Quantitative thickness prediction of tectonically deformed coal using Extreme Learning Machine and Principal Component Analysis: a case study

The thickness of tectonically deformed coal (TDC) has positive correlation associations with gas outbursts. In order to predict the TDC thickness of coal beds, we propose a new quantitative predicting method using an extreme learning machine (ELM) algorithm, a principal component analysis (PCA) algorithm, and seismic attributes. At first, we build an ELM prediction model using the PCA attributes of a synthetic seismic section. The results suggest that the ELM model can produce a reliable and accurate prediction of the TDC thickness for synthetic data, preferring Sigmoid activation function and 20 hidden nodes. Then, we analyze the applicability of the ELM model on the thickness prediction of the TDC with real application data. Through the cross validation of near-well traces, the results suggest that the ELM model can produce a reliable and accurate prediction of the TDC. After that, we use 250 near-well traces from 10 wells to build an ELM predicting model and use the model to forecast the TDC thickness of the No. 15 coal in the study area using the PCA attributes as the inputs. Comparing the predicted results, it is noted that the trained ELM model with two selected PCA attributes yields better predication results than those from the other combinations of the attributes. Finally, the trained ELM model with real seismic data have a different number of hidden nodes (10) than the trained ELM model with synthetic seismic data. In summary, it is feasible to use an ELM model to predict the TDC thickness using the calculated PCA attributes as the inputs. However, the input attributes, the activation function and the number of hidden nodes in the ELM model should be selected and tested carefully based on individual application. We use extreme learning machine to estimate tectonically deformed coal (TDC).The inputs are linearly uncorrelated PCs calculated from seismic attributes.The inputs, the activation function and the hidden nodes affect the estimate.Sigmoid function, in this case, is the best for the estimate of the TDC thickness.The signal-to-noise ratio of input data affects the estimate.

[1]  Kurt J. Marfurt,et al.  Seismic Attributes for Prospect Identification and Reservoir Characterization , 2007 .

[2]  SongShiji,et al.  Trends in extreme learning machines , 2015 .

[3]  Abdulkadir Sengur,et al.  GA-SELM: Greedy algorithms for sparse extreme learning machine , 2014 .

[4]  B. Schrauwen,et al.  Reservoir computing and extreme learning machines for non-linear time-series data analysis , 2013, Neural Networks.

[5]  Farid Sheikholeslam,et al.  Stability analysis and design of fuzzy control systems , 1998, 1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).

[6]  Kazuo Tanaka,et al.  Stability analysis and design of fuzzy control systems , 1992 .

[7]  K. Payrazyan,et al.  Principal Component Analysis Applied to 3D Seismic Data for Reservoir Property Estimation , 2001 .

[8]  Sébastien Da Veiga,et al.  Appropriate formulation of the objective function for the history matching of seismic attributes , 2013, Comput. Geosci..

[9]  Steven J. Cooke,et al.  A moving target—incorporating knowledge of the spatial ecology of fish into the assessment and management of freshwater fish populations , 2016, Environmental Monitoring and Assessment.

[10]  Quanlin Hou,et al.  Macromolecular and pore structures of Chinese tectonically deformed coal studied by atomic force microscopy , 2015 .

[11]  Yanqing Zhao,et al.  Coalbed methane sorption related to coal deformation structures at different temperatures and pressures , 2012 .

[12]  R.J.W. Bunt Sea Lion Field, North Falkland Basin: The Use of Seismic Attributes in Fan and Reservoir Definition , 2015 .

[13]  Guang-Bin Huang,et al.  An Insight into Extreme Learning Machines: Random Neurons, Random Features and Kernels , 2014, Cognitive Computation.

[14]  Wellington Pinheiro Dos Santos,et al.  Detection and classification of masses in mammographic images in a multi-kernel approach. , 2016, Computer methods and programs in biomedicine.

[15]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[16]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.

[17]  R. Gayer,et al.  The impact of tectonic deformation upon coal seams in the South Wales coalfield, UK , 1999 .

[18]  Yugui Zhang,et al.  The influence of tectonic deformation on some geochemical properties of coals—a possible indicator of outburst potential , 2003 .

[19]  I. Jolliffe Principal Component Analysis , 2002 .

[20]  Paul C. Hackley,et al.  Organic petrology of Paleocene Marcelina Formation coals, Paso Diablo mine, western Venezuela: Tectonic controls on coal type , 2007 .

[21]  Yiwen Ju,et al.  New research progress on the ultrastructure of tectonically deformed coals , 2009 .

[22]  M. Reza Rezaee,et al.  Petrophysical data prediction from seismic attributes using committee fuzzy inference system , 2009, Comput. Geosci..

[23]  H. R. Hardy,et al.  Void detection at an anthracite mine using an in-seam seismic method , 2008 .

[24]  Bruce S. Hart,et al.  Channel detection in 3-D seismic data using sweetness , 2008 .

[25]  Basil Beamish,et al.  Coalbed methane sorption related to coal composition , 1998 .

[26]  Benoît Frénay,et al.  Feature selection for nonlinear models with extreme learning machines , 2013, Neurocomputing.

[27]  Yanbin Yao,et al.  Evaluation of coal texture distributions in the southern Qinshui basin, North China: Investigation by a multiple geophysical logging method , 2015 .

[28]  Yujiro Ogawa,et al.  Mechanism of methane flow through sheared coals and its role on methane recovery , 2003 .

[29]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[30]  Mikhail Kanevski,et al.  Extreme Learning Machines for spatial environmental data , 2015, Comput. Geosci..

[31]  R. Deo,et al.  An extreme learning machine model for the simulation of monthly mean streamflow water level in eastern Queensland , 2016, Environmental Monitoring and Assessment.

[32]  Wei Li,et al.  Deformed coal types and pore characteristics in Hancheng coalmines in Eastern Weibei coalfields , 2012 .

[33]  Xin Wang,et al.  Quantitative Prediction of Tectonic Coal Thickness Based on FNN and Seismic Attributes , 2014 .

[34]  Liming Yang,et al.  A sparse extreme learning machine framework by continuous optimization algorithms and its application in pattern recognition , 2016, Eng. Appl. Artif. Intell..