7/12/2017

Use magnitude and phase to improve the result

Today, I read some papers and decide to use magnitude and phase again.

Summary:

There are some papers which predict magnitude and phase of one value like permittivity. So I think it may be helpful. After applying this method into abernathy data, the accuracy of prediction improves a lot.

The first is the prediction result for magnitude. R2 of testing data are 0.93, 0.91, 0.88, 0.77.


The second is the prediction result for phase. R2 of the testing data are 0.85, 0.94, 0.91, 0.88.

 I think the accuracy now is enough for publication.

Tomorrow, I will continue to read papers if you can give me some time.


Posted by at

6 comments:

  1. siddharth misraThursday, July 13, 2017 at 11:30:00 AM CDT

    then try understanding the effect of various data on dielectric prediction..
    which logs strongly govern the prediction ...

    ReplyDelete
  2. siddharth misraThursday, July 13, 2017 at 11:31:00 AM CDT

    and after that bring in NMR bins to improve the prediction further

    ReplyDelete
  3. siddharth misraThursday, July 13, 2017 at 11:31:00 AM CDT

    add these two points to your pending tasks

    ReplyDelete
  4. siddharth misraThursday, July 13, 2017 at 11:31:00 AM CDT

    you have still not resolved the issue of how to utilize the fact that conductivity and perm have empirical relationships that connect them... you need to bring that in your analysis

    ReplyDelete
  5. siddharth misraThursday, July 13, 2017 at 11:47:00 AM CDT

    Your NN should be inspired by the Physics

    ReplyDelete

Subscribe to: Post Comments (Atom)