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 .
Claims 1-20 are pending and are examined on the merits. This action is a first action on the merits and is non-final.
Claim Objections
Claim 15-20 is/are objected to because of informalities. The examiner recommends the following changes.
Claim 15 is objected to because of the following informality: the preamble recites “A computer storage medium has computer-executable instructions that, upon execution by a processor, cause the processor to at least.” The verb “has” should be “having.” Appropriate correction is required.
Claims 16-20 depend either directly or indirectly from the objection of claim 15, therefore they are also objected.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim(s) 6, 7, 13, 18, and 19 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claim(s) 7 recites, as the third alternative, “generating a notification indicating significant change in the monitored boundaries of the forest in the geographic region." There is insufficient antecedent basis for “the monitored boundaries.” The only recitation of monitored boundaries appears in the second alternative of the same “at least one of” list. Because claim 7 is an "at least one of' recitation, each alternative must be independently electable. The third alternative is not: it presupposes that the boundaries are already being monitored, which occurs only if the second alternative has been performed first. It is therefore unclear whether the third alternative can be elected at all, and if it can, what boundaries it refers to.
Claim 7 is further indefinite for the term “significant change.” “Significant” is a relative term. No quantitative boundary is disclosed anywhere in the specification, and the disclosure compounds the ambiguity by describing the same concept as “substantial changes” elsewhere. The claim does not inform one of ordinary skill of the scope of the invention with reasonable certainty. Nautilus, Inc. v. Biosig Instruments, Inc., 572 U.S. 898 (2014); MPEP § 2173.05(b).
For purposes of the prior art rejection below, "significant change in the monitored boundaries" is treated as any detected change in the extent of the forest in the geographic region. MPEP § 2173.06(II).
Claim(s) 6, 13, and 19 each recite that classifying the vegetation and causing the recited action “are based on analyzing the obtained vegetation data.” Parent claim 1 recites causing the action “based on the vegetation being classified as a forest;” parent claim 8 recites classifying “using the plotted signature curve;” and parent claim 15 recites classifying “based on the comparison of the plotted signature curve to the ground truth signature curves.” It is unclear whether the recited analysis replaces the basis stated in the parent claim or supplements it. Clarification is required. For purposes of examination these claims are treated as adding the recited analysis to the basis stated in the parent claim.
Claim 18 recites “wherein classifying vegetation in the geographic region using the plotted signature curve includes.” There is insufficient antecedent basis for this limitation. Parent claim 15 does not recite classifying vegetation using the plotted signature curve; claim 15 recites classifying vegetation “based on the comparison of the plotted signature curve to the ground truth signature curves.” It is further unclear whether claim 18 is intended to replace the ground truth comparison of claim 15 with a trained model classification, or to add the trained model to it. Clarification is required. For purposes of examination, claim 18 is treated as further limiting the classification step of claim 15.
Appropriate correction is required.
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 invention is directed to an abstract idea without significantly more.
Claim 1 – Step 1.
Claim 1 recites a processor and a memory. The claim is directed to a machine, which is a statutory category. The analysis proceeds to Step 2A.
Claim 1 – Step 2A, Prong One.
The claim recites a judicial exception. Specifically:
(a) “generate vegetation index data points using the obtained vegetation image data” – the
specification defines the vegetation index as a ratio of spectral reflectance measurements computed per Equation 1 (Spec. ¶20). Computing that ratio is a mathematical calculation, within the mathematical concepts grouping. MPEP § 2106.04(a)(2)(I).
(b) “plot a signature curve associated with the geographic region using the generated vegetation index data points” – plotting values against time and fitting a curve to them is
an act that can be performed by a person with pen and paper, and is additionally a
mathematical operation, the specification disclosing Gaussian and polynomial fits (Spec. ¶45). It falls within the mental processes grouping and independently within mathematical concepts.
MPEP § 2106.04(a)(2)(III).
