Predicting openhole minislam logs from casedhole pulsed neutron capture logs using neural networks

1
Predicting open-hole mini-slam logs from
cased-hole pulsed neutron capture logs using
neural networks

• Dong (Cynthia) Xue
• August 10th
• Baker Hughes Houston Technology Center

2
Acknowledgements

• Sheng fang, Dan Georgi
• Allen Gilchrist, Pingjun Guo
• Darryl Trcka, Freddy Mendez, M.Milan, S.Mathur
• Tsili Wang, Weidong Li.
• Many thanks to all of those I haven't named

3
Outline

• Introduction
• Motivation
• Background
• Data selecting and preprocessing
• Selection of PNC Curves
• Removal of Outliers
• Optimization of neural network
• Improvement of Generalization
• Selection of the Training, Validation and Test
  Samples
• Selection of the Neurons
• Results
• Data from Thailand
• Data from Colorado

4
Motivation

• The result of using coil tubing as production
  casing
• Unavailable Mini-slam data in open holes
• Neutron porosity
• Resistivity
• Density porosity
• Available pulsed neutron data in cased hole
• Neural network as a prediction tool
• Strengths, assumptions, and limitations of a
  neural-network approach
• Accuracy and variability of prediction results

5
Neural Network

• Biases, a sigmoid layer, and a linear output
  layer are capable of approximating any function.
• Overcome overfitting by improving generalization
• Regularization.
• Early stopping.
• Conjugate gradient, Quasi-Newton, and
  Levenberg_Marquardt
• LM fastest convergence
• Bayesian regularization (BR) better
  generalization

6
Prior Work

• R.C.Odom - 2000
• Predicted neutron porosity and density parameters
  
• Used a Multi-Layer network
• M.Mullen - 2001
• Predicted open hole triple combo data.
• Used a commercial neural network software
  package.
• J.Quirein - 2003
• A good assessment of neutron porosity and density
  porosity.
• Unavailable to accurately predict deep
  resistivity
• Non-linearity of the predictions due to the coals
  and depth misalignment

7
Pulsed Neutron Capture (PNC)

• Logging measurement from the Reservoir
  Performance Monitor (RPM).
• Generator, SS, LS, XLS
• Time decay spectra for SS and LS detector
• Inelastic energy
• Capture energy
• Count rates or ratios

8
Input PNC curves and targets

• Input logs PNC curves
• 1.      GR gamma ray ,
• 2.      CSS capture gamma ray count rate
  from short space(ss) detector,
• 3.      CLS capture gamma ray count rate
  from long space(ls) detector,
• 4.      SGFC corrected formation sigma,
• 5.      RONE ss to ls capture gamma ray
  ratio. RONE CSS/CLS,
• 6.      RIN ss to ls inelastic gamma ray
  ratio. RIN ISS/ILS,
• 7.      SGB1 dual exponential borehole
  sigma from ss.
• Output logs the mini-slam data
• ILDI deep induction resistivity,
• NPHIOHI neutron porosity,
• RHOBI density.

9
Correlation between logs

• Relate open hole data to case hole data from
  deterministic method
• A comparison of
• cased hole and open
• hole cross plots

10
Correlation of open-hole resisitivity with
cased-hole logs

• Single measurements (GRI -- Best Single Input
  Measurement)

2. Double measurements (SGFC)
3.Three measurements7. All the seven
measurements
11
The stepwise regression of cased hole inputs for
both training and application wells
12
The uplift Effect

• Best single input measurement v.s. All seven
  measurements

13
Removal of Outliers

• Polynomial approximation a discontinuous
  function
• Removal of discontinuity
• Outliner removal,
• Additional measurements adoption.

14
Selection of data samples

• Data samples Training, Validation and Test
• Guard against using too small a percentage of
  samples for training.

15
Selection of the neurons

• The number of neurons in hidden layers.
• Too few neurons - Underfitting
• Too many neurons - Overfitting
• BR always has less variation
• Less neutron is generally best.

16
Results One Well from Thailand

• The top half well is Training well for
  resistivity

ILDI
CLS
SGFC
GR
ILDI
CLS
SGFC
GR
17
The bottom half well is application well for
resistivity
ILDI
CLS
SGFC
GR
ILDI
CLS
SGFC
GR
18
Optimization of training (1)
19
Optimization of training(2)

• First half training
• Second half application

• Every other 100 ft for training the rest for
  application.

20
Two offset wells
21
Conclusions and future work

• Neural network predictions are feasible.
• Problems
• Near-far ratio is sensitive to the presence of
  gas.
• Difficult to characterize borehole and diffusion
  effects.
• Existing complicated geological environments.
• Solutions
• Establish a model predictability assessment
  system to compensate measurements
• Adopt RPM-C data instead of RPM-A.
• Include special environments as inputs .

22

• Thank you for coming

23
The training well for neutron porosity
24
The application well for neutron porosity
25
The training well for density
26
The application well for density
27
(No Transcript)
28
(No Transcript)