DETAILED ACTION
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 .
Drawings
The drawings are objected to because figures 3, 10, and 11 include graphs with no axis labels making them unclear. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
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 1-7, 9-17, 19, and 20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
With respect to claims 1 and 12,
Step 2A Prong One:
The following bold limitations are considered abstract:
“receiving, by a seismic processing system, a seismic dataset regarding a subsurface region of interest, wherein the seismic dataset comprises a plurality of time-space waveforms organized in a first data domain, and wherein the seismic processing system comprises a trainable machine-learning (ML) network;
and using the seismic processing system:
forming a training waveform set from a subset of the plurality of time-space waveforms, wherein the training waveform set is organized in a second data domain, and wherein an extent of the second data domain comprises an extent of the first data domain,
partitioning the first data domain in training bins to generate a plurality of training subsets from the training waveform set, wherein each training subset is associated to a corresponding training bin,
determining a plurality of initial first arrivals based on the plurality of training subsets, wherein each initial first arrival is associated to a corresponding training subset, and wherein each initial first arrival is based on picking a first arrival of at least one time-space waveform of the corresponding training subset,
forming a training dataset, wherein the training dataset comprises an input training dataset and an output training dataset, wherein the input training dataset is based on the plurality of training subsets and the output training dataset is based on the plurality of initial first arrivals,
and training, using the training dataset, the machine-learning (ML) network to predict the output training dataset, at least in part, from the input training dataset.”
The above bolded limitations are directed to abstract ideas and would fall within the “Mathematical Concept” and “Mental Process” groupings of abstract ideas. Training using a training dataset to predict an output data set is a mathematical concept as data is just input into an algorithm as seen in Para(s). [0059-0063] of the specification. According to MPEP 2106.04(C) “A claim that recites a mathematical calculation, when the claim is given its broadest reasonable interpretation in light of the specification, will be considered as falling within the "mathematical concepts" grouping. A mathematical calculation is a mathematical operation (such as multiplication) or an act of calculating using mathematical methods to determine a variable or number, e.g., performing an arithmetic operation such as exponentiation. There is no particular word or set of words that indicates a claim recites a mathematical calculation. That is, a claim does not have to recite the word "calculating" in order to be considered a mathematical calculation. For example, a step of "determining" a variable or number using mathematical methods or "performing" a mathematical operation may also be considered mathematical calculations when the broadest reasonable interpretation of the claim in light of the specification encompasses a mathematical calculation.” Forming a waveform set and partitioning data into bins can be viewed as a mental process as it is just sorting data into groups using observation and judgement. Determining a plurality of first arrivals is also a mental process as seen in Para. [0058] of the specification as it can also be done through manual picking. According to MPEP 2106.04(a)(2)(III) “"mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions,” and “As the Federal Circuit has explained, "[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind." Versata Dev. Group v. SAP Am., Inc., 793 F.3d 1306, 1335, 115 USPQ2d 1681, 1702 (Fed. Cir. 2015).”
Step 2A Prong Two:
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements –
“receiving, by a seismic processing system, a seismic dataset regarding a subsurface region of interest, wherein the seismic dataset comprises a plurality of time-space waveforms organized in a first data domain, and wherein the seismic processing system comprises a trainable machine-learning (ML) network; and using the seismic processing system”
Examiner views these limitations amount to generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h).
Moreover, Examiner views the claims to be merely generally linking the use of the judicial exception to seismic data and a generic machine learning algorithm. Furthermore, a seismic processing system is viewed as using a computer as a tool and receiving the seismic data is viewed as mere data gathering.
As such Examiner does NOT view that the claims
-Improve the functioning of a computer, or to any other technology or technical field
-Apply the judicial exception with, or by use of, a particular machine - see MPEP
2106.05(b)
-Effect a transformation or reduction of a particular article to a different state or thing -
see MPEP 2106.05(c)
-Apply or use the judicial exception in some other meaningful way beyond generally
linking the use of the judicial exception to a particular technological environment, such that the
claim as a whole is more than a drafting effort designed to monopolize the exception - see MPEP
2106.05(e) and Vanda Memo.