(c) “classify vegetation in the geographic region as a forest using the plotted signature curve” – reaching a classification by inspecting a curve is an observation, evaluation, and judgment, and is a mental process. The specification confirms this characterization, stating that plotting the patterns as signature curves “provides visual patterns that can be compared efficiently by humans and/or by trained ML models” (Spec. ¶17).
These limitations fall within the mathematical concepts and mental processes groupings
and are treated together as a single abstract idea. MPEP § 2106.04(II)(B).
Claim 1 – Step 2A, Prong Two.
The claim does not integrate the exception into a practical application. The additional elements are (i) the processor, (ii) the memory comprising computer program code, (iii) obtaining target coordinates, (iv) obtaining vegetation image data, and (v) causing a forest preservation action to be performed.
The processor and memory are recited at a high level of generality. The specification describes the processor as “any technology capable of executing logic or instructions” (Spec. ¶87) and lists smartphones, personal computers, set top boxes, gaming consoles, and
mainframes as suitable environments (Spec. ¶93). These amount to mere instructions to implement the exception on a computer and to use of a computer as a tool. MPEP § 2106.05(f).
Obtaining target coordinates and obtaining vegetation image data are data gathering necessary to perform the recited calculation, and are insignificant extra-solution activity. MPEP § 2106.05(g); Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354 (Fed. Cir. 2016).
“Cause a forest preservation action to be performed” is recited at the highest level of
generality. No particular action is recited, no particular machine is recited, no article is transformed, and no mechanism by which the action occurs is claimed. The limitation is functional result language appended to the classification step and amounts to a generic linkage of the exception to a field of use. MPEP § 2106.05(h). Dependent claim 7 confirms the point: the disclosed species of forest preservation action are generating a notification, scheduling monitoring, and generating a further notification, each of which terminates in the outputting of information. Contrast Example 46 of the Subject Matter Eligibility Examples, in which claim 2 was eligible because it recited transmitting a control signal to a feed dispenser and claim 3 because it recited operating a sorting gate; in each the information derived from the exception was used to take a particular recited action. Claim 1 recites no analogous action.
To the extent an improvement in classification accuracy is asserted, that improvement is
described only in the specification, at Spec ¶ 17, and no paragraph of the specification discloses a mechanism that produces it. The claim likewise recites no such mechanism. An asserted technological improvement must be reflected in the claim itself and must be examined rather than dismissed at a high level of generality. Ex parte Desjardins, Appeal No. 2024-000567 (PTAB Sept. 26, 2025) (Appeals Review Panel) (precedential); MPEP § 2106.05(a). Applicant is invited to identify, in the claim, the mechanism by which the recited classification accuracy is achieved.
The claim is directed to the abstract idea.
Claim 1 – Step 2B.
The claim does not amount to significantly more. The processor and memory were found above to be mere instructions to apply the exception, and that finding carries through to this step. The data gathering steps are reconsidered here and are well-understood, routine, and conventional. The Background states that satellite and remote sensing technologies are already deployed for the recited monitoring purpose, and the Detailed Description identifies Sentinel-2 imagery, GOOGLE EARTH Engine, planetary computers, and FARMVIBES.AI as existing sources of the claimed data. The disclosure establishes conventionality. MPEP § 2106.05(d)(I). Considered individually and as an ordered combination, the additional elements add nothing beyond generic computer implementation, conventional data acquisition, and a generically stated downstream action. Claim 1 is ineligible.
Claim 8.
