[OpendTect_Users] Neural Network Fault Cube Questions

[Paul de Groot]

Hello Nicola,

*1) In order to run NNFC you need to provide a steering cube. Which is the
one to use between background and detailed? Which are the parameters
suggested for calculating such steering cube?*

Typically we use background steering cubes as inputs for dip-steered
filters and detailed steering cubes when we want to preserve details in
attribute calculations. More information on steering cubes and parameters
can be found in this webinar on the subject:
http://www.opendtect.org/tutorials/Webinar_Optimal_Steering .

*2) I noticed that my NNFC fails in areas of very steep reflectors - even
if these areas are not faulted at all, my NNFC reports very high fault
probability there. Is there any attribute I can add/remove/change to the
process in order to address this problem?*

You could try including picks of "non-faults" in steeply dipping areas and
see if the NN can learn to distinguish these picks from picks at real
faults. If "polar dip" is not in your attribute set yet, I recommend
including that.

*3) While my NNFC seems to perform well with relatively large fault (length
> 300ms), it fails in picking "small" faults (length ≤ 100ms) e.g.
polygonal faults. Is this behaviour expected? Is there any recommendation
for detecting "small" faults?*

Yes, this is expected behavior. NN Fault Cubes are good for large faults
but not so good for picking up small faults. In general a NNFC shows better
continuity of large scale faults than single attributes but single
attributes are better for small scale faults. To pick up polygonal faults I
recommend applying a Fault Enhancement Filter (combination filter of
dip-steered median and dip-steered diffusion, see default attributes) and
then compute similarity with a small time-gate on the fault enhanced cube.

Best regards,

Paul.

*-- *
*Paul de Groot*
*President *
*dGB Earth Sciences, Nijverheidstraat 11-2, 7511 JM Enschede, The
Netherlands.*
*Tel. +31 53 43 15 155, Fax +31 53 43 15 104.*
*paul.degroot at dgbes.com, www.dgbes.com, www.opendtect.org.*

On Fri, Apr 20, 2012 at 10:33 AM, Nicola Scarselli <
n.scarselli at es.rhul.ac.uk> wrote:

>
> Dear ODT Users,
> I have few questions/comments regarding the Neural Network Fault Cube
> (NNFC) I'm testing at the moment:
>
> 1) In order to run NNFC you need to provide a steering cube. Which is the
> one to use between background and detailed? Which are the parameters
> suggested for calculating such steering cube?
>
> 2) I noticed that my NNFC fails in areas of very steep reflectors - even
> if these areas are not faulted at all, my NNFC reports very high fault
> probability there. Is there any attribute I can add/remove/change to the
> process in order to address this problem?
>
> 3) While my NNFC seems to perform well with relatively large fault (length
> > 300ms), it fails in picking "small" faults (length ≤ 100ms) e.g.
> polygonal faults. Is this behaviour expected? Is there any recommendation
> for detecting "small" faults?
>
> Many thanks,
> Nicola
>
> PS Is there any plan for a NNFC webinar?
>
> -----
> Nicola Scarselli
> Postgraduate Researcher
> Fault Dynamics Research Group
> http://fdrg.rhul.ac.uk/
> Star Group
> Room 262
>
> Department of Earth Sciences
> Royal Holloway University of London
> Egham, Surrey
> TW20 0EX
> United Kingdom
>
> Tel: +44 (0) 1784 44 3597
>
>
>
>
> _______________________________________________
> Users mailing list
> Users at opendtect.org
> http://www.opendtect.org/mailman/listinfo/users
>
> You receive this mail because you are listed on users at opendtect.org To
> unsubscribe please go to http://lists.opendtect.org/mailman/options/users. If you encounter any problems, please contact
> support at opendtect.org .
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.opendtect.org/pipermail/users/attachments/20120422/ae4858e2/attachment.html>