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Considering the claim as a whole, one of ordinary skill in the art would not know the practical application of the present invention since the claims do not apply or use the judicial exception in some meaningful way. As currently claimed, Examiner views that the additional elements do not apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, because the claim fails to recite clearly how the judicial exception is applied in a manner that does not monopolize the exception because the limitations “receiving, by a seismic processing system, a seismic dataset regarding a subsurface region of interest, wherein the seismic dataset comprises a plurality of time-space waveforms organized in a first data domain, and wherein the seismic processing system comprises a trainable machine-learning (ML) network” just tie the claim to some computational device and seismic data. Examiner further notes that such additional elements are viewed to be well known routine and conventional as evidenced by Schaefer (US 20240385343 A1) and Vinje (US 20230086711 A1).
Dependent claims 2-7, 9-11, 13-17, 19, and 20 when analyzed as a whole are held to be patent ineligible under 35 U.S.C. 101 because the additional recited limitation(s) fail(s) to establish that the claims are not directed to an abstract idea, as detailed below:
The dependent claims are directed to training ML subnetworks, forming further subsets of data, determining an image, determining a drilling target, and making predictions all of which are mathematical concepts and abstract ideas.
Therefore, dependent claims 2-7, 9-11, 13-17, 19, and 20 further limit the abstract idea with an abstract idea and thus the claims are still directed to an abstract idea without significantly more.
Claims 8 and 18 are patent eligible under 35 U.S.C. 101 because they contain the limitation “drilling, using a drilling system, a portion of a wellbore guided by the planned wellbore trajectory.” This limitation integrates the claims into a practical application because they are using the judicial exception in a meaningful way by drilling the borehole to reach the determined drilling target. (See MPEP 2106.05).
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 1-5, 9, 10, 12-16, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Schaefer (US 20240385343 A1) in view of Vinje (US 20230086711 A1).
With respect to claims 1 and 12,
Schaefer teaches,
receiving, by a seismic processing system, a seismic dataset regarding a subsurface region of interest, wherein the seismic dataset comprises a plurality of time-space waveforms organized in a first data domain, and wherein the seismic processing system comprises a trainable machine-learning (ML) network; (Para. [0024] teaches “sensing cables are permanently installed in the injection well and/or monitoring wells, and/or surface 1-axis and/or 3-axis seismic sensors, e.g., geophones or accelerometers, are used for data collection. In certain situations, the surface sensor stations include rotational sensors in addition to the seismic sensors.” Para. [0050] teaches “By developing a population of microseismic events in common source gather sorting, a user annotates each with the pixels (samples of time and measured depth) that correspond to the compressional and shear arrivals respectively. The ML model applied is like the Deep Learning Signal Processing in that it is a modified UNet tuned for classification purposes, e.g., using a cross entropy cost function.” [Para. [0052] teaches “In certain embodiments, the sample MSEs are collected from actual DAS systems in actual wellbores are used. In certain embodiments, the noise samples are collected from actual DAS systems in actual wellbores”)
and using the seismic processing system:
forming a training waveform set from a subset of the plurality of time-space waveforms, wherein the training waveform set is organized in a second data domain, and wherein an extent of the second data domain comprises an extent of the first data domain, (Para. [0047] teaches “dataset of 10,000 samples to recognize DAS MSE characteristics, wherein the seismic energy released when a fracture that fails during hydraulic stimulation crates compression and shear waves that propagate outward. In certain embodiments, the data in the training dataset is divided into different subsets including training data, validation data, and test data. The resulting arrivals observed are hyperbolic in their shape along the gather.”)
determining a plurality of initial first arrivals based on the plurality of training subsets, wherein each initial first arrival is associated to a corresponding training subset, and wherein each initial first arrival is based on picking a first arrival of at least one time-space waveform of the corresponding training subset, (Para. [0050] teaches “Input microseismic data wherein the samples are integer valued. For example, the background noise will be annotated as class 0, the compressional arrival will be class 1, and shear horizontal arrival as class 2. Thus, the model seeks to build a latent (compressed) representation that captures the statistical nature of each of these annotated pixels (time and measured depth). The CNN model will make predictions for each input class (noise, compressional, shear) and the maximum prediction for each pixel will be utilized.”