Claim 8 is a process and satisfies Step 1. Claim 8 recites the same abstract idea in broader
form: generating vegetation index data points is a mathematical calculation; plotting a signature curve is a mental process and a mathematical operation; and classifying vegetation using the plotted signature curve is an evaluation and judgment. Claim 8 requires neither a forest classification nor image data, and “vegetation data” under the broadest reasonable interpretation encompasses data recorded by a human observer, so the entire body of claim 8 is capable of performance in the human mind with pen and paper. The only additional elements are obtaining vegetation data, which is data gathering under MPEP § 2106.05(g), and causing a vegetation management action to be performed, which is a generically recited result. The specification states that the vegetation management action “includes updating a GUI to display the vegetation classification,” which is the outputting of information. Collecting information, analyzing it, and displaying the results of the analysis is abstract, and merely presenting the results of the analysis adds nothing that takes the claim out of the exception. Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1353-54 (Fed. Cir. 2016). The claim does not use the classification to do anything further. Claim 8 recites no computer in its body and so cannot claim even the computer as a tool integration that claim 1 fails on. Claim 8 is ineligible under Step 2A, Prong Two and under Step 2B.
Claim 15.
A computer storage medium is an article of manufacture and satisfies Step 1. The specification expressly states at Spec ¶ 88 that a computer storage medium “is not a propagating signal,” so no non-statutory signal rejection is made. Claim 15 recites the same mathematical and mental process limitations and adds one more: “compare the plotted signature curve to ground truth signature curves.” Comparing a curve to a set of reference curves and selecting the closest match is an observation and evaluation performed in the human mind; the specification describes it in those terms, stating that “[t]he ground truth signature curve that is most similar to the plotted signature curve provides the most likely type of vegetation in the geographic region” (Spec. ¶ 75). The additional elements are the processor, the storage medium, obtaining satellite imagery data including near infrared light data, and causing a vegetation management action. The processor and medium are generic. Narrowing the source of the gathered data to satellite imagery does not change the character of the step; it remains data gathering and a field-of-use limitation. MPEP § 2106.05(g), (h). Acquisition of near infrared satellite imagery is conventional on the face of the disclosure. Claim 15 is ineligible.
Dependent claims.
Claims 2 and 9 add satellite imagery including near infrared light data. This narrows the source of gathered data only and remains insignificant extra-solution activity and a field-of-use limitation. MPEP § 2106.05(g), (h).
Claims 3, 10, and 16 specify NDVI. This narrows the mathematical concept itself and
does not add additional elements.
Claims 4, 11 , and 17 add identifying a coordinate set, calculating index values per
coordinate over a time period, and averaging. Averaging is a further mathematical
operation and the coordinate identification is further data gathering. No additional
element is added.
Claims 5, 12, and 18 add providing the curve to a trained model, generating a model
query, and the model generating classification output. The model is recited only by the
result it achieves. No architecture, no training operation, and no improvement to the model itself is claimed. Claims that do no more than apply generic machine learning to a new data environment, without disclosing improvements to the machine learning model to be applied, are ineligible. Recentive Analytics, Inc. v. Fox Corp., 134 F.4th 1205, 1211 (Fed. Cir. 2025). Compare Ex parte Desjardins, supra, where the claims were held eligible because they improved the functioning of the machine learning model itself. These claims apply a model; they do not improve one. MPEP § 2106.05(f).
Claims 6, 13, and 19 add analyzing the data using a cropland data layer data set or a wildfire historical data set. Consulting an additional data set is further data gathering and is insignificant extra-solution activity. MPEP § 2106.05(g). The result of the added analysis is applied to nothing beyond the same generically recited action already addressed above.
Claim 7 recites the forest preservation action as generating a notification, scheduling periodic monitoring, or generating a notification of change. Every alternative outputs information. None takes corrective action on a physical thing.
Claims 14 and 20 recite the vegetation management action as a fire notification, triggering a crop watering operation, triggering a crop fertilizing operation, or displaying a GUI. An “at least one of” recitation is satisfied by any single alternative, and the broadest reasonable interpretation encompasses displaying a GUI alone, which is ineligible for the reasons given for claim 7.
Claims 2-7, 9-14, and 16-20 are therefore 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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 8-10 and 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wolfson et al., US 2022/0391613 A1 (hereinafter “Wolfson”).
Claim 15.
