Abstract
This contribution discusses the usage of blind tests, BT, to cross-validate and interpret the results of predictions by statistical models applied to spatial databases. Models such as Bayesian probability, empirical likelihood ratio, fuzzy sets, or neural networks, were and are being applied to identify areas likely to contain events such as undiscovered mineral resources, zones of high natural hazard, or sites with high potential environmental impact. Processing the information in a spatial database, the models establish the relationships between the distribution of known events and their contextual settings, described by both thematic and continuous data layers. The relationships are to locate situations where similar events are likely to occur. Maps of predicted relative resource potential or of relative hazard/impact levels are generated. They consist of relative values that need careful quantitative scrutiny to be interpreted for taking decisions on further action in exploration or on hazard/impact mitigation and avoidance. The only meaning of such relative values is their rank. Obviously, to assess the reliability of the predicted ranks, tests are indispensable. This is also a consequence of the impracticality of waiting for the future to reveal the goodness of our prediction. During the past decade only a few attempts have been made by some researchers to cross-validate the results of spatial predictions. Furthermore, assumptions and applications of cross-validations differ considerably in a number of recent case studies. A perspective for all such experiments is provided using two specific examples, one in mineral exploration and the other in landslide hazard, to answer the fundamental question: how good is my prediction?
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
Agterberg FP, Bonham-Carter GF (2005) Measuring the performance of mineral potential maps. Nat Resour Res 14 (1): 1–17
Arthur JD, Wood HAR, Baker AF, Cichon JR, Raines GL (2007) Development and implementation of a Bayesian-based aquifer vulnerability assessment in Florida. Nat Resour Res 16 (2): 93–107
Begueria S (2006) Validation and evaluation of predictive models in hazard assessment and risk management. Nat Hazards 37: 315–329
Behnia P (2007) Application of Radial Basis Functional Link Networks to exploration for Proterozoic mineral deposits in central Iran. Nat Resour Res 16 (2): 147–158
Brown W, Groves D, Gedeon T (2003) Use of fuzzy membership input layers to combine subjective geological knowledge and empirical data in a neural network method for mineral-potential mapping. Nat Resour Res 12 (3): 183–200
Cheng Q (2004) Application of weights of evidence methods for assessment of flowing wells in the Greater Toronto Area, Canada. Nat Resour Res 13 (2): 77–86
Chung CF (2003) Use of airborne geophysical surveys for constructing mineral potential maps. Econ Geol Monogr 11: 879–891
Chung CF (2006) Using likelihood ratio functions for modeling the conditional probability of occurrence of future landslides for risk assessment. Comput Geosci 32 (8): 1052–1068
Chung CJ, Bonin D, Fannin RJ, Fabbri AG, Journeay M (2006) Uncertainty in predicting landslide hazard in the Coquitlam reservoir area, B.C., Canada. In: Proceedings of IAMG’06, Liege, Belgium, 3–8 Sept 2006, Session S09-07, p 4, CD
Chung CF, Fabbri AG (1993) Representation of geoscience data for information integration. J Nonrenew Res 2 (2): 122–139
Chung CF, Fabbri AG (1998) Three Bayesian prediction models for landslide hazard. In: Buccianti A (ed) Proceedings of international association for mathematical geology 1998 annual meeting (IAMG’98), Ischia, Italy, 3–7 October 1998, pp 204–211
Chung CF, Fabbri AG (1999) Probabilistic prediction models for landslide hazard mapping. Photogramm Eng Remote Sens 65 (12): 1389–1399