forming a training dataset, wherein the training dataset comprises an input training dataset and an output training dataset, wherein the input training dataset is based on the plurality of training subsets and the output training dataset is based on the plurality of initial first arrivals, (Para. [0092] teaches “(CNN) trained with a third set of training windows comprising a plurality of third subsets of training windows; each third subset comprises an output training window having an example arrival pick and a plurality of input training windows each having a respective selection from a plurality of MSEs associated with the example arrival pick; and the truncation of the signal window is performed before the third CNN identifies the first arrival pick.)
and training, using the training dataset, the machine-learning (ML) network to predict the output training dataset, at least in part, from the input training dataset. (Para. [0092] teaches “identifying the first arrival pick is performed by a third convolutional neural network (CNN) trained with a third set of training windows”)
Schaefer does not explicitly teach,
partitioning the first data domain in training bins to generate a plurality of training subsets from the training waveform set, wherein each training subset is associated to a corresponding training bin. However, Schaefer does teach a plurality of training subsets as seen in Para. [0050].
Vinje teaches,
partitioning the first data domain in training bins to generate a plurality of training subsets from the training waveform set, wherein each training subset is associated to a corresponding training bin. (Para. [0029] teaches “Preprocessed data 220 is then sorted and binned at S202, to obtain binned data 230 (labeled “R6”) with irregularly populated bins in offset classes due to the data acquisition geometry.” Also see figure 2.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Schaefer with partitioning the first data domain in training bins to generate a plurality of training subsets from the training waveform set, wherein each training subset is associated to a corresponding training bin such as that of Vinje.
One of ordinary skill would have been motivated to modify Schaefer, because binning can reduce the number of missing values in a dataset and make the data more manageable for the machine learning algorithm to process which would increase efficiency. This is further corroborated by Para. [0008] of Vinje which states that their method increases efficiency and accuracy of seismic data processing.
With respect to claims 2 and 13,
Schaefer further teaches,
wherein training the ML network comprises training a plurality of ML subnetworks, wherein each ML subnetwork is trained to predict each initial first arrival from, at least in part, the corresponding training subset. (Para. [0071] teaches “In summary, the procedures an expert analyst would perform in processing DAS microseismic data can not only be automated but optimized using a cascading workflow of trained ML models. Applying a cutting-edge signal processing technique (deep learning signal processing) to a sliding window of continuous record data, the MSE energy can be boosted while reducing the coherent/incoherent background noise.”)
With respect to claims 3 and 15,
Schaefer further teaches,
further comprising: forming a plurality of input subsets from the plurality of time-space waveforms; and determining a plurality of predicted first arrivals using the plurality of ML subnetworks, wherein each predicted arrival is associated to a corresponding input subset, and wherein each ML subnetwork is used to predict a predicted first arrival from, at least in part, the corresponding input subset. (Para. [0092] teaches “Identifying the first arrival pick and the event apex position comprises truncating the signal window to remove a portion of the signal window that does not contain the identified MSE, thereby providing a third reduction in the magnitude of the received signal to be further analyzed; identifying the first arrival pick is performed by a third convolutional neural network (CNN) trained with a third set of training windows comprising a plurality of third subsets of training windows; each third subset comprises an output training window having an example arrival pick and a plurality of input training windows each having a respective selection from a plurality of MSEs associated with the example arrival pick; and the truncation of the signal window is performed before the third CNN identifies the first arrival pick.”)
With respect to claims 4 and 16,
Schaefer does not explicitly teach,
wherein forming the plurality of input subsets comprises using the training bins, and wherein each waveform of the input subset is located in a corresponding training bin.