Wolfson teaches a computer storage medium has computer-executable instructions that, upon execution by a processor, cause the processor to at least (Wolfson¶ 100: “The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.”; ¶ 101: the medium “is not to be construed as being transitory signals per se"; Wolfson's computer readable storage medium is a computer storage medium as claimed and is non-transitory.):
obtain vegetation data associated with a geographic region, wherein the vegetation data includes satellite imagery data of the geographic region, including near infrared light data (Wolfson ¶ 71: “planting date determination program 122 receives an aerial image of the area of interest from an optical Earth observation satellite such as Sentinel-2, MODIS, ASTER, or Landsat”; ¶ 28: the Sentinel-2 multi-spectral instrument has “four VNIR bands (i.e., blue at 490 nm, green at 560 nm, red at 665 nm, and near-infrared at 842 nm) at 10 m resolution”; Wolfson's “area of interest” is the claimed geographic region and the received Sentinel-2 imagery expressly includes a near infrared band.);
generate vegetation index data points using the obtained vegetation data (Wolfson ¶ 75: “In step 320, planting date determination program 122 calculates the Vegetation Index. In an embodiment, planting date determination program 122 calculates the NDVI of the crop(s) growing at the plurality of points captured in the one or more observed signatures.”; ¶ 11: “the Vegetation Index is selected from the group consisting of a Normalized Difference Vegetation Index and an Enhanced Vegetation Index”; FIG. 3 step 320.);
plot a signature curve associated with the geographic region using the generated vegetation index data points (Wolfson ¶ 76: “planting date determination program 122 plots the calculated Vegetation Index on a line graph ... Each line of the line graph represents the crop growing at one point of the plurality of points”; ¶ 77: “Planting date determination program 122 calculates the Vegetation Index of these crops and plots the calculated Vegetation Indices on the line graph."; ¶ 80: “planting date determination program 122 builds up the observed signature in the vector by increasing the length of the vector in storage for the season.”; ¶ 81: “The actual signature is a cumulative representation of the one or more observed signatures.”; the observed signature is accumulated as a vector of Vegetation Index values over the season and is plotted at ¶ 76 as a line of the line graph, so the plotted line is a signature curve associated with the area of interest.);
compare’ the plotted signature curve to ground truth signature curves (Wolfson ¶ 82: “planting date determination program 122 cross-correlates the actual signature against the plurality of historical reference signatures”; ¶ 69: “A historical reference signature is a datum of observation points of a known crop ... comprised of field data related to the crop type, including, but not limited to, historical benchmark curves and historical dates of planting acquired over past growing seasons”; ¶ 64: those curves “correspond to known crops with known plant dates” and are gathered “from maps produced by government agencies”; curves built from known crops and government agency maps are ground truth signature curves.);
classify vegetation in the geographic region based on the comparison of the plotted signature curve to the ground truth signature curves (Wolfson ¶ 84: “planting date determination program 122 ranks the products of the cross-correlation of the actual signature against the plurality of historical reference signatures to identify the crop growing in the area of interest. The highest ranked cross-correlation product (i.e., the historical reference signature that best matches the actual signature) is the crop determined to most likely be growing in the area of interest.”; identifying which crop is growing is classifying the vegetation, and it is done on the
basis of the comparison.); and
cause a vegetation management action to be performed in association with the geographic region based on the classified vegetation (Wolfson ¶ 89: “planting date determination program 122 outputs information on the identification of the winning crop and the estimated date of planting of the winning crop to the user through user interface 132 of user computing device 130."; the specification states that the vegetation management action "includes updating a GUI to display the vegetation classification," so outputting the classification to a user interface is a vegetation management action under the broadest reasonable interpretation supplied by applicant's disclosure.).
