Neural net prediction of seismic streamer shape

Details Neural net prediction of seismic streamer shape Neural net prediction of seismic streamer shape

2002-06-28

2004-08-10

McElheny, Jr., Donald (Department: 2857)

Data processing: measuring, calibrating, or testing

Measurement system in a specific environment

Earth science

Reexamination Certificate

active

06775619

ABSTRACT:

BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to a system and method for the generation of a predicted cable shape during seismic data acquisition. In particular the invention provides a neural network trained to predict the shape of a seismic streamer or receiver cable during sea borne, vessel-towed, seismic data collection operations.
2. Description of the Related Art
Cable shape and motion associated with sea borne towing is an important factor in determining the optimal path of a seismic vessel and its associated streamer of receivers during seismic data acquisition operations. In seismic data acquisition surveys, much of the subsurface terrain is improperly sampled or completely missed due to cable feathering or displacement. Accurate prediction of the receiver cable shape is important to anticipate and compensate for the feathering or displacement of the seismic cable during seismic data acquisition. The more accurately a survey path can be selected and executed, the more optimal and efficient the survey path becomes.
There are an infinite number of possible paths that the seismic towing vessel may traverse during the initial and secondary or in fill portions of a seismic survey. Moreover, in many cases, the optimal traversal path can be difficult to determine. If optimal initial and in fill paths can be identified, however, it significantly lowers the total effort and expense associated with seismic data collection. Thus, there is a need for an efficient means of determining the cable shape to attain optimal paths in seismic surveying.
Targets missed on an initial pass have to be re-shot on secondary passes. Each additional pass increases the cost of the survey. Such secondary passes significantly increase the time associated cost to complete a survey. Typical operating costs of a seismic vessel exceed $50,000 per day. Thus, predicting cable shape to attain an optimal path would result in an enormous cost savings for surveying each seismic prospect. These large cost reductions would provide a competitive advantage in the marine data collection market. Thus, cable shape prediction is important in sampling the survey target area during initial and secondary passes. There is a long-felt need in the art for predicting the shape of the seismic streamer during seismic data acquisition operations.
SUMMARY OF THE INVENTION
The above-mentioned long-felt need has been met in accordance with the present invention with a neural network to predict seismic streamer shape during seismic operations. In accordance with a preferred embodiment of the present invention, a system for predicting cable shape is provided comprising a neural network having an input layer, an optional hidden layer, and an output layer, each layer having one or more nodes. The first layer comprises input nodes attached to seismic data acquisition operational parameters as follows: vessel coordinates, receiver coordinates, time, vessel velocity, current velocity, wind velocity, water temperature, salinity, tidal information, water depth, streamer density, and streamer dimensions. Each node in the input layer is connected to each node in the hidden layer and each node in the hidden layer is connected to each node in the output layer, the output layer outputting a predicted cable shape. The hidden layer may be omitted. When the hidden lay is omitted, each node in the input layer is attached to each node in the output layer.
Each connection between nodes has an associated weight and a training process for determining the weights for each of the connections of the neural network. The trained neural network is responsive to the inputs and outputs to generate a predicted cable shape. The training process applies a plurality of training sets to the neural network. Each training set comprises a set of inputs and a desired cable shape. With each training data set, the training process determines the difference between the cable shape predicted by the neural network and the desired or known cable shape. The training process then adjusts the weights of the neural network nodes based on the difference between the output predicted cable shape and the desired cable shape. The error assigned to each node in the neural network may be assigned by the training process via the use of back propagation or some other learning technique.


REFERENCES:
patent: 5461699 (1995-10-01), Arbabi et al.
patent: 6418378 (2002-07-01), Nyland
patent: 0 613 025 (1994-08-01), None
patent: WO 99/35460 (1999-07-01), None
“The Shape of a Marine Streamer in a Cross Current”, P. M. Krail & H. Brysk; Geophysics, vol. 54, No. 3, (Mar. 1989), pp. 302-308.
“Dynamic Control of ROBs Making Use of the Neural Network Concept”, Tadaski Ooi, Yuki Yoskida, Yoskiaki Takahashi &Hideki Kidouski; Proceedings of the Forth (1994) International Offshore and Polar Engineering Conference, Osaka, Japan, Apr. 10-15, 1994; pp. 374-381.

Affiliated with

Also associated with

Rating

Neural net prediction of seismic streamer shape does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural net prediction of seismic streamer shape, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural net prediction of seismic streamer shape will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3310315