DETAILED ACTION
This action is responsive to the claims filed on October 16, 2023. Claims 1-20 are under examination.
Claims 1-20 are rejected under 35 USC 101 as ineligible.
Claims 1-6, 8-13, and 15-20 are rejected under 35 USC 103 as unpatentable over Halsey and Nivlet.
Claims 7 and 14 are rejected under 35 USC 103 as unpatentable over Halsey, Nivlet, and Al-Farisi.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed subject matter is directed to an abstract idea without significantly more.
Independent Claims
Claim 15 (Statutory Category – Machine)
Step 2A – Prong 1: Judicial Exception Recited?
Yes, the claims recite mental processes, which are abstract ideas, as well as fundamental economic practices. The fundamental economic practices and/or commercial interactions, which are methods of organizing human activity, were addressed in the introduction paragraph of this section, and are applied to the method as a whole rather than to any particular element. That is, under the category of organizing human activity, the claimed recited operations are elements of an abstract idea. The mental process grouping will be applied element-by-element, in accordance with the eligibility tests of the MPEP.
Claim 15 recites:
generate a set of feature vectors to learn [minds], the set of feature vectors defined based on a distance between each of the observed data points and a set of randomly selected points in the reservoir volume; (Mental Process - Determining random points and vectors with distances between the random points and preloaded points is practically performable in the mind or with basic aids, such as, a pen, paper, and a calculator.)
generate a three-dimensional populated log by propagating well log values of the set of feature vectors across the reservoir volume; (Mental Process – Organizing data to be indexed for three dimensional model is practically performable in the mind or with basic aids, such as, a pen, paper, and a calculator.)
quantify uncertainty by applying the learned [mind] to generate a plurality of realizations including the three-dimensional populated log; (Mental Process – Organizing data to be indexed for three dimensional model is practically performable in the mind or with basic aids, such as, a pen, paper, and a calculator.)
change, by [mind], the set of randomly selected points, wherein each of the plurality of realizations is different and equally probable; and (Mental Process – Changing the random set of points (e.g., generating new random points) is practically performable in the mind or with basic aids, such as, a pen, paper, and a calculator.)
generate a plurality of static models comprising a random sample of three- dimensional populated log data of the plurality of realizations. (Mental Process –Modeling using random sampling is practically performable in the mind or with basic aids, such as, a pen, paper, and a calculator.)
Claim 15 recites mental processes, which are abstract ideas.
Claim 15 recites an abstract idea.
Step 2A – Prong 2: Integrated into a Practical Application?
No.
Additional limitations:
A system for developing a reservoir, the system comprising:
one or more processors; and
at least one non-transitory computer readable medium having stored therein instructions executed by the one or more processors to:
[…] static modeler […]
[…] neural networks […]
These are generic computing elements recited at a high level, which, under MPEP 2106.05(f), fail to integrate the abstract idea into a practical application.
receive static data at a static modeler, the static data including a set of observed data points in a reservoir volume along a well trajectory and well logs corresponding to the set of observed data points;
generate a three-dimensional populated log by propagating well log values of the set of feature vectors across the reservoir volume;
change, by the static modeler, the set of randomly selected points, wherein each of the plurality of realizations is different and equally probable
This is mere data gathering akin to the MPEP 2106.05(g) examples: “i. Performing clinical tests on individuals to obtain input for an equation” “v. Consulting and updating an activity log, Ultramercial,” “i. Limiting a database index to XML tags” “iii. Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display.” Accordingly, this is extra-solution activity and fails to integrate the abstract ideas into a practical application.
Also, the nature of the data and the context merely limit the abstract idea to a technological environment, which, under MPEP 2106.05(h), fail to integrate the abstract idea into a practical application.
Claim 15 fails to recite any additional limitations that integrate the abstract idea into a practical application.
Claim 15 is directed to the abstract idea.
Step 2B: Claim provides an Inventive Concept?
No.
Additional limitations:
A system for developing a reservoir, the system comprising:
one or more processors; and
at least one non-transitory computer readable medium having stored therein instructions executed by the one or more processors to:
[…] static modeler […]
[…] neural networks […]
These are generic computing elements recited at a high level, which, under MPEP 2106.05(f), fail to combine with the other elements of the claim to provide significantly more than the abstract idea that would confer an inventive concept.
receive static data at a static modeler, the static data including a set of observed data points in a reservoir volume along a well trajectory and well logs corresponding to the set of observed data points;
generate a three-dimensional populated log by propagating well log values of the set of feature vectors across the reservoir volume;
change, by the static modeler, the set of randomly selected points, wherein each of the plurality of realizations is different and equally probable
This is well-understood, routine, and conventional (WURC) activity akin to the MPEP 2106.05(d) examples: “iii. Electronic recordkeeping” “iv. Storing and retrieving information in memory” “v. Electronically scanning or extracting data from a physical document” “i. Determining the level of a biomarker in blood by any means “ “v. Analyzing DNA to provide sequence information or detect allelic variants” “vi. Arranging a hierarchy of groups, sorting information, eliminating less restrictive pricing information and determining the price.” Because this activity is WURC and insignificant extra-solution activity, under MPEP 2106.05(d) and 2106.05(g), the limitation fails to combine with the other elements of the claim to provide significantly more than the abstract idea that would confer an inventive concept.
