Page 132 - Machine Learning for Subsurface Characterization

108 Machine learning for subsurface characterization

logs.
80. 80. 80. 80.
EPSI_XO_F0 EPSI_XO_F1 EPSI_XO_F2 EPSI_XO_F3
8 permittivity-dispersion

0.8 1000. 0.8 1000. 0.8 1000. 0.8 1000.
COND_XO_F0 (MM/M) COND_XO_F1 (MM/M) COND_XO_F2 (MM/M) are 8

7 COND_XO_F3 (MM/M) Tracks

160. 0. 0. 160. 0. 0. and logs;

6 DTC_BHP (us/ft) DTS_BHP (us/ft)

40. 40. conductivity-dispersion
2000. 2000. 2000.

5 RLA1 (OHMM) RLA2 (OHMM) RLA3 (OHMM) Features and targets for training/testing the SNN model. Track 1 is depth, Track 2 is gamma ray log, Track 3 contains density porosity and neutron porosity logs; Track 4 contains bulk density, volume of clay, and formation photoelectric factor logs; Track 5 contains

0.2 0.2 0.2 Track
3. 0.5 6. RLA3);

4 RHOZ (G/C3) VCL_BHP (V/V) PEFZ (B/E) and RLA2,

2. 0. 0.
0.4 0.4 (RLA1,

3 DPHZ (CFCF) NPOR (CFCF) investigation

0. 0. of
150. depths
GR_EDTC (GAPI) six

2 the

0. of out
XX00 XX00
1 FIG. 4.2 three at