Summary:
1.
I validate that BR and SCG is equally effective to predict geomechanical data, which are better than LM. So, if we write the paper, we can include them as one of our sections.
I validate that BR and SCG is equally effective to predict geomechanical data, which are better than LM. So, if we write the paper, we can include them as one of our sections.
2.
You mentioned that I can try to predict Vp first and Vs next. I did and I found that prediction accuracy did not improve.
As I mentioned before, accuracy of the ANN model without deleting outliers is 0.8611 and 0.8252 in terms of R2 and 0.0622 and 0.0660 in terms of NRMSE.
However, when I predict Vp in the first model and predict Vs in the second model, accuracy of ANN models without deleting outliers is 0.8500, 0.8178 in terms of R2 and 0.0710 and 0.0733 in terms of NRMSE.
Tomorrow, I will think about other ways to improve the accuracy.
You mentioned that I can try to predict Vp first and Vs next. I did and I found that prediction accuracy did not improve.
As I mentioned before, accuracy of the ANN model without deleting outliers is 0.8611 and 0.8252 in terms of R2 and 0.0622 and 0.0660 in terms of NRMSE.
However, when I predict Vp in the first model and predict Vs in the second model, accuracy of ANN models without deleting outliers is 0.8500, 0.8178 in terms of R2 and 0.0710 and 0.0733 in terms of NRMSE.
Tomorrow, I will think about other ways to improve the accuracy.
why is this observation??? what is the reason...
ReplyDelete"accuracy of the ANN model without deleting outliers is 0.8611 and 0.8252 in terms of R2 and 0.0622 and 0.0660 in terms of NRMSE.
However, when I predict Vp in the first model and predict Vs in the second model, accuracy of ANN models without deleting outliers is 0.8500, 0.8178 in terms of R2 and 0.0710 and 0.0733 in terms of NRMSE."
I think the difference between dielectric dispersion and geomechanical log is the number of prediction and accuracy gap. There are 8 outputs of dielectric dispersion while only two outputs of geomechanical log. So it may be more necessary to predict them together. In addition, accuracy of predicting permittivity dispersion is much lower than that of conductivity dispersion while accuracy of Vp and Vs is close to each other. It maybe another reason why there is no improvement of geomechanical log prediction accuracy when predicting them seperately.
ReplyDelete