Also, the nature of the data and the context merely limit the abstract idea to a technological environment, which, under MPEP 2106.05(h), fail to combine with the other elements of the claim to provide significantly more than the abstract idea that would confer an inventive concept.
The additional limitations fail to combine with the other elements of claim 1 to provide significantly more than the abstract idea that would confer an inventive concept.
Claims 1 is ineligible.
Claim 8 recites an implementation of (the implicit storage of) the information processing system with one or more processors of claim 15, and claim 1 recites the operations of claim 15, so claims 1 and 8 are ineligible for at least the same reasons as claim 15.
Dependent Claims
Dependent claims 2-7, 9-14, and 16-20 are also ineligible for at least the following reasons.
Claims 2, 9, and 16
clustering the reservoir volume into a plurality of clustered three-dimensional volumes using a [mind] alongside randomly selected three-dimensional log data from the plurality of realizations, wherein the static models include one of the clustered three- dimensional volumes.
Clustering data for use in a model is practically performable in the mind or with basic aids, such as, a pen, paper, and/or a calculator, so it is an evaluation, a mental process, an element of the abstract idea.
Should it be found otherwise, this is mere data gathering and WURC for at least the same reasons as the receiving step of the respective independent claim.
[…] learned model […]
This is a generic computing implementation recited at a high level, so this fails to confer eligibility under MPEP 2106.05(f).
Claims 2, 9, and 16 fail to recite any additional limitations that confer eligibility.
Claims 2, 9, and 16 are ineligible.
Claims 3, 10, and 17
wherein at least one of the static models includes one or more fault planes fitted to the plurality of clustered three-dimensional volumes.
Fitting fault plane data to multidimensional values for use in a model is practically performable in the mind or with basic aids, such as, a pen, paper, and/or a calculator, so it is an evaluation, a mental process, an element of the abstract idea.
Claims 3, 10, and 17 fail to recite any additional limitations that confer eligibility.
Claims 3, 10, and 17 are ineligible.
Claims 4, 11, and 18
wherein a reservoir graph is constructed from the static model with each of the one or more clusters represented as a vertex.
Constructing a graph from a model and clustered data represented as a vertex is practically performable in the mind or with basic aids, such as, a pen, paper, and/or a calculator, so it is an evaluation, a mental process, an element of the abstract idea.
Should it be found otherwise, this is mere data gathering and WURC for at least the same reasons as the receiving step of the respective independent claim.
Claims 4, 11, and 18 fail to recite any additional limitations that confer eligibility.
Claims 4, 11, and 18 are ineligible.
Claims 5, 12, and 19
wherein the reservoir graph is defined such that at least one of the clustered three-dimensional volumes has at least one of: at most one pressure observation point, only one well passing through the cluster, or a spatially continuous voxel set only.
Constructing a graph from a model and clustered data represented as a vertex, where the graph is defined such that at least one of the volumes includes specific data types is practically performable in the mind or with basic aids, such as, a pen, paper, and/or a calculator, so it is an evaluation, a mental process, an element of the abstract idea.
Should it be found otherwise, this is mere data gathering and WURC for at least the same reasons as the receiving step of the respective independent claim.
Claims 5, 12, and 19 fail to recite any additional limitations that confer eligibility.
Claims 5, 12, and 19 are ineligible.
Claims 6, 13, and 20
populating core data in the reservoir volume using a learned k-nearest neighbor algorithm alongside the three-dimensional populated log, wherein the static models include a three- dimensional volume of the core data, and wherein the core data includes at least one of porosity, permeability, or water saturation.
Determining where to place data in a volume using a k-nearest neighbor algorithm is practically performable in the mind or with basic aids, such as, a pen, paper, and/or a calculator, so it is an evaluation, a mental process, an element of the abstract idea.
Should it be found otherwise, this is mere data gathering and WURC for at least the same reasons as the receiving step of the respective independent claim.
Claims 6, 13, and 20 fail to recite any additional limitations that confer eligibility.
Claims 6, 13, and 20 are ineligible.
Claims 7 and 14
wherein the three-dimensional populated log data includes at least one of gamma ray, neutron porosity, bulk density, or resistivity.
Choosing what data to use for determining where to place data in a volume using a k-nearest neighbor algorithm is practically performable in the mind or with basic aids, such as, a pen, paper, and/or a calculator, so it is an evaluation, a mental process, an element of the abstract idea.
Should it be found otherwise, this is mere data gathering and WURC for at least the same reasons as the receiving step of the respective independent claim.
Claims 7 and 14 fail to recite any additional limitations that confer eligibility.
Claims 7 and 14 are ineligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-6, 8-13, and 15-20: Halsey and Nivlet
Claims 1-6, 8-13, and 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over US 2018/0188403 A1 to Halsey et al. (Halsey) in view of US 2008/0162093 A1 to Nivlet et al. (Nivlet).