Vinje teaches,
wherein forming the plurality of input subsets comprises using the training bins, and wherein each waveform of the input subset is located in a corresponding training bin. (Para. [0029] teaches “In FIG. 2, real data 210 (labeled “R1”) acquired over the explored subsurface formation is subjected to preprocessing for removing unwanted energy (waves and noise) in S201. Although the description of the method illustrated in FIG. 2 refers to the entire dataset and all offset classes, only a representative portion thereof and possibly only one or less than all offset classes may be used for training (e.g., about 10% of the data). Step S201 may include denoising, deblending, removing source signature (i.e., designature if the source was a multi-element source), debubbling (if removal of bubble oscillations is necessary in a marine environment), deghosting, demultiple, etc. The preprocessing is performed using known techniques and yields preprocessed data 220 (labeled “R5,” labels “R2,” “R3” and “R4” are used later, when the preprocessing is illustrated in more detail). Preprocessed data 220 is then sorted and binned at S202, to obtain binned data 230 (labeled “R6”) with irregularly populated bins in offset classes due to the data acquisition geometry.” Also see figure 2.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Schaefer with partitioning the first data domain in training bins to generate a plurality of training subsets from the training waveform set, wherein each training subset is associated to a corresponding training bin such as that of Vinje.
One of ordinary skill would have been motivated to modify Schaefer, because binning can reduce the number of missing values in a dataset and make the data more manageable for the machine learning algorithm to process which would increase efficiency. This is further corroborated by Para. [0008] of Vinje which states that their method increases efficiency and accuracy of seismic data processing.
With respect to claim 5,
Schaefer further teaches,
The method of claim 1, wherein the data domain comprises a common-depth-point domain. (Para. [0050] teaches “The input to the model is the common source gather microseismic event which has been truncated in time and space due to the predicted event onset time in a previous step and the output is the annotated “mask.” The mask is a set of samples in time and measured depth with the same shape as the input microseismic data wherein the samples are integer valued.”)
With respect to claim 9,
Schaefer further teaches,
wherein the ML network comprises a convolutional neural network. (Para. [0004] teaches “The data collected using a DAS system inherently has a low signal-to-noise ratio (SNR). One conventional method of extracting the signal from the data is to use a convolutional neural network (CNN) design”)
With respect to claims 10 and 19,
Schaefer further teaches,
further comprising: receiving, by the seismic processing system, a second plurality of time-space waveforms organized in a third data domain, wherein the extent of the second data domain comprises an extent of the third data domain; and predicting, using the seismic processing system and the trained ML network, a plurality of predicted first arrivals based, at least in part, on the second plurality of time-space waveforms. (Para(s). [0062-0064] teach “The windows are classified as “having an MSE” if an MSE is detected or classified as “noise” if no MSE is detected. In certain embodiments, the “having an MSE” group is subdivided into a “high SNR” and a “low SNR” group. The noise group is routed by step 542 to step 544 and discarded, thereby further reducing the magnitude of the data set being analyzed and further reducing the computational time. Step 550 submits the windows having an MSE to a second CNN trained to increase the SNR of the MSE compared to the noise in the window then identify an onset time and peak channel in the window. Step 560 receives the window and information from step 550 and identifies a first arrival time and an event apex position based, in part, on the onset time and peak channel. In certain embodiments, the ML model for onset detection has an EfficientDet architecture. In certain embodiments, the ML model is trained using a plurality of data windows, e.g., 10,000 data windows, that have bounding boxes annotated around the center of the hyperbolic moveout peak along the channel axis (measured depth) and in time at the onset of arrival. In certain embodiments, the training is posed as a classification and regression problem, structured to minimize cross-entropy and mean squared error respectively.”)
With respect to claim 14
Schaefer further teaches,
The system of claim 12, further comprising a seismic acquisition system configured to acquire the seismic dataset. (Para. [0056] teaches “with the receipt of a signal from an optical detector (see FIG. 6) connected to a FO cable disposed within a wellbore (as shown in FIG. 1). In this example, the signal is an analog electronic signal having an approximate total duration equal to time that a laser pulse takes to make the round-trip from the laser to the bottom end of the FO cable and return to the optical detector. The signal contains portions that are phase-shifted, also referred to herein as a “differential phase,” from the frequency of the input laser pulse.”)