Chung CF, Fabbri AG (2003) Validation of spatial prediction models for landslide hazard mapping. In: Chacon J, Corominas J (eds) Special issue on landslides and GIS. Nat Hazards 30 (3): 451–472
Chung CF, Fabbri AG (2004) Systematic procedures of landslide hazard mapping for risk assessment using spatial prediction models. In: Glade T, Anderson MG, Crozier MJ (eds) Landslide hazard and risk. John Wiley & Sons, New York, pp 139–174
Chung CF, Fabbri AG (2005) On mineral potential maps and how to make them useful. In: Cheng Q, Bonham-Carter G (eds) GIS and spatial analysis, proceedings of IAMG ’05, vol 1, Toronto, Canada, 21–26 August 2005, pp 533–538
Chung CF, Fabbri AG (2008) Predicting future landslides for risk analysis – spatial models and cross-validation of their results. Geomorphology 94 (3–4): 438–452
Chung CF, Fabbri AG, Chi KH (2002a) A strategy for sustainable development of nonrenewable resources using spatial prediction models. In: Fabbri AG, Gäal G, McCammon RB (eds) Geoenvironmental deposit models for resource exploitation and environmental security. Kluwer, Dordrecht, pp 101–118
Chung CF, Fabbri AG, Jang DH, Scholten HJ (2005a) Risk assessment using spatial prediction model for natural disaster preparedness. In: van Oosterom P, Zlatanova S, Fendel EM (eds) Geo-informastion for disaster management. Springer, Berlin, pp 619–640. Proceedings of Gi4DM, the first symposium on geo-information for disaster management, Delft, Netherlands, 21–23 March 2005, pp 619–640
Chung CF, Fabbri AG, van Westen CJ (1995) Multivariate regression analysis for landslide hazard zonation. In: Carrara A, Guzzetti F (eds) Geographical information systems in assessing natural hazards. Kluwer Academic Publishers, Dordrecht, pp 107–133
Chung CF, Harris JR, Keating P, Kjarsgaard B, Parsons S (2005b) Preliminary report on developing a mineral potential map for diamond exploration in Lac de Gras area, NWT. Unpublished manuscript
Chung CF, Kojima H, Fabbri AG (2002b) Stability analysis of prediction models for landslide hazard mapping. In: Allison RJ (ed) Applied geomorphology: theory and practice. John Wiley and Sons, Ltd., New York, pp 3–19
Coolbaugh MF, Raines GL, Zehner E (2007) Assessment of exploration bias in data-driven predictive models and the estimation of undiscovered resources. Nat Resour Res 16 (2): 199–207
Corominas J, Copons R, Vilaplana JM Altimir J, Amigó J (2003) Integrated landslide susceptibility analysis and hazard assessment in the principality of Andorra. In: Chacon J, Corominas J (eds) Special issue on landslides and GIS. Nat Hazards 30 (3): 421–435
de Quadros TFP, Koppe JC, Strieder AJ, Coste JFCL (2006) Mineral potential mapping: a comparison of weights-of-evidence and fuzzy methods. Nat Resour Res 15 (1): 49–65
Fabbri AG, Chung CF, Cendrero A, Remondo J (2003) Is prediction of future landslides possible with a GIS? In: Chacon J, Corominas J (eds) Special issue on landslides and GIS. Nat Hazards 30 (3): 487–499
Fabbri AG, Chung CF, Jang DH (2004) A software approach to spatial predictions of natural hazards and consequent risks. In: Brebbia CA (ed) Risk Analysis IV. WIT Press, Southampton, Boston, pp 289–305
Harris DV, Zurcher L, Stanley M, Marlowe J, Pan G (2003) A comparative analysis of favorability mapping by Weights of Evidence, Probabilistic Neural Networks, Discriminant Analysis and Logistic Regression. Nat Resour Res 12 (4): 241–255
Lee S, Ryu JH, Lee MJ, Won JS (2006) The application of artificial neural networks for landslide susceptibility mapping at Jangshung, Korea. Mat Geol 38 (2): 199–220
Masetti M, Poli S, Sterlacchini S (2007) The use of Weights-of-Evidence modeling technique to estimate the vulnerability of groundwater to nitrate contamination. Nat Resour Res 16 (2): 109–119