Claims 1, 8, and 15
Regarding claim 15, Halsey teaches:
A system for developing a reservoir, the system comprising: one or more processors; and at least one non-transitory computer readable medium having stored therein instructions executed by the one or more processors to: (Halsey [0015] “a system for evaluating and performing a hydrocarbon operation for a subsurface region is described. The system may include a processor; an input device in communication with the processor and configured to receive input data associated with a subsurface region; memory in communication with the processor, the memory having a set of instructions. The set of instructions, when executed by the processor, are configured to: obtain a first data set associated with a subsurface region, wherein the two or more reservoir models are based on a first data set; create two or more reservoir models for a subsurface region from the first data set; obtain a second data set associated with a subsurface region and the two or more reservoir models; may obtain production data associated with a subsurface region; dispose the production data or at least a portion of the production data and/or the second data set or at least a portion of the second data set into a feature space; determine a region of interest within the feature space; evaluate the region of interest in the feature space; and determine whether to perform a hydrocarbon operation based on the evaluation of the region of interest.” – Developing a reservoir.)
receive static data at a static modeler, the static data including a set of observed data points in a reservoir volume along a well trajectory and well logs corresponding to the set of observed data points; (Halsey [0034]-[0036] “As used herein, the term “subsurface model” refers to a model of a subsurface region and may include a reservoir model, a geomechanical model, a watertight model, and/or a geologic model. The subsurface model may include subsurface data distributed within the model in two-dimensions (e.g., distributed into a plurality of cells, such as elements or blocks), three-dimensions (e.g., distributed into a plurality of voxels,), or four or more dimensions. As used herein, the term “geologic model” refers to a model (e.g., a two-dimensional model or a three dimensional model) of the subsurface region having static properties and includes objects, such as faults and/or horizons, and properties, such as facies, lithology, porosity, permeability, and/or the proportion of sand and shale. As used herein, the term “reservoir model” is a model (e.g., a two-dimensional model or a three-dimensional model) of the subsurface that in addition to static properties, such as porosity and/or permeability, also has dynamic properties that vary over the timescale of resource extraction, such as fluid composition, pressure, and/or relative permeability.” – The models include static models. [0014] “For example, the method may include performing one or more regression techniques to evaluate the metric or metrics in the region of interest; wherein the first data set comprises one of seismic data, well test data, well log data and any combination thereof; wherein the second data set comprises one of generated or observed seismic data, generated or observed well test data, generated or observed well log data, generated or observed production data and any combination thereof” – Observed data points in a reservoir volume along a well trajectory and well logs.)
generate a set of feature vectors to learn neural networks, the set of feature vectors defined based on a distance ; (Halsey [0099] “machine learning algorithms for classification (such as the neural networks” [0038] “a subsurface model is created in the physical space or domain to represent the subsurface region. […] The subsurface model may include multiple dimensions. […] A cell, such as block, mesh element or voxel, is a subvolume of the space, which may be constructed from nodes within the mesh.” [0039] “[…] one or more subsurface models are created, which are conditioned to seismic data, well logs, well test data, and any other available data to determine the underlying geological and statistical concepts for the subsurface region. Accordingly, the subsurface models may be used to determine the fluid flow within the reservoir and from the respective production wells.” [0044] “The spatial relationship may be the forming of a region or area that is associated with the results within a distance threshold in the space of the measured or observed production data (e.g., actually observed production data). In the feature space, machine learning classification or regression techniques (e.g., k-means clustering, support vector models, or Kriging) may then be used to establish the preferred decision for a given set of data.” [0048] “ Feature space creation is commonly practiced in machine learning applications, and may follow standard supervised or unsupervised machine learning practices.” [0066] “a feature space is used with regression techniques to evaluate the hydrocarbon operation, as shown in blocks 212 to 218. The regression techniques may include estimate of the model form error or bias along with estimate of measurement noise. At block 212, a feature space is determined. As noted above, the feature space may be a higher dimensional space or may be a lower dimensional space with respect to some reference, e.g. that created by raw, unfit or unapproximated data alone. The feature space may be used to highlight differences and to assist in evaluating the metric and/or hydrocarbon operations.” – A set of feature vectors are generated to learn neural networks, the set of feature vectors defined based on a distance/distance threshold.)
generate a three-dimensional populated log by propagating well log values of the set of feature vectors across the reservoir volume; (Halsey [0016] “wherein the first data set comprises one of seismic data, well test data, well log data and any combination thereof; wherein the second data set comprises one of generated or observed seismic data, generated or observed well log data, generated or observed well test data, generated or observed production data and any combination thereof” [0078] “By way of example, FIG. 3B is an exemplary diagram 320, that shows the permeability K.sub.x of a sample realization of the subsurface region, which contains various wellbores that are configured to operate as producers or injectors. This sample realization is a part of an ensemble of 285 reservoir models, which are generated by conditioning the reservoir models to pre-production data. The ensemble of realizations represents uncertainty in the earth parameters, such as the porosity, the proximal/distal/medial grain size, the net-to-gross ratio (NTG) and the stacking pattern. – Realizations, which each include a three-dimensional populated log generated by propagating well log values of the set of feature vectors across the reservoir volume.)