Wolfson plots the calculated Vegetation Index at ¶ 76 on a line graph in which “[e]ach line of the line graph represents the crop growing at one point of the plurality of points,” while the object cross-correlated at ¶ 82 is the actual signature of ¶ 81, and Wolfson does not state in terms that the plotted line is the object supplied to the cross-correlation. Supplying the plotted seasonal curve to the comparison step is on this record an obvious use of a known technique in a method ready for that improvement rather than an express disclosure.
It would have been obvious to one of ordinary skill in the art before the effective filing date to supply Wolfson’s plotted Vegetation Index curve to the comparison step. The line graph of ¶76 and the actual signature of ¶ 81 are formed from the same Vegetation index calculated at ¶ 75, and Wolfson already compares against “historical benchmark curves” ¶¶ 64, 69. Using the plotted curve rather than the underlying vector as the object of comparison is the use of a known technique, disclosed in Wolfson, to improve a method of the same reference that is ready for improvement, and gives the cleaner input because plotting “tunes out the noise between the plotted points in order. The modification is also the more reliable of the two, because Wolfson states that in plotting the curve the program “tunes out the noise between the plotted points in order to get fairly pure lines” ¶ 76. MPEP § 2143(I)(C). Success is expected because the modification requires no data or step Wolfson does not already perform.
Claim 8.
Wolfson teaches a computerized method comprising:
obtaining vegetation data associated with a geographic region (Wolfson ¶ 71: “planting date determination program 122 receives an aerial image of the area of interest from an optical Earth observation satellite such as Sentinel-2, MODIS, ASTER, or Landsat”; ¶ 60: the area of interest is “inputted into a control file by a user through user interface 132”);
generating vegetation index data points using the obtained vegetation data (Wolfson ¶ 75: “In step 320, planting date determination program 122 calculates the Vegetation Index. In an embodiment, planting date determination program 122 calculates the NDVI of the crop(s) growing at the plurality of points captured in the one or more observed signatures.”; ¶ 11);
plotting a signature curve associated with the geographic region using the generated vegetation index data points (Wolfson ¶ 76: “planting date determination program 122 plots the calculated Vegetation Index on a line graph ... Each line of the line graph represents the crop growing at one point of the plurality of points”; ¶ 77);
classifying vegetation in the geographic region using the plotted signature curve (Wolfson ¶ 84: “The highest ranked cross-correlation product (i.e., the historical reference signature that best matches the actual signature) is the crop determined to most likely be growing in the area of interest.”); and
causing a vegetation management action to be performed in association with the geographic region based on the classified vegetation (Wolfson ¶ 89: “planting date determination program 122 outputs information on the identification of the winning crop … to the user through user interface 132 of user computing device 130”).
Claim 9.
Wolfson teaches the computerized method of claim 8, wherein obtaining the vegetation data associated with the geographic region includes obtaining satellite imagery data of the geographic region, including near infrared light data (Wolfson ¶ 71; ¶ 28: the Sentinel-2 MSI includes a “near-infrared at 842 nm” band at 10 m resolution.).
Claim 10.
Wolfson teaches the computerized method of claim 9, wherein generating the vegetation index data points using the obtained vegetation data includes generating Normalized Difference Vegetation Index (NDVI) data points (Wolfson¶ 11: “the Vegetation Index is selected from the group consisting of a Normalized Difference Vegetation Index and an Enhanced Vegetation Index”; ¶ 39 gives the NDVI ratio of near-infrared to visible radiation.).
Claim 16.
Wolfson teaches the computer storage medium of claim 15, wherein generating the vegetation index data points using the obtained vegetation data includes generating Normalized Difference Vegetation Index (NDVI) data points (Wolfson¶ 11; ¶ 39.).
Claim Rejections - 35 USC § 103
Claims 1-3 and 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wolfson in view of Xiao et al., US 2022/0392215 A1 (hereinafter “Xiao”) and further in view of Khatami et al., US 2024/0035962 A1 (hereinafter “Khatami”).
Claim 1.
