The Kernal Support Vector Machine (KSVM) is a nonlinear supervised statistical learning algorithm that recognizes the discrete classes for the given data based on maximizing the margin around the separating hyperplane and the decision function is fully specified by a subset of the supporting vectors. The posterior distribution was validated using the true and predicted facies counts matrix that estimated by KSVM.
In this work, KSVM was adopted her to estimate the continuous predicted probability Distribution of Lithofacies in Karpur Dataset.
Install the packages required to implement KSVM algorithm with their functions.
#First, install the required packages.
require(kernlab)
## Loading required package: kernlab
require(e1071)
## Loading required package: e1071
require(ggplot2)
## Loading required package: ggplot2
##
## Attaching package: 'ggplot2'
##
## The following object is masked _by_ '.GlobalEnv':
##
## mpg
require(MASS)
## Loading required package: MASS
require(lattice)
## Loading required package: lattice
library(kernlab)
library(e1071)
library(ggplot2)
library(MASS)
library(lattice)
Call the dataset and show the dataset head: -
## depth caliper ind.deep ind.med gamma phi.N R.deep R.med SP
## 1 5667.0 8.685 618.005 569.781 98.823 0.410 1.618 1.755 -56.587
## 2 5667.5 8.686 497.547 419.494 90.640 0.307 2.010 2.384 -61.916
## 3 5668.0 8.686 384.935 300.155 78.087 0.203 2.598 3.332 -55.861
## 4 5668.5 8.686 278.324 205.224 66.232 0.119 3.593 4.873 -41.860
## 5 5669.0 8.686 183.743 131.155 59.807 0.069 5.442 7.625 -34.934
## 6 5669.5 8.686 109.512 75.633 57.109 0.048 9.131 13.222 -39.769
## density.corr density phi.core k.core Facies
## 1 -0.033 2.205 33.9000 2442.590 F1
## 2 -0.067 2.040 33.4131 3006.989 F1
## 3 -0.064 1.888 33.1000 3370.000 F1
## 4 -0.053 1.794 34.9000 2270.000 F1
## 5 -0.054 1.758 35.0644 2530.758 F1
## 6 -0.058 1.759 35.3152 2928.314 F1
Summary of the dataset.
## depth caliper ind.deep ind.med
## Min. :5667 Min. :8.487 Min. : 6.532 Min. : 9.386
## 1st Qu.:5769 1st Qu.:8.556 1st Qu.: 28.799 1st Qu.: 27.892
## Median :5872 Median :8.588 Median :217.849 Median :254.383
## Mean :5873 Mean :8.622 Mean :275.357 Mean :273.357
## 3rd Qu.:5977 3rd Qu.:8.686 3rd Qu.:566.793 3rd Qu.:544.232
## Max. :6083 Max. :8.886 Max. :769.484 Max. :746.028
##
## gamma phi.N R.deep R.med
## Min. : 16.74 Min. :0.0150 Min. : 1.300 Min. : 1.340
## 1st Qu.: 40.89 1st Qu.:0.2030 1st Qu.: 1.764 1st Qu.: 1.837
## Median : 51.37 Median :0.2450 Median : 4.590 Median : 3.931
## Mean : 53.42 Mean :0.2213 Mean : 24.501 Mean : 21.196
## 3rd Qu.: 62.37 3rd Qu.:0.2640 3rd Qu.: 34.724 3rd Qu.: 35.853
## Max. :112.40 Max. :0.4100 Max. :153.085 Max. :106.542
##
## SP density.corr density phi.core
## Min. :-73.95 Min. :-0.067000 Min. :1.758 Min. :15.70
## 1st Qu.:-42.01 1st Qu.:-0.016000 1st Qu.:2.023 1st Qu.:23.90
## Median :-32.25 Median :-0.007000 Median :2.099 Median :27.60
## Mean :-30.98 Mean :-0.008883 Mean :2.102 Mean :26.93
## 3rd Qu.:-19.48 3rd Qu.: 0.002000 3rd Qu.:2.181 3rd Qu.:30.70
## Max. : 25.13 Max. : 0.089000 Max. :2.387 Max. :36.30
##
## k.core Facies
## Min. : 0.42 F8 :184
## 1st Qu.: 657.33 F9 :172
## Median : 1591.22 F10 :171
## Mean : 2251.91 F1 :111
## 3rd Qu.: 3046.82 F5 :109
## Max. :15600.00 F3 : 55
## (Other): 17
Visualize the dataset:
Modeling the Facies given well logs and core data through KSVM model:
## Support Vector Machine object of class "ksvm"
##
## SV type: C-bsvc (classification)
## parameter : cost C = 10
##
## Gaussian Radial Basis kernel function.
## Hyperparameter : sigma = 0.1
##
## Number of Support Vectors : 270
##
## Objective Function Value : -29.5751 -5.7183 -12.6285 -9.7755 -3.1325 -5.1116 -3.2175 -31.3784 -466.329 -80.5273 -33.3939 -35.5583 -6.013 -16.441 -4.2832 -2.1841 -2.6184 -2.0174 -32.6271 -7.1898 -8.1195 -4.2553 -13.3536 -66.2724 -69.0838 -27.5201 -2.9589 -64.0039