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Schaefer (US 20240385343 A1) and Vinje (US 20230086711 A1) as applied to claim 1 above, and further in view of Gordon (WO 2016075550 A1).
With respect to claim 6,
Schaefer does not explicitly teach,
The method of claim 1, wherein each time-space waveform of a corresponding training subset is associated to a spatial coordinate, and wherein a spatial coordinate of the at least one time-space waveform is a closest spatial coordinate to an average of the spatial coordinates of all time-space waveforms of the corresponding training subset.
Gordon teaches,
wherein each time-space waveform of a corresponding training subset is associated to a spatial coordinate, and wherein a spatial coordinate of the at least one time-space waveform is a closest spatial coordinate to an average of the spatial coordinates of all time-space waveforms of the corresponding training subset. (Para. [0123] teaches “With multiple datasets, it may be of interest to interpolate all vintages on to a common sampling that includes positions not occupied by any dataset. The positions could be designed so that the interpolation distance on average is minimum, i.e., the positions are selected as close as possible to the input data positions because the interpolation quality at positions further away is expected to degrade.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Schaefer and Vinje, wherein each time-space waveform of a corresponding training subset is associated to a spatial coordinate, and wherein a spatial coordinate of the at least one time-space waveform is a closest spatial coordinate to an average of the spatial coordinates of all time-space waveforms of the corresponding training subset such as that of Gordon.
One of ordinary skill would have been motivated to modify the combination of Schaefer and Vinje, because quality of the data degrades as the selected spatial coordinate moves further away from the input data positions as seen in Para. [0123] of Gordon. Therefore, it would be obvious to combine the prior art in order to increase accuracy of the model.
Claims 7, 8, 17, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Schaefer (US 20240385343 A1) and Vinje (US 20230086711 A1) as applied to claims 2 and 15 above, and further in view of Zhao (US 20250004154 A1).
With respect to claim 7,
Schaefer does not explicitly teach,
The method of claim 2, further comprising: generating, using the seismic processing system, a seismic image based, at least in part, on the plurality of predicted first arrivals; and determining, using a seismic interpretation system, a drilling target in the subsurface region based, at least in part, on the seismic image.
Zhao teaches,
further comprising: generating, using the seismic processing system, a seismic image based, at least in part, on the plurality of predicted first arrivals; and determining, using a seismic interpretation system, a drilling target in the subsurface region based, at least in part, on the seismic image. (Para. [0061] teaches “The picked first arrivals may then be employed to build a velocity model of the subterranean volume, as at 412, which may be used to generate digital models (and display/visualize images) of the subsurface volume. Such digital models have a wide variety of practical applications in the art, such as, for example, in exploration to predict reservoir locations, in well planning to establish trajectories and drilling parameters, and/or in treatment to establish treatment (e.g., fracturing) plans.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Schaefer and Vinje further comprising: generating, using the seismic processing system, a seismic image based, at least in part, on the plurality of predicted first arrivals; and determining, using a seismic interpretation system, a drilling target in the subsurface region based, at least in part, on the seismic image such as that of Zhao.
One of ordinary skill would have been motivated to modify the combination of Schaefer and Vinje, because determining a drilling target is one of the many practical applications of generating an image using predicted first arrivals as seen in Para. [0061] of Zhao. Furthermore, those targets allow a user to drill or fracture a well to reach their target.
With respect to claim 8,
Schaefer does not explicitly teach,
The method of claim 7, further comprising: planning, using a wellbore planning system, a planned wellbore trajectory to intersect the drilling target; and drilling, using a drilling system, a portion of a wellbore guided by the planned wellbore trajectory.