quantify uncertainty by applying the learned neural networks to generate a plurality of realizations including the three-dimensional populated log; (Halsey [0078] “By way of example, FIG. 3B is an exemplary diagram 320, that shows the permeability K.sub.x of a sample realization of the subsurface region, which contains various wellbores that are configured to operate as producers or injectors. This sample realization is a part of an ensemble of 285 reservoir models, which are generated by conditioning the reservoir models to pre-production data. The ensemble of realizations represents uncertainty in the earth parameters, such as the porosity, the proximal/distal/medial grain size, the net-to-gross ratio (NTG) and the stacking pattern. – Uncertainty is quantified by the generation of a plurality of realizations.
and
generate a plurality of static models comprising a random sample of three-dimensional populated log data of the plurality of realizations. (Halsey [0034]-[0036] “As used herein, the term “subsurface model” refers to a model of a subsurface region and may include a reservoir model, a geomechanical model, a watertight model, and/or a geologic model. The subsurface model may include subsurface data distributed within the model in two-dimensions (e.g., distributed into a plurality of cells, such as elements or blocks), three-dimensions (e.g., distributed into a plurality of voxels,), or four or more dimensions. As used herein, the term “geologic model” refers to a model (e.g., a two-dimensional model or a three dimensional model) of the subsurface region having static properties and includes objects, such as faults and/or horizons, and properties, such as facies, lithology, porosity, permeability, and/or the proportion of sand and shale. As used herein, the term “reservoir model” is a model (e.g., a two-dimensional model or a three-dimensional model) of the subsurface that in addition to static properties, such as porosity and/or permeability, also has dynamic properties that vary over the timescale of resource extraction, such as fluid composition, pressure, and/or relative permeability.” [0078] “This sample realization is a part of an ensemble of 285 reservoir models, which are generated by conditioning the reservoir models to pre-production data. The ensemble of realizations represents uncertainty in the earth parameters, such as the porosity, the proximal/distal/medial grain size, the net-to-gross ratio (NTG) and the stacking pattern. FIG. 3E is an exemplary diagram 346 of the ensemble of the 285 models, which represent different clusters associated with different scenarios. These clusters are shown along a quality of interest (QoI) axis and a history axis (d.sub.H).” [0094] “The training set (shown in equation e8 below) contains 255 randomly selected realizations from the ensemble.” – Static property models are generated based on a random sampling of realizations.)
Halsey does not appear to explicitly teach, but Halsey in view of Nivlet teaches:
generate a set of feature vectors to learn neural networks, the set of feature vectors defined based on a distance between at least one of the observed data points and a set of randomly selected points in the reservoir volume; […] change, by the static modeler, the set of randomly selected points, wherein each of the plurality of realizations is different and equally probable; (Nivlet [0011]-[0013] “These techniques reproduce a model of spatial variability of these properties (variogram) and thus provide realistic subsoil images as regards this variability; These techniques can integrate indirect information on the geology so as to better estimate the lateral variations of heterogeneities, by dealing if necessary with the problem of making (direct and indirect) information whose measuring support and resolution can be very different compatible; and These techniques can provide many equally probable realizations of the underground formation studied and therefore allow to estimate the uncertainties linked with modelling.” [0098]-[0100] “These techniques are based on Monte-Carlo or Markov Chain type simulations. The following document is referenced, whose method is based on purely geostatistical simulations, which allows accounting for the spatial variability of the data: Joseph, C., F. Fournier, and Vernassa S., 1999, Pseudowell Methodology: A Guiding Tool for Lithoseismic Interpretation: 69th Annual International Meeting, SEG, Expanded Abstracts, 938-941. The latter method allows generation of equally probable realizations of well data of high vertical resolution such as, for example, lithologic facies columns and the impedances of P and S waves. These realizations will be referred to as pseudologs hereafter, all of the pseudologs corresponding to a realization called pseudo-well. Pseudologs thus are simulated logs described as a function of depth.” [0109] “Simulation is performed sequentially, that is the lithologies assigned to the various depths z are simulated by as many successive random selections by lots according to the following procedure: [0110] random selection by lot of a depth z to be simulated in the lithologic column, [0111] kriging of each indicatrix I.sub.i(z) at depth point z knowing the nature of the lithofacies at n conditioning points or depth points already simulated in the neighbourhood of z.“ – Randomly selected depths (e.g., distance between a random point on the surface and the point in the reservoir directly below it) are used in a Monte-Carlo simulation to determine feature vectors used in training and modeling. These steps can be repeated as needed for one or more simulations.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claims to modify the reservoir modeling teachings of Halsey by the reservoir modeling techniques of Nivlet because the person of ordinary skill in the art would be motivated by the aim of Halsey to use stochastic processes to adequately model a reservoir Nivlet, which teaches robust and better calibrated stochastic distributions of relevant modeling parameters. (Halsey [0044] “In the feature space, machine learning classification or regression techniques (e.g., k-means clustering, support vector models, or Kriging) may then be used to establish the preferred decision for a given set of data. This may involve regressing the value of the metric to the point, points, or region that represent the truth case from neighboring reservoir models (e.g., in the feature space or the higher dimensional space), which have been simulated (e.g., both prior to and subsequent to the time T); and/or may involve estimating a probability distribution function of the metric value for the preferred decision or may involve determining clusters from the data corresponding to the reservoir models. The metric may be defined as a function in the feature space, with regression to the value of the function at the point, points, or region corresponding to the truth case, or it is possible to create a larger feature space by including the metric value as an axis, and then determine the metric at the truth case point or points using conventional regression methods, as noted above, in the sub-region occupied by reservoir