## Training error : 0.023199
## Probability model included.
## Length Class Mode
## 1 ksvm S4
Head & Sumary of predicted discrtet and posterior distributions of Facies by KSVM:
## F1 F10 F2 F3 F5 F7
## [1,] 0.9420069 0.02415062 0.003600989 0.005542730 0.004820740 0.003950962
## [2,] 0.9443455 0.02085043 0.003723612 0.005667284 0.005295246 0.004194428
## [3,] 0.9449228 0.02166083 0.003521716 0.006261963 0.005010991 0.004124452
## [4,] 0.9558534 0.01745893 0.003095547 0.005042009 0.003129275 0.003651956
## [5,] 0.9450055 0.02139177 0.003595512 0.005447882 0.005113368 0.004249314
## [6,] 0.9440478 0.02071560 0.003708630 0.005822525 0.005868332 0.004373920
## F8 F9
## [1,] 0.01203424 0.003892810
## [2,] 0.01229356 0.003629921
## [3,] 0.01112826 0.003368938
## [4,] 0.00897607 0.002792779
## [5,] 0.01184974 0.003346937
## [6,] 0.01202087 0.003442304
## F1 F10 F2
## Min. :-0.01150 Min. :0.0004239 Min. :-0.007770
## 1st Qu.: 0.04911 1st Qu.:0.1223078 1st Qu.: 0.005372
## Median : 0.07354 Median :0.1495795 Median : 0.051580
## Mean : 0.19482 Mean :0.2949670 Mean : 0.049397
## 3rd Qu.: 0.12857 3rd Qu.:0.3071582 3rd Qu.: 0.061017
## Max. : 0.99326 Max. :0.9937074 Max. : 0.841170
## F3 F5 F7
## Min. :0.0002971 Min. :-0.015050 Min. :-0.017741
## 1st Qu.:0.0413950 1st Qu.: 0.005415 1st Qu.: 0.002282
## Median :0.0973518 Median : 0.083129 Median : 0.078393
## Mean :0.0866778 Mean : 0.062161 Mean : 0.057837
## 3rd Qu.:0.1075710 3rd Qu.: 0.094976 3rd Qu.: 0.096656
## Max. :0.7819388 Max. : 0.186582 Max. : 0.129606
## F8 F9
## Min. :-0.016184 Min. :-0.015594
## 1st Qu.: 0.004653 1st Qu.: 0.003252
## Median : 0.161129 Median : 0.056299
## Mean : 0.171845 Mean : 0.082296
## 3rd Qu.: 0.278095 3rd Qu.: 0.137680
## Max. : 0.900641 Max. : 0.294194
## [1] F1 F1 F1 F1 F1 F1
## Levels: F1 F10 F2 F3 F5 F7 F8 F9
## F1 F10 F2 F3 F5 F7 F8 F9
## 111 178 8 47 109 9 183 174
Means of the Well logs and core data given each Facies:
KSVM Modeling Validation by computing the total correct percent.
## qq
## F1 F10 F2 F3 F5 F7 F8 F9
## F1 111 0 0 0 0 0 0 0
## F10 0 166 0 4 1 0 0 0
## F2 0 0 8 0 0 0 0 0
## F3 0 12 0 43 0 0 0 0
## F5 0 0 0 0 108 0 0 1
## F7 0 0 0 0 0 9 0 0
## F8 0 0 0 0 0 0 183 1
## F9 0 0 0 0 0 0 0 172
## F1 F10 F2 F3 F5 F7 F8
## 1.0000000 0.9325843 1.0000000 0.9148936 0.9908257 1.0000000 1.0000000
## F9
## 0.9885057
Total percent correct that reflects the KSVM accuracy of classification:
## [1] 0.976801
Scatteratrix plot of Lithofacies Classification by KSVM:
Visualizing the predicted posterior distribution of the Eight Facies.
Combining the posterior distribution of the eight Lithofacies in one plot.
## Warning in bxp(structure(list(stats = structure(c(5667, 5680.75, 5694.5, :
## some notches went outside hinges ('box'): maybe set notch=FALSE
## Warning in bxp(structure(list(stats = structure(c(5667, 5680.75, 5694.5, :
## some notches went outside hinges ('box'): maybe set notch=FALSE
References
Cristianini, N., and Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge university press.
Al-Mudhafar, W. J. (2015). Integrating Component Analysis & Classification Techniques for Comparative Prediction of Continuous & Discrete Lithofacies Distributions. Offshore Technology Conference. doi:10.4043/25806-MS.
Karpur, L., L. Lake, and K. Sepehrnoori. (2000). Probability Logs for Facies Classification. In Situ 24(1): 57.
Al-Mudhafer, W. J. (2014). Multinomial Logistic Regression for Bayesian Estimation of Vertical Facies Modeling in Heterogeneous Sandstone Reservoirs. Offshore Technology Conference. doi:10.4043/24732-MS.
Al-Mudhafar, W. J. (2015). Applied Geostatistics in R: 1. Naive Bayes Classifier for Lithofacies Modeling in a Sandstone Formation. RPubs.
Al-Mudhafar, W. J. (2015). Applied Geostatistics in R: 2. Applied Geostatistics in R: 2. Logistic Boosting Regression (LogitBoost) for Multinomial Lithofacies Classification in a Sandstone Formation. RPubs.
Al-Mudhafar, W. J. (2015). Applied Geostatistics in R: 3. Linear Discriminant Analysis (LDA) for Multinomial Lithofacies Classification in a Sandstone Formation. RPubs.
Al-Mudhafar, W. J. (2015). Applied Geostatistics in R: 4. Applied Geostatistics in R: 4. Multinomial Logistic Regression (MLR) for Posterior Lithofacies Probability Prediction in a Sandstone Formation. RPubs.
Al-Mudhafar, W. J. (2015). Applied Geostatistics in R: 5. Improved Reservoir Characterization through Facies Tree-Based Classification Models. RPubs.