Zhao teaches,
further comprising: planning, using a wellbore planning system, a planned wellbore trajectory to intersect the drilling target; and drilling, using a drilling system, a portion of a wellbore guided by the planned wellbore trajectory. (Para. [0029] teaches “Typically, the wellbore is drilled according to a drilling plan that is established prior to drilling. The drilling plan typically sets forth equipment, pressures, trajectories and/or other parameters that define the drilling process for the wellsite. The drilling operation may then be performed according to the drilling plan.” Para. [0061] teaches “The picked first arrivals may then be employed to build a velocity model of the subterranean volume, as at 412, which may be used to generate digital models (and display/visualize images) of the subsurface volume. Such digital models have a wide variety of practical applications in the art, such as, for example, in exploration to predict reservoir locations, in well planning to establish trajectories and drilling parameters, and/or in treatment to establish treatment (e.g., fracturing) plans.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Schaefer and Vinje further comprising: planning, using a wellbore planning system, a planned wellbore trajectory to intersect the drilling target; and drilling, using a drilling system, a portion of a wellbore guided by the planned wellbore trajectory such as that of Zhao.
One of ordinary skill would have been motivated to modify the combination of Schaefer and Vinje, because drilling the well would allow the user to extract whatever their target was.
With respect to claim 17,
Schaefer does not explicitly teach,
The system of claim 15, wherein the seismic processing system is further configured to generate a seismic image based, at least in part, on the plurality of predicted first arrivals.
Zhao teaches,
The system of claim 15, wherein the seismic processing system is further configured to generate a seismic image based, at least in part, on the plurality of predicted first arrivals. (Para. [0061] teaches “The picked first arrivals may then be employed to build a velocity model of the subterranean volume, as at 412, which may be used to generate digital models (and display/visualize images) of the subsurface volume. Such digital models have a wide variety of practical applications in the art, such as, for example, in exploration to predict reservoir locations, in well planning to establish trajectories and drilling parameters, and/or in treatment to establish treatment (e.g., fracturing) plans.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Schaefer and Vinje wherein the seismic processing system is further configured to generate a seismic image based, at least in part, on the plurality of predicted first arrivals such as that of Zhao.
One of ordinary skill would have been motivated to modify the combination of Schaefer and Vinje, because seismic images provide a detailed image of the area of interest. This would allow for determinations to be made about the area e.g. how to drill or fracture to get to the desired location.
With respect to claim 18,
Schaefer does not explicitly teach,
The system of claim 17, further comprising: a seismic interpretation system configured to determine a drilling target in the subsurface region based, at least in part, on the seismic image; a wellbore planning system configured to plan a planned wellbore trajectory to intersect the drilling target; and a drilling system configured to drill a portion of a wellbore guided by the planned wellbore trajectory
Zhao teaches,
further comprising: a seismic interpretation system configured to determine a drilling target in the subsurface region based, at least in part, on the seismic image; a wellbore planning system configured to plan a planned wellbore trajectory to intersect the drilling target; and a drilling system configured to drill a portion of a wellbore guided by the planned wellbore trajectory. (Para. [0029] teaches “Typically, the wellbore is drilled according to a drilling plan that is established prior to drilling. The drilling plan typically sets forth equipment, pressures, trajectories and/or other parameters that define the drilling process for the wellsite. The drilling operation may then be performed according to the drilling plan.” Para. [0061] teaches “The picked first arrivals may then be employed to build a velocity model of the subterranean volume, as at 412, which may be used to generate digital models (and display/visualize images) of the subsurface volume. Such digital models have a wide variety of practical applications in the art, such as, for example, in exploration to predict reservoir locations, in well planning to establish trajectories and drilling parameters, and/or in treatment to establish treatment (e.g., fracturing) plans.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Schaefer and Vinje further comprising: a seismic interpretation system configured to determine a drilling target in the subsurface region based, at least in part, on the seismic image; a wellbore planning system configured to plan a planned wellbore trajectory to intersect the drilling target; and a drilling system configured to drill a portion of a wellbore guided by the planned wellbore trajectory such as that of Zhao.
One of ordinary skill would have been motivated to modify the combination of Schaefer and Vinje, because drilling the well would allow the user to extract whatever their target was.
Claims 11 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Schaefer (US 20240385343 A1) and Vinje (US 20230086711 A1) as applied to claims 2 and 14 above, and further in view of Kim (US 20220187485 A1).
