Study on logging interpretation of coal-bed methane content based on deep learning
- 29 Downloads
To solve quantitative interpretation problems in coal-bed methane logging, deep learning is introduced in this study. Coal-bed methane logging data and laboratory results are used to establish a deep belief network (DBN) to compute coal-bed methane content. Network parameter effects on calculations are examined. The calculations of DBN, statistical probabilistic method and Langmuir equation are compared. Results show that, first, the precision and speed of DBN calculation should determine the restricted Boltzmann machine’s quantity. Second, the hidden layer neuron quantity must align with calculation accuracy and stability. Third, the ReLU function is the best for logging data; the Sigmoid function and Linear function are second; and the Softmax function has no effect. Fourth, the cross-entropy function is superior to MSE function. Fifth, RBMs make DBN more accuracy than BPNN. Furthermore, DBN calculation accuracy and stability are better than those of statistical probabilistic method and Langmuir equation.
KeywordsCoal-bed methane Geophysics logging Deep learning Restricted Boltzmann machine Coal-bed methane content
This research was supported by the Natural Science Foundation of Xinjiang Uygur Autonomous Region (2017D01B08), the Scientific Research Planning Project of Xinjiang Uygur Autonomous Region (XJEDU2017S056 and XJEDU2017S057), the Ph.D. Research Startup Foundation of the Xinjiang Institute of Engineering (2016xgy341812), Tianchi Doctor Research Project of Xinjiang Uygur Autonomous Region (BS2017001) and Xinjiang Uygur Autonomous Region key specialty of Geological Engineering.
- Bhanja AK, Srivastava OP (2008) A new approach to estimate CBM gas content from well logs. SPE115563:1–5. https://doi.org/10.2118/115563-ms
- Hinton GE (2012) A practical guide to training restricted boltzmann machines, vol 7700. Springer, Berlin, pp 599–619Google Scholar
- Juanjuan L, Hong C (2006) Researching development on BP neural networks. Control Eng China 13(5):449–451Google Scholar
- Junsheng H, Ying W (1999) Interpretation of well logging data for coalbed methane using BP neural network. Geol Prospect 35(3):41–45Google Scholar
- Liu Z, Luo P (2015) Deep learning face attributes in the wild. In: Proceedings of the IEEE international conference on computer vision, pp 3730–3738. https://doi.org/10.1109/iccv.2015.425
- Pan H, Liu G (1997) Applying back- propagation artificial neural networks to predict coal quality parameters and coal bed gas content. Earth Sci J China Univ Geosci 22(2):210–214Google Scholar
- Wang Z (2009) Logging methods evaluation of the gas content in Coal-bed methane reservoir. Jilin University, Changchun, pp 55–60Google Scholar
- Xiaofan Y, Tingkui C (1994) Inherent advantages and disadvantages of artificial neural networks. Comput Sci 2:23–26Google Scholar
- Yang Y, Cloud T, Kirk CV (2005) New application of well log parameters in coalbed methane (CBM) reservoir evaluation at the Drunkards Wash Unit, Uinta Basin, Utah. In: SPE Eastern regional meeting, 1–9. https://doi.org/10.2523/97988-ms
- Zeliang J, Haifei X, Haibin G (2013) Technology for evaluation of CBM reservoir logging and its application. Coal Geol Explor 41(2):42–45Google Scholar