 31:L18502 doi:10.1029/2004GL020864
Tsai FTC, Yeh WWG (2004) Characterization and identification of aquifer heterogeneity with generalized parameterization and Bayesian estimation. Water Resour Res 40: W10102 doi:10.1029/2003WR002893
Wohlberg BE, Tartakovsky DM, Guadagnini A (2006) Subsurface characterization with support vector machines. IEEE Trans Geosci Remote Sens 44:47–57 doi:10.1109/TGRS.2005. 859953
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer Science+Business Media B.V.
About this chapter
Cite this chapter
Tartakovsky, D.M., Guadagnini, A., Wohlberg, B.E. (2008). Machine Learning Methods for Inverse Modeling. In: Soares, A., Pereira, M.J., Dimitrakopoulos, R. (eds) geoENV VI – Geostatistics for Environmental Applications. Quantitative Geology and Geostatistics, vol 15. Springer, Dordrecht. https://doi.org/10.1007/978-1-4020-6448-7_10
Download citation
DOI: https://doi.org/10.1007/978-1-4020-6448-7_10
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-4020-6447-0
Online ISBN: 978-1-4020-6448-7
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)