With respect to claims 11 and 20,
Schaefer further teaches,
wherein the seismic dataset comprises a plurality of observed time-space waveforms acquired by a seismic acquisition system, and wherein the method further comprises: predicting the plurality of first arrivals using the trained ML network based, at least in part, on the plurality of observed time-space waveforms; (Para. [0056] teaches “with the receipt of a signal from an optical detector (see FIG. 6) connected to a FO cable disposed within a wellbore (as shown in FIG. 1). In this example, the signal is an analog electronic signal having an approximate total duration equal to time that a laser pulse takes to make the round-trip from the laser to the bottom end of the FO cable and return to the optical detector. The signal contains portions that are phase-shifted, also referred to herein as a “differential phase,” from the frequency of the input laser pulse.” Para. [0071] teaches “Each unique event will then be passed through a first arrival picking ML model, which seeks to identify the onset of energy for each waveform phase of interest (compressional and shear horizontal/vertical waves).”)
Schaefer does not explicitly teach,
receiving a seismic velocity model of the subsurface region of interest; and generating an updated seismic velocity model iteratively, or recursively, until a stopping condition is reached, wherein generating the updated seismic velocity model comprises: generating a synthetic seismic dataset based, at least in part, on the seismic velocity model and a geometry of the plurality of observed time-space waveforms, and updating, the seismic velocity model based, at least in part, on the synthetic seismic dataset, the plurality of predicted first arrivals and the plurality of observed time-space waveforms.
Kim teaches,
receiving a seismic velocity model of the subsurface region of interest; (Para. [0031] teaches “In Block 304 the initial seismic velocity model is first assigned to be the current seismic velocity model. Later in the flow, the current seismic velocity model will be updated iteratively as part of the inversion.”)
and generating an updated seismic velocity model iteratively, or recursively, until a stopping condition is reached, wherein generating the updated seismic velocity model comprises: generating a synthetic seismic dataset based, at least in part, on the seismic velocity model and a geometry of the plurality of observed time-space waveforms, and updating, the seismic velocity model based, at least in part, on the synthetic seismic dataset, the plurality of predicted first arrivals and the plurality of observed time-space waveforms. (Abstract teaches “obtaining the seismic data set and an initial seismic velocity model, and determining an updated seismic velocity model based on the seismic data set.” Para. [0021] teaches “Processing a seismic data set comprises a sequence of steps designed, without limitation, to correct for near surface effects, attenuate noise, compensate of irregularities in the seismic survey geometry, calculate a seismic velocity model, image reflectors in the subsurface, calculate a plurality of seismic attributes.” Para. [0027] teaches “In accordance with one or more embodiments a method if picking arrival-times (202) of a first event (204) in a seismic data set (200) may be combined with a method for estimating the arrival-time (202) of a first event (204) in a simulated seismic data set calculated for a seismic velocity model to yield a result of adequate accuracy.” Para. [0031] teaches “In Block 304 the initial seismic velocity model is first assigned to be the current seismic velocity model. Later in the flow, the current seismic velocity model will be updated iteratively as part of the inversion.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Schaefer and Vinje with receiving a seismic velocity model of the subsurface region of interest; and generating an updated seismic velocity model iteratively, or recursively, until a stopping condition is reached, wherein generating the updated seismic velocity model comprises: generating a synthetic seismic dataset based, at least in part, on the seismic velocity model and a geometry of the plurality of observed time-space waveforms, and updating, the seismic velocity model based, at least in part, on the synthetic seismic dataset, the plurality of predicted first arrivals and the plurality of observed time-space waveforms such as that of Kim.
One of ordinary skill would have been motivated to modify the combination of Schaefer and Vinje, because updating the velocity model would ensure that the data maintains accuracy over time.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSHUA L FORRISTALL whose telephone number is 703-756-4554. The examiner can normally be reached Monday-Friday 8:30 AM- 5 PM.
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, Andrew Schechter can be reached on 571-272-2302. 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.
/JOSHUA L FORRISTALL/Examiner, Art Unit 2857
/LINA CORDERO/Primary Examiner, Art Unit 2857
Prosecution Insights