Summary:
23th categories define lithologies (1 to 7)
24th categories define one or two peaks (0 or 1)
25th categories define small or big miu (-1 0 or 1)
26th categories define small peaks (0 or 1)
27th categories define big deviations (0 or 1)
The following is the T2 comparison of 2667 depths with all 11 lithologies. The accuracy is not good.
The following is the T2 comparison of 416 depths with middle 7 lithologies. The accuracy is good.
The median value of R2 is 0.71 (last week it is 0.65 with 25 inputs.).
The I use k-nearest neighbor method to predict these catogories with 23 input data.
24th categories testing data (20%) is 86% correctly predicted.
25th categories testing data (20%) is 83% correctly predicted.
26th categories testing data (20%) is 80% correctly predicted.
27th categories testing data (20%) is 86% correctly predicted.
The following is 416 depths T2 comparison with 64 bins predicted by 27 input data. The accuracy is good.
The median value of R2 is 0.77.
RMSE:
R2:
Tomorrow, I will continue to improve the prediction of categories and try to conbine the results of 64 bins prediction and 6 parameter prediction.
Are Test and Train Data completely separated?
ReplyDeleteAre Train data 80% and Test Data 20% split?
Generate absolute prediction error distribution for each depth as a frequency vs error? The unit of absolute error is Pore Volumes?
Generate relative prediction error distribution (i.e. absolute error divided by total pore volume from NMR) for all the depths as relative error vs frequency? Unit of rel error is fraction.
1. Are Test and Train Data completely separated?
2. Are Train data 80% and Test Data 20% split?
3. Generate absolute prediction error distribution for each depth as a frequency vs error? The unit of absolute error is Pore Volumes?
4. Generate relative prediction error distribution (i.e. absolute error divided by total pore volume from NMR) for all the depths as relative error vs frequency? Unit of rel error is fraction.
5. Add INSET figure of Actual NMR and Predicted NMR for R=-2 R=0 and R=0.5. and R=1 so the reader understands what it means...
ReplyDelete6. are people using categories, is there a technical term for the qualitative flags/categories that you are creating?
ReplyDeleteCombine 64 bins and 6 parameters to improve your overall results.
ReplyDeleteThank you for your patience.
DeleteOk, so now there are 3 things to do:
ReplyDelete1. PLot RMSE Distirbution and RMSRE distribution
2. try to find a technical term for the categories dividing way
3. Combine 64 bins and 6 parameters to improve your overall results.