Abstract
Subsurface gypsum dissolution hazards imply risks to the construction and operation of new transport infrastructure including subsidence, cavity collapse and cavity flooding. This is a concern in Abu Dhabi, United Arab Emirates, where gypsum geohazards are observed and an extensive transportation network is planned. This paper proposes an artificial neural network (ANN)-based approach for the prediction of underground gypsum. Moreover, the approach is developed to provide the expected probability of gypsum presence and to generate gypsum hazard maps. Such maps provide both a general planning instrument and an input for the decision support systems. An application to Masdar City, Abu Dhabi, is discussed at the site of a planned metro line. Twenty-one boreholes are used to train and validate the ANN that is used to produce a 3D geological model identifying the expected presence of gypsum. Most significantly, the application illustrates how gypsum hazard maps can be obtained at any required depth providing planners and designers with essential information for risk assessment and management.
Similar content being viewed by others
References
Ford D, Williams P (2007) Karst hydrology and geomorphology, 1st edn. Wiley, New York
Jones CF, Cooper HA (2005) Road construction over voids caused by active gypsum dissolution, with an example from Ripon, North Yorkshire, England. J Environ Geol 48:384–394
Casagrande G, Cucchi F, Zini L (2005) Hazard connected to railway tunnel construction in karstic area: applied geomorphological and hydrogeological surveys. Nat Hazards Earth Syst Sci 5:243–250
Department of Transport (2009) Surface transport master plan: a vision for connecting Abu Dhabi. Government of Abu Dhabi, Abu Dhabi, UAE
Longley PA, Goodchild M, Maguire D, Rhind D (2010) Geographic information systems and science, 3rd edn. Wiley, New York
Kuzevicova Z, Gergelova M, Kuzevic S, Polkova J (2014) Spatial interpolation and calculation of the volume of irregular solid. Int J Eng Appl Sci 4(8):14–21
Isaaks EH, Srivastava RM (1990) An introduction to applied geostatistics. Oxford University Press, New York
Hengl T (2009) A practical guide to geostatistical mapping. Office for Official Publications of the European Communities, Luxembourg
Arel E (2012) Predicting the spatial distribution of soil profile in Adapazari/Turkey by artificial neural networks using CPT data. J Comput Geosci 43:90–100
Erzin Y, Cetin T (2013) The prediction of the critical factor of safety of homogeneous finite slopes using neural networks and multiple regressions. J Comput Geosci 51:305–313
Yang W, Xiaohong X (2013) Prediction of mining subsidence under thin bedrocks and thick unconsolidated layers based on field measurement and artificial neural networks. J Comput Geosci 52:199–203
Pradhan B (2011) An assessment of the use of an advanced neural network model with five different training strategies for preparation of landslide susceptibility maps. J Data Sci 9:65–81
Nevtipilova V, Pastwa J, Boori SB, Vozenilek V (2014) Testing artificial neural network (ANN) for spatial interpolation. Int J Geol Geosci 3(2):1–9
Gangopadhyay S, Gautam TR, Gupta AD (1999) Subsurface characterization using artificial neural network and GIS. J Comput Civ Eng 13(3):153–161
FUGRO Middle East (2008) Consultancy services for Masdar development. Geotechnical investigation for Masdar City. Fugro Middle East, Abu Dhabi, UAE
MacDonald M (2010) Site-wide infrastructure design, site-wide infrastructure design geotechnical report. Abu Dhabi, United Arab Emirates
Banimahd M, Yasrobi SS, Woodward PK (2005) Artificial neural network for stress-strain behavior of sandy soils: knowledge based verification. J Comput Geotech 32(5):337–386
Poggio T, Girosi F (1990) Networks for approximation and learning. Proc Inst Electr Electron Eng 78(9):1481–1497
Abdulla MB, Herzallah RO, Hammad MA (2013) Pipeline leak detection using artificial neural networks. In: Proceedings of the international conference on modelling, identification and control, Cairo, Egypt, pp. 329–332
Zhang LM (1993) Artificial neural networks. Fudan University Press, Shanghai
Abdulla MB (2013) Experimental study of pipeline leak detection using artificial neural networks. Master’s dissertation, University of Jordan, Jordan
Shahin MA, Jaksa BM, Maier HR (2009) Recent advances and future challenges for artificial neural systems in geotechnical engineering applications. J Adv Artif Neural Syst 2009:9, Art ID 308239. doi:10.1155/2009/308239
Herzallah R (2011) Enhancing the performance of intelligent control systems in the face of higher levels of complexity and uncertainty. Int J Model Identif Control 12(4):311–327
Herzallah R, Lowe D (2002) A novel approach to modeling and exploiting uncertainty in stochastic control systems. In: International conference on artificial neural networks, ICANN, vol 1, pp 801–806, Spain
Barnard E, Wessels LFA (1992) Extrapolation and interpolation in neural network classifier. Trans IEEE Control Syst. doi:10.1109/37.158890
Wu W, Maier HR, Dandy GC, May R (2012) Exploring the impact of splitting data methods on artificial neural network models. In: 10th International conference on hydroinformatics, Germany
Nabney IT (2002) NETLAB: algorithms for pattern recognition. Springer, New York, USA
Comets F (2011) Logistic regression, international encyclopedia of statistical science. ISBN: 978-3-642-04897-5 (Print) 978-3-642-04898-2 (Online)
Abdulla MB, Herzallah RO (2015) Probabilistic multiple model neural network based leak detection system: experimental study. J Loss Prev Process Ind 36:30–38
Herzallah R, Lowe D (2007) Distribution modelling of nonlinear inverse controller under a Bayesian framework. IEEE Trans Neural Netw 18(1):107–114
Herzallah R, Lowe D (2003) Robust control of nonlinear stochastic systems by modelling conditional distributions of control signals. Neural Comput Appl 12:98–108
Bishop C (2009) Pattern recognition and machine learning. Springer, New York, USA
Montgomery D, Runger G (2013) Applied statistics and probability for engineers, 6th edn. Wiley, New York
Acknowledgements
This work was funded by the Cooperative Agreement between Masdar Institute of Science and Technology (Masdar Institute), Abu Dhabi, UAE and Massachusetts Institute of Technology (MIT), Cambridge, MA, USA. The authors benefited greatly from discussions with Professor Herbert Einstein.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Abdulla, M.B., Costa, A.L. & Sousa, R.L. Probabilistic identification of subsurface gypsum geohazards using artificial neural networks. Neural Comput & Applic 29, 1377–1391 (2018). https://doi.org/10.1007/s00521-016-2655-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2655-3