model data in that larger space. These two approaches are equivalent. “ [0055] “Beneficially, the present techniques provide various enhancements to the hydrocarbon extraction process. The present techniques avoid the slow and cumbersome process of determining the reservoir or subsurface model that preferrably matches or assimilates additional data (data set B). In addition, the techniques use information from the full ensemble of two or more reservoir models, and not just from one or more history matched models, to evaluate the results of a hydrocarbon operation, which may improve the accuracy of the determination of the results of a hydrocarbon operation under consideration. Furthermore, the techniques allow two or more reservoir or subsurface models comprising the ensemble to be used differentially to support different hydrocarbon operations decisions, which may also improve the accuracy of the determination of the results of these different hydrocarbon operations. The present techniques may be further understood with reference to FIGS. 1 to 4, which are described further below.” [0073] “Alternatively, an estimate of a probability distribution function of the metric value for the truth case may also be utilized. One approach may be to use classification algorithms known in the statistical learning or machine learning art to determine if the point, points, or region corresponding to the truth case clusters or classifies with those reservoir models for which with the decision to add the well was successful or unsuccessful based on pre-determined economic and/or physical criteria.” ; Nivlet [0166] “The method according to the invention allows estimation at any point of the subsoil lithologic facies distributions that take fully advantage of the seismic information and of its spatial non-stationarities. The average of these distributions being more robust and better calibrated, it then allows better geological modelling and, consequently, better development of the petroleum reservoir corresponding to the geological model. The method according to the invention also allows estimation of the uncertainties on this seismic constraint. Potentially, it allows better integration of the seismic information in the geological modelling.”)
Claims 2, 9, and 16
Regarding claim 2, Halsey in view of Nivlet teaches the features of claim 1 and further teaches:
clustering the reservoir volume into a plurality of clustered three-dimensional volumes using a learned clustering algorithm alongside randomly selected three-dimensional log data from the plurality of realizations, wherein the static models include one of the clustered three- dimensional volumes. (Halsey [0044] “. The spatial relationship may be the forming of a region or area that is associated with the results within a distance threshold in the space of the measured or observed production data (e.g., actually observed production data). In the feature space, machine learning classification or regression techniques (e.g., k-means clustering, support vector models, or Kriging) may then be used to establish the preferred decision for a given set of data. This may involve regressing the value of the metric to the point, points, or region that represent the truth case from neighboring reservoir models (e.g., in the feature space or the higher dimensional space), which have been simulated (e.g., both prior to and subsequent to the time T); and/or may involve estimating a probability distribution function of the metric value for the preferred decision or may involve determining clusters from the data corresponding to the reservoir models. The metric may be defined as a function in the feature space, with regression to the value of the function at the point, points, or region corresponding to the truth case, or it is possible to create a larger feature space by including the metric value as an axis, and then determine the metric at the truth case point or points using conventional regression methods, as noted above, in the sub-region occupied by reservoir model data in that larger space.” – A clustering model is used to cluster the reservoir model into clustered three-dimensional volumes based on the randomly selected realizations of Nivlet.)
Claims 9 and 16 recite substantially the same features as claim 2 and are rejected for at least the same reasons.
Claims 3, 10, and 17
Regarding claim 3, Halsey in view of Nivlet teaches the features of claim 2 and further teaches:
wherein at least one of the static models includes one or more fault planes fitted to the plurality of clustered three-dimensional volumes. (Halsey [0044] “. The spatial relationship may be the forming of a region or area that is associated with the results within a distance threshold in the space of the measured or observed production data (e.g., actually observed production data). In the feature space, machine learning classification or regression techniques (e.g., k-means clustering, support vector models, or Kriging) may then be used to establish the preferred decision for a given set of data. This may involve regressing the value of the metric to the point, points, or region that represent the truth case from neighboring reservoir models (e.g., in the feature space or the higher dimensional space), which have been simulated (e.g., both prior to and subsequent to the time T); and/or may involve estimating a probability distribution function of the metric value for the preferred decision or may involve determining clusters from the data corresponding to the reservoir models. The metric may be defined as a function in the feature space, with regression to the value of the function at the point, points, or region corresponding to the truth case, or it is possible to create a larger feature space by including the metric value as an axis, and then determine the metric at the truth case point or points using conventional regression methods, as noted above, in the sub-region occupied by reservoir model data in that larger space.” – A clustering model is used to cluster the reservoir model into clustered three-dimensional volumes based on the randomly selected realizations of Nivlet. [0004] “The subsurface model may represent measured data and/or interpreted data for the subsurface region, may be within a physical space or domain, and may include objects (e.g., horizons, faults, surfaces, volumes, and the like).“ [0035] “ As used herein, “geologic model” is a three-dimensional model of the subsurface region having static properties and includes objects, such as faults and/or horizons, and properties, such as facies, lithology, porosity, permeability, or the proportion of sand and shale.” [0038] “The subsurface model may include multiple dimensions. The subsurface model may include a structural framework of objects, such as faults and horizons, and may include a mesh or grid of nodes to divide the structural framework and/or subsurface model into cells, which may include mesh elements or blocks in two-dimensions, mesh elements or voxels in three-dimensions or other suitable mesh elements in other dimensions.” – The models created from the clusters include models of facies and faults, fault planes.)
