Data processing: measuring – calibrating – or testing – Measurement system in a specific environment – Earth science
Reexamination Certificate
1999-08-30
2001-05-22
McElheny, Jr., Donald E. (Department: 2862)
Data processing: measuring, calibrating, or testing
Measurement system in a specific environment
Earth science
C702S013000, C706S929000
Reexamination Certificate
active
06236942
ABSTRACT:
FIELD OF THE INVENTION
This invention relates to a system and method for delineating hydrocarbon accumulations. In particular, this invention is drawn to a method and system using a neural network for delineating spatially dependent objects such as hydrocarbon accumulations from seismic data.
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to a system, method, and process for delineating objects in one (1), two (2), or three (3) dimensional space from data that contains patterns related to the existence of said objects. For example, seismic data frequently contains patterns from which hydrocarbon accumulations can be detected through the identification of bright spots, flat spots, and dim spots. In the past, when neural networks have been used for similar purposes other than the detection of hydrocarbon accumulations, it has been necessary to define training sets consisting of data from areas where it is known that certain conditions exist and do not exist. In the case of hydrocarbon accumulations and prior to the disclosures of the present invention, this would have required expensive drilling of oil and gas wells before the data for the training sets could have been acquired. In the method disclosed in the present invention, it is not necessary to use explicitly known training sets to outline the various spatially dependent objects such as hydrocarbon accumulations. By the method disclosed in the present invention, it is possible to automate the interpretation process and quickly provide important information on hydrocarbon accumulations even before drilling commences.
Automated delineation of hydrocarbon accumulations from seismic data will be used as a non-exclusive, actual example to describe the system, method, and process of the present invention. However, the method disclosed is also applicable to a wide range of applications other than hydrocarbon accumulations, such as but not limited to, aeromagnetic profiles, astronomical clusters from radio-telescope data, weather clusters from radiometers, objects from radar, sonar, and infrared returns, etc. Many other applications will be obvious to those skilled in the pertinent art. Accordingly, it is intended by the appended claims to cover all such applications as fall within the true spirit and scope of the present invention.
2. Description of the Prior Art
Many organizations, whether commercial or governmental, have a need to recognize objects from patterns in the data acquired from some sensing process. Spatial delineation of objects is often the first step toward the identification of these objects. Neural networks have been used for this type of delineation and identification in the past. However, prior to the present invention, the neural network approach has generally required that known data be used to form training sets that are used as input to the neural network process. However, acquisition of the known data is often a long and expensive process.
For example, in the oil and gas industry, it is common that seismic data be initially subjected to an interpretation process that is labor intensive. Furthermore, this interpretation is carried out by highly skilled and; therefore, expensive personnel who are limited in the amount of data that they can physically process in a fixed period of time. Even though the interpreters are generally highly skilled and experienced, they are still only able to render subjective judgements as to where hydrocarbon accumulations might exist. Having a clear and accurate areal or spatial delineation of possible hydrocarbon accumulations, i.e. reservoirs, before the interpretation process begins, will greatly improve the accuracy and quality of the interpretation; thereby, reducing the risk in drilling. Drilling of oil and gas wells commonly runs into millions of dollars for each well; and wellbore data, i.e. known data, is not available until this drilling has taken place.
U.S. Pat. No. 5,884,295, which discloses a “System For Neural Network Interpretation of Aeromagnetic Data”, is assigned to Texaco, Inc., one of the world's major oil companies. This patent discloses “a system for processing Aeromagnetic survey data to determine depth to basement rock;” and although it does not pertain to the method of the present invention, it is interesting in that it points out “the high cost of drilling deep exploratory well holes and collecting reflection seismic data.”
U.S. Pat. No. 5,444,619 (incorporated herein by reference) is assigned to Schlumberger Technology, a leading seismic processing organization. In this patent, the inventors state that “Seismic data are routinely and effectively used to estimate the structure of reservoir bodies but often play no role in the essential task of estimating the spatial distribution of reservoir properties. Reservoir property mapping is usually based solely on wellbore data, even when high resolution 3D seismic data are available.” The Schulumberger patent provides a means for extrapolation of wellbore data throughout a field based on seismic data; however, it does not provide a means for the spatial delineation of reservoir properties, such as the gas cap, permeability zones, porosity zones, etc., prior to the acquisition of wellbore data.
The method of the present invention provides a process of spatially delineating accumulations of various types and properties. For example, it provides an automated process for delineating hydrocarbon accumulations from seismic data. One particular hydrocarbon accumulation is the gas below the cap, i.e. gas cap, in an oil and/or gas field. Being able to accurately delineate the gas cap, from 2D and 3D seismic data, before the interpretation process even begins, will prove to be very valuable to the oil and gas industry. See, for example, U.S. Pat. Nos. 4,279,307, 3,788,398, 4,183,405, and 4,327,805 which all rely on knowledge of the gas cap in their various methods and processes for enhancing hydrocarbon recovery. Accurate delineation of the gas cap, from seismic data, is a long felt and important need in the oil and gas industry.
Numerous U.S. patents have been issued on the topics of machine vision, image contour recognition, visual recognition, pattern recognition, image edge sensing, object recognition, object tracking, image edge extraction, etc. See, for example, U.S. Pat. Nos. 5,103,488, 5,111,516, 5,313,558, 5,351,309, 5,434,927, 5,459,587, 5,613,039, 5,740,274, 5,754,709, and 5,761,326 that deal with subjects tangentially related to the present invention. Even though the cited patents may in some cases provide superior methods, to that of the present invention, for dealing with each of their particular subjects; these patents indicate the potentially wide range of usage for the novelty included in the present invention and indicate the importance of the disclosure of the present invention. Furthermore, those skilled in the pertinent arts will find a wide range of application for the present invention. It is, therefore, intended by the appended claims to cover all such applications that fall within the true spirit and scope of the present invention. In addition to the patents cited above, a number of specific examples where the present invention might find usage have also been addressed in U.S. patents.
In U.S. Pat. No. 5,214,744, the inventors describe a method for automatically identifying targets in sonar images where they point out that “the noisy nature of sonar images precludes the use of line and edge detection operators.” Seismic data is also generally recognized as being highly noisy. However, the present invention has been proven to provide a process for accurately delineating hydrocarbon accumulations directly from seismic data. Therefore, it might be expected that, at least in some cases, the present invention might provide another and possibly better process for accomplishing the task described in the sonar patent cited at the start of this paragraph.
U.S. Pat. No. 5,732,697 discloses a “Shift-Invariant Artificial Neural Network for Computerized Detection o
Davis & Johnson, LLP
McElheny Jr. Donald E.
Scientific Prediction Incorporated
LandOfFree
System and method for delineating spatially dependent... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for delineating spatially dependent..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for delineating spatially dependent... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2468353