Nelson EP, Connors KA, Suárez CS (2007) GIS-based slope stability analysis, Chuquicamata open pit copper mine, Chile. Nat Resour Res 16 (2): 171–190
Nykauml;nen V, Ojala VJ (2007) Spatial analysis techniques as successful mineral-potential mapping tools for orogenic gold deposits in the northern Fennoscandian Shield, Finland. Nat Resour Res 16 (2): 85–92
Poli S, Sterlacchini S (2007) Landslide representation strategies in susceptibility studies using Weights-of-Evidence modeling technique. Nat Resour Res 16 (2): 121–134
Porwal A, Carranza EJM, Hale M (2003a) Knowledge-driven and data-driven fuzzy models for predictive mineral potential mapping. Nat Resour Res 12 (1): 1–25
Porwal A, Carranza EJM, Hale M (2003b) Artificial neural networks for mineral-potential mapping: a case study from Aravalli province, western India. Nat Resour Res, 12 (3): 155–171
Porwal A, Carranza EJM, Hale M (2006a) Bayesian network classifiers for mineral potential mapping. Comput Geosci 32: 1–16
Porwal A, Carranza EJM, Hale M (2006b) A hybrid fuzzy weights-of-evidence model for mineral potential mapping. Nat Resour Res 15 (1): 1–14
Raines GL (1999) Evaluation of weights of evidence to predict epithermal-gold deposits in the great basin of the western United States. Nat Resour Res 8 (4): 257–276
Remondo J, González-Díez A, Díaz de Terán JR, Cendrero A (2003a) Quantitative landslide susceptibility models by means of spatial data analysis techniques; a case study in the lower Deva valley, Guipuzcoa (Spain). In: Chacon J, Corominas J (eds) Special issue on landslides and GIS. Nat Hazards 30 (3): 267–279
Remondo J, Gonzälez-Díez A, Díaz de Terän JR, Cendrero A, Fabbri AG, Chung CF (2003b) Validation of landslide susceptibility maps; examples and applications from a case study in Northern Spain. In: Chacon J, Corominas J (eds) Special issue on landslides and GIS. Nat Hazards 30 (3): 437–449
Robinson GR Jr, Larkins PM (2007) Probabilistic prediction models for aggregate quarry siting. Nat Resour Res 16 (2): 135–146
Santacana N, Baeza C, Corominas J, de Paz A, Marturiäp J (2003) A GIS-based multivariate statistical analysis for shallow landslide susceptibility mapping in La Pobla de Lillet Area (Eastern Pyrenees, Spain). In: Chacon J, Corominas J (eds) Special issue on landslides and GIS. Nat Hazards 30 (3): 281–295
Singer DA, Kouda R (1999) A comparison of weight-of-evidence method and probabilistic neural networks. Nat Resour Res 8 (4): 287–298
Skabar AA (2005) Mapping mineralization probabilities using multilayer perceptrons. Nat Resour Res 14 (2): 109–123
Tissari S, Nykänen V, Lerssi J, Kolehmainen M (2007) Classification of soil groups using Weights-of-Evidence method and RBFLN-neural nets. Nat Resour Res 16 (2): 159–169
van Westen CJ, Rengers N, Soeters R (2003) Use of geomorphological information in indirect landslide susceptibility assessment. In: Chacon J, Corominas J (eds) Special issue on landslides and GIS. Nat Hazards 30 (3): 399–419
Zêzere JL, Reis E, Garcia R, Oliveira S, Rodrigues ML, Vieira G, Ferreira AB (2004) Integration of spatial and temporal data for the definition of different landslide hazard scenarios in the area north of Lisbon (Portugal). Nat Hazards Earth Syst Sci 4: 133–146
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Fabbri, A.G., Chung, CJ. (2008). On Blind Tests and Spatial Prediction Models. In: Bonham-Carter, G., Cheng, Q. (eds) Progress in Geomathematics. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69496-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-540-69496-0_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69495-3
Online ISBN: 978-3-540-69496-0
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)