Page 153 - Machine Learning for Subsurface Characterization

Stacked neural network architecture Chapter 4 127

in the DD logs. Low resistivity, high porosity, high relative dielectric permit-
tivity, large dielectric dispersion, low skewness and large coefficient of varia-
tion of conventional logs facilitate better DD log synthesis.

References

[1] Han Y, Misra S, Simpson G. Dielectric dispersion log interpretation in Bakken Petroleum
System. In: SPWLA 58th annual logging symposium. Society of Petrophysicists and Well-
Log Analysts, June; 2017.
[2] Ko WL, Mittra R. Conductivity estimation by neural network. In: IEEE Antennas and Prop-
agation Society international symposium, AP-S digest, June, vol. 4; 1995.
[3] Brovko AV, Ethan KM, Vadim VY. Waveguide microwave imaging: neural network recon-
struction of functional 2-D permittivity profiles. IEEE Trans Microw Theory Tech 2009;57
(2):406–14.
[4] Hasan A, Andrew FP. Measurement of complex permittivity using artificial neural networks.
IEEE Antennas Propag Mag 2011;53(1):200–3.
[5] Paul S, Sindhu TK. A neural network model for predicting the dielectric permittivity of epoxy-
aluminum nanocomposite and its experimental validation. IEEE Trans Compon Packag Manuf
Technol 2015;5(8):1122–8.
[6] Nitta T. Complex-valued neural networks: utilizing high-dimensional parameters. Hershey,
NY: IGI Global; 2009.
[7] Yang C, Bose NK. Landmine detection and classification with complex-valued hybrid neural
network using scattering parameters dataset. IEEE Trans Neural Netw 2005;16(3):743–53.
[8] Ji R, et al. Prediction of soil moisture with complex-valued neural network. In: IEEE control
and decision conference (CCDC), 29th Chinese, May; 2017.
[9] Wu Y, Misra S, Sondergeld C, Curtis M, Jernigen J. Machine learning for locating organic
matter and pores in scanning electron microscopy images of organic-rich shales. Fuel
2019;253:662–76.
[10] Li H, Misra S, He J. Neural network modeling of in situ fluid-filled pore size distributions in
subsurface shale reservoirs under data constraints. Neural Comput Applic 2019;1–13.
[11] Genty C. Distinguishing carbonate reservoir pore facies with nuclear magnetic resonance as an
aid to identify candidates for acid stimulation [M.S. thesis]. Texas, USA: Dept. Petroleum
Eng., Texas A&M Univ.; 2006.
[12] Cheng C, et al. Long-term prediction of discharges in Manwan Reservoir using artificial neural
network models. In: Advances in neural networks–ISNN 2005. vol. 3498. 2005. p. 1040–5.
[13] Han Y, Misra S. Joint petrophysical inversion of multifrequency conductivity and permittivity
logs derived from subsurface galvanic, induction, propagation, and dielectric dispersion mea-
surements. Geophysics 2018;83(3):1–63.
[14] He J, Misra S. Generation of synthetic dielectric dispersion logs in organic-rich shale forma-
tions using neural-network models. Geophysics 2019;84(3):D117–29.