Claims 10 and 17 recite substantially the same features as claim 3 and are rejected for at least the same reasons.
Claims 4, 11, and 18
Regarding claim 4, Halsey in view of Nivlet teaches the features of claim 2, and further teaches:
wherein a reservoir graph is constructed from at least one of the static models with at least one three-dimensional volumes represented as a vertex. (Halsey [0066] “At block 212, a feature space is determined. As noted above, the feature space may be a higher dimensional space or may be a lower dimensional space with respect to some reference, e.g. that created by raw, unfit or unapproximated data alone. The feature space may be used to highlight differences and to assist in evaluating the metric and/or hydrocarbon operations. Then, the simulation results or a portion of the simulation results are optionally transformed into the feature space, as shown in block 214. This transformation may involve a mathematical representation or a graphical representation, which may depend on the size of the dimensionality. Then, at block 216, a region of interest in the feature space is identified.“ [0034] “As used herein, “subsurface model” refers to a reservoir model, a geomechanical model, a watertight model and/or a geologic model. The subsurface model may include subsurface data distributed within the model in two-dimensions (e.g., distributed into a plurality of cells, such as elements or blocks), three-dimensions (e.g., distributed into a plurality of voxels) or three or more dimensions.”– The data generated is used to construct a reservoir graph representing the data and which includes at least one vertex (as graphs do) based on that data.)
Claims 11 and 18 recite substantially the same features as claim 4 and are rejected for at least the same reasons.
Claims 5, 12, and 19
Regarding claim 5, Halsey in view of Nivlet teaches the features of claim 4, and further teaches:
wherein the reservoir graph is defined such that at least one of the clustered three-dimensional volumes has at least one of: at most one pressure observation point, only one well passing through the cluster, or a spatially continuous voxel set only. (Halsey [0004] “The subsurface model may also be discretized with a mesh or a grid that includes nodes and forms cells (e.g., voxels or elements) within the model. The geologic model may represent measured or interpreted data for the subsurface region, such as seismic data and well log data, and may have material properties, such as rock properties. The reservoir model may be used to simulate flow of fluids within the subsurface region. Accordingly, the reservoir model may use the same mesh and/or cells as other models, or may resample or upscale the mesh and/or cells to lessen the computations for simulating the fluid flow.” [0034] “As used herein, “subsurface model” refers to a reservoir model, a geomechanical model, a watertight model and/or a geologic model. The subsurface model may include subsurface data distributed within the model in two-dimensions (e.g., distributed into a plurality of cells, such as elements or blocks), three-dimensions (e.g., distributed into a plurality of voxels) or three or more dimensions.” – The graph is defined such that the volumes have a spatially continuous voxel set.)
Claims 12 and 19 recite substantially the same features as claim 5 and are rejected for at least the same reasons.
