Summary:
There are 13 inputs and 2 outputs (compressional and shear).
one hidden layer with 8 neurons
R2: 0.8570, 0.8184
NRMSE: 0.0631, 0.0673
two hidden layers with 9 and 5 neurons
R2: 0.8619, 0.8247
NRMSE: 0.0620, 0.0661
Asoodeh et al. (2011) improved accuracy using CMIS compared with ANN. But it is just 0.16% for compressional velocity and 0.63% for shear velocity with R2.
In our case, the accuracy is also improved by adding one more hidden layers. It is 0.57% for compressional velocity and 0.77% for shear velocity with R2.
The result shows that both of two methods improve little in accuracy and there is no need to use CMIS. Adding one more hidden layer is more efficient.
Tomorrow, I will search papers to see if I can find new methods.
show me the flowchart of prediction... also share the empirical/physical models for compressional and shear waves...
ReplyDeleteI just predict them together today.
Deleteempirical/physical models are just empirical equations, I will show them after I finish the ANN part.
provide the entire list of inputs
ReplyDeleteGR, DCAL, DPHZ, NPOR, PEFZ, RHOZ, Resistivity laterolog 0-5
Deletehow does your trained and tested model work when you take it from one well and apply the frozen model to another well in prediction mode (without performing testing and training in the other well)
ReplyDeleteI have not tried it.
Deletegive me all the ways your model is superior to others.....we need to demonstrate the innovations and new ideas included in the predictive method....
ReplyDeleteFor now, my model is not superior to others, please give me a few days to look for papers on it.
DeleteVp/vs is independent of density.... how can you include vp/vs into the model to improve the predictins?
ReplyDelete