Claims 6, 13, and 20
Regarding claim 6, Halsey in view of Nivlet teaches the features of claim 1, and further teaches:
populating core data in the reservoir volume using a learned k-nearest neighbor algorithm alongside the three-dimensional populated log, wherein the static models include a three- dimensional volume of the core data, and wherein the core data includes at least one of porosity, permeability, or water saturation. (Halsey [0044] “In the feature space, machine learning classification or regression techniques (e.g., k-means clustering, support vector models, or Kriging) may then be used to establish the preferred decision for a given set of data. This may involve regressing the value of the metric to the point, points, or region that represent the truth case from neighboring reservoir models (e.g., in the feature space or the higher dimensional space), which have been simulated (e.g., both prior to and subsequent to the time T); and/or may involve estimating a probability distribution function of the metric value for the preferred decision or may involve determining clusters from the data corresponding to the reservoir models. The metric may be defined as a function in the feature space, with regression to the value of the function at the point, points, or region corresponding to the truth case, or it is possible to create a larger feature space by including the metric value as an axis, and then determine the metric at the truth case point or points using conventional regression methods, as noted above, in the sub-region occupied by reservoir model data in that larger space. These two approaches are equivalent. [0035] “As used herein, “geologic model” is a three-dimensional model of the subsurface region having static properties and includes objects, such as faults and/or horizons, and properties, such as facies, lithology, porosity, permeability, or the proportion of sand and shale.” [0042] “The first data set may include seismic data, well test data and well log data that is used to generate the reservoir models. A second data set, which may be referred to as data set B, includes data that is not used to condition the reservoir models, but instead defines a feature space (which may ultimately be simplified or reduced in dimension) in which the reservoir model results or operations data can be represented as points.” – Core data (e.g., porosity etc. ) is populated with the reservoir volume using k-nearest neighbors. This is used with other data, including three-dimensional log data. [0034]-[0036] ““As used herein, the term “subsurface model” refers to a model of a subsurface region and may include a reservoir model, a geomechanical model, a watertight model, and/or a geologic model. The subsurface model may include subsurface data distributed within the model in two-dimensions (e.g., distributed into a plurality of cells, such as elements or blocks), three-dimensions (e.g., distributed into a plurality of voxels,), or four or more dimensions. As used herein, the term “geologic model” refers to a model (e.g., a two-dimensional model or a three dimensional model) of the subsurface region having static properties and includes objects, such as faults and/or horizons, and properties, such as facies, lithology, porosity, permeability, and/or the proportion of sand and shale. As used herein, the term “reservoir model” is a model (e.g., a two-dimensional model or a three-dimensional model) of the subsurface that in addition to static properties, such as porosity and/or permeability, also has dynamic properties that vary over the timescale of resource extraction, such as fluid composition, pressure, and/or relative permeability.” [0078] “This sample realization is a part of an ensemble of 285 reservoir models, which are generated by conditioning the reservoir models to pre-production data. The ensemble of realizations represents uncertainty in the earth parameters, such as the porosity, the proximal/distal/medial grain size, the net-to-gross ratio (NTG) and the stacking pattern. FIG. 3E is an exemplary diagram 346 of the ensemble of the 285 models, which represent different clusters associated with different scenarios. These clusters are shown along a quality of interest (QoI) axis and a history axis (d.sub.H).” – 3-D static models with core data are generated.)
Claims 13 and 20 recite substantially the same features as claim 6 and are rejected for at least the same reasons.
Claims 7 and 14 : Halsey, Nivlet, and Al-Farisis
Claims 7 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over US 2018/0188403 A1 to Halsey et al. (Halsey) in view of US 2008/0162093 A1 to Nivlet et al. (Nivlet) and NPL: “Quantification of Fracture Permeability From Micro Resistivity Logs in Offshore Abu Dhabi Reservoir” by Al-Farisi et al. (Al-Farisi).
Claims 7 and 14
Regarding claim 7, Halsey in view of Nivlet teaches the features of claim 1. Halsey suggests using permeability as a feature in the feature space of static models (Halsey [0035]-[0036] “As used herein, “geologic model” is a three-dimensional model of the subsurface region having static properties and includes objects, such as faults and/or horizons, and properties, such as facies, lithology, porosity, permeability, or the proportion of sand and shale. As used herein, “reservoir model” is a three-dimensional model of the subsurface that in addition to static properties, such as porosity and permeability, also has dynamic properties that vary over the timescale of resource extraction, such as fluid composition, pressure, and relative permeability.), but does not appear to explicitly teach, but Halsey in view of Nivlet and :
wherein the three-dimensional populated log data includes at least one of gamma ray, neutron porosity, bulk density, or resistivity. (Al-Farisi Abstract “it is recognized that fractures play an important role in influencing reservoir flow and connectivity both vertically (between reservoir units) and areally within the same reservoir unit. Image logs and borehole seismic surveys have been run to extensively identify fracture location and direction to understand the flow path of these reservoirs. However, in this paper an advanced step has been achieved in quantifying the fracture permeability from Conventional Logging Data, which is Micro-Resistivity Log, aided with Gamma-ray and Neutron-Density porosity logs. We all realized how vital, useful and critical this type of information would be as an input to reservoir simulators. This paper presents two techniques that have been developed to determine fracture permeability in reservoir rock and dense zones, these two techniques are merged to call it UFLIP (Universal Fracture Log Integrated Permeability).” – The log data includes gamma-ray and Neutron-Density porosity logs.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claims to modify the generic permeability consideration for the model in Halsey by the permeability determination of Al-Farisi because the person of ordinary skill in the art would be motivated by the aim of Halsey to model reservoirs based on permeability, to look to Al-Farisi, which teaches vital, useful, and critical metrics from which to determine permeability. (Halsey [0004] “In exploration, development and/or production stages for resources, such as hydrocarbons, different types of subsurface models may be used to represent the subsurface structures, which may include a description of subsurface structures and material properties for a subsurface region. For example, the subsurface model may be a geologic model or a reservoir model. The subsurface model may represent measured data and/or interpreted data for the subsurface region, may be within a physical space or domain, and may include objects (e.g., horizons, faults, surfaces, volumes, and the like). The subsurface model may also be discretized with a mesh or a grid that includes nodes and forms cells (e.g., voxels or elements) within the model. The geologic model may represent measured or interpreted data for the subsurface region, such as seismic data and well log data, and may have material properties, such as rock properties. The reservoir model may be used to simulate flow of fluids within the subsurface region. Accordingly, the reservoir model may use the same mesh and/or cells as other models, or may resample or upscale the mesh and/or cells to lessen the computations for simulating the fluid flow.” [0035] “As used herein, “geologic model” is a three-dimensional model of the subsurface region having static properties and includes objects, such as faults and/or horizons, and properties, such as facies, lithology, porosity, permeability, or the proportion of sand and shale.”; Al-Farisi Abstract “In Abu Dhabi offshore carbonates, it is recognized that fractures play an important role in influencing reservoir flow and connectivity both vertically (between reservoir units) and areally within the same reservoir unit. Image logs and borehole seismic surveys have been run to extensively identify fracture location and direction to understand the flow path of these reservoirs. However, in this paper an advanced step has been achieved in quantifying the fracture permeability from Conventional Logging Data, which is Micro-Resistivity Log, aided with Gamma-ray and Neutron-Density porosity logs.”)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
NPL: “Automatic fracture density update using smart well data and artificial neural networks” by Al-Anazi et al. (Teaches using neural networks to update well data)
NPL: “On the Capability of Support Vector Machines to Classify Lithology from Well Logs” by Al-Anazi et al. (Teaches using SVMs to characterize well lithology)
NPL: “Permeability prediction and construction of 3D geological model: application of neural networks and stochastic approaches in an Iranian gas reservoir” by Fegh et al. (Teaches using neural networks and stochastic relationship to determine permeability)
NPL: “Sequential Monte Carlo Methods to Train Neural Network Models” by de Freitas et al. (Teaches training neural nets using Monte Carlo methods)
NPL: “Use of Multi-Attribute Transforms to Predict Log Properties from Seismic Data” by Hampson et al. (Teaches using multi-attribute transforms to predict log properties from seismic data)
NPL: “Practical application of fuzzy logic and neural networks to fractured reservoir characterization” by Ouenes et al. (Teaches using neural networks and fuzzy logic to determine fractured reservoir characteristics)
NPL: “Reservoir Permeability Prediction Using Artificial Neural Network; A Case Study of “XZ” Field, Offshore Niger Delta” by Ozebo et al. (Teaches using neural networks to determine permeability)
NPL: “Using artificial neural networks to generate synthetic well logs” by Rolon et al. (Teaches using neural networks to generate synthetic well data)
NPL: “Estimation of Reservoir Properties from Seismic Attributes and Well Log Data using Artificial Intelligence” by Sitouah (Teaches using machine learning to determine properties from seismic and well log data)
NPL: “Artificial Neural Networks applied to estimate permeability, porosity and intrinsic attenuation using seismic attributes and well-log data” by Iturraran-Viveros et al. (Teaches using neural networks to determine properties from seismic and well log data)
US 2012/0221306 A1 to Hurley et al. (Teaches upscaled lithology modeling using well data)
US 2020/0124753 A1 to Halsey et al. (Teaches determining variability of a metric in an ensemble of subsurface realizations)
US 2014/0039859 A1 to Maucec et al. (Teaches selecting models based on dynamic simulation realization sets)
US 2017/0139065 A1 to Gentilhomme (Teaches generating and selecting realizations from an ensemble based on a sensitivity matrix and and model to yield subsurface parameters)
US 2016/0326845 A1 to Djikpesse et al. (Teaches inferring oilfield design parameters based on stochastic determinations of unknowns)
US 8,965,744 B2 to Da Veiga et al. (Teaches reservoir model reconstruction, including selecting random numbers for input into a geostatistical simulator to provide a facies/fault representation)
US 7,079,953 B2 to Thorne et al. (Teaches creating a reservoir model by geostatistical simulation based on a training image and facies probability cubes)
US 8,874,419 B2 to Da Veiga (Teaches using stochastic methods to determine facies values of cells in a mesh)
US 6,480,790 B1 to Calvert et al. (Teaches generating a 3D geologic model based on spatial attributes of geologic interfaces)
US 9,779,060 B2 to Maucec et al. (Teaches updating geologic models based on discrete cosine transform (DCT) basis functions using the distribution of DCT coefficients of geologic model realizations)
CA 2,384,810 C to Cullick et al. (Teaches modeling a reservoir based on randomly selected points for potential completions and arc lengths and angles between arc pairs)
WO 2001/033481 A1 to Calvert et al. (Teaches stochastic process generation of geologic models)
CA 2816815 A1 to Maucec (Teaches updating geologic models based on discrete cosine transform (DCT) basis functions using the distribution of DCT coefficients of geologic model realizations)
WO 2015/103582 A1 to Djikpesse et al. (Teaches designing an oil field by stochastic analysis of a control variable)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAY MICHAEL WHITE whose telephone number is (571) 272-7073. The examiner can normally be reached Mon-Fri 11:00-7:00 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Ryan Pitaro can be reached at (571) 272-4071. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/J.M.W./Examiner, Art Unit 2188
/RYAN F PITARO/Supervisory Patent Examiner, Art Unit 2188