Wolfson teaches a system comprising:
a processor; and
a memory comprising computer program code, the memory and the computer program code configured to cause the processor to (Wolfson¶ 94: “Programs may be stored in persistent storage 408 and in memory 406 for execution and/or access by one or more of the respective computer processors 404 via cache 416.”; ¶ 93: “Memory 406 and persistent storage 408
are computer readable storage media.”):
obtain target coordinates (Wolfson ¶ 60: “historical reference signature building component 124 receives an area of interest inputted into a control file by a user through user interface 132 of user computing device 130”; ¶ 54: field data includes “geographic identifiers, boundary identifiers” and “geographic coordinates and boundaries” used “to identify farm land”; the user-supplied area of interest and its geographic coordinates are the claimed target coordinates);
obtain vegetation image data associated with a geographic region described by the obtained target coordinates (Wolfson ¶ 71: “planting date determination program 122 receives an aerial image of the area of interest from an optical Earth observation satellite such as Sentinel-2, MODIS, ASTER, or Landsat”; ¶ 28);
generate vegetation index data points using the obtained vegetation image data (Wolfson ¶ 75: “In step 320, planting date determination program 122 calculates the Vegetation Index ... calculates the NDVI of the crop(s) growing at the plurality of points captured in the one or more observed signatures.”; ¶ 11.);
plot a signature curve associated with the geographic region using the generated vegetation index data points (Wolfson ¶ 76: “planting date determination program 122 plots the calculated Vegetation Index on a line graph ... Each line of the line graph represents the crop growing at one point of the plurality of points”; ¶ 80: “planting date determination program 122 builds up the observed signature in the vector by increasing the length of the vector in storage for the season.”);
Wolfson does not teach classifying the vegetation in the geographic region as a forest; however, Xiao in the same field of endeavor teaches classifying a geographic region as forest from vegetation index values taken over time (Xiao ¶ 72: “the at least one land cover mask 200 may be determined via the plurality of vegetation indices as the evergreen land cover type 206 ... When a pixel has a frequency of 90% or higher with LSWI>0 and minimum EVI>0.2 in a year, the pixel is classified as the evergreen land cover type. A decision tree classification algorithm that uses time series constructed of LSWI and EVI data may be used to identify the evergreen land cover type 206.”; ¶ 68: “The evergreen land cover type 206 may be defined as a land cover mask associated with land having plants or plant cover including, but not limited to, forests, tree plantations, orchards, shrubs, combinations thereof, and the like.”; Xiao classifies a location as evergreen land cover, which it defines to include forests, on the basis of a time series of vegetation index values, which is the claimed classification of vegetation as a forest.)
Neither Wolfson nor Xiao teaches causing a forest preservation action to be performed; however, Khatami in the same field of endeavor teaches "cause a forest preservation action to be performed in association with the geographic region based on the vegetation being classified as a forest" (Khatami ¶ 27: “the program may continually monitor the subregions to detect changes to the forest cover. If a change is detected, the program may inform the subregion owner of the anomaly and ask for further assurances that the owner is maintaining the subregion in accordance with the program.”; ¶ 22: the landowner enrolls “land areas within defined boundaries” and “may be required to furnish evidence of compliance with continued maintenance of the forest of the land areas”; the continual monitoring of forested
land and the resulting notification are performed in order to maintain the forest, and are a forest preservation action.)
It would have been obvious to one of ordinary skill in the art before the effective
filing date to apply Wolfson's vegetation index signature analysis to the forest classification of Xiao and, on that classification, to perform the forest monitoring and notification of Khatami. Wolfson, Xiao, and Khatami are each directed to classifying land cover from satellite derived vegetation index values collected over a season, so the classification technique of one is a known technique applicable to the others. MPEP § 2143 (I)(C). Doing so makes forest monitoring faster and more objective, an advantage Khatami states for itself: “Efficient (e.g., automated) and objective approaches to monitoring the forest cover of enrolled land simplifies the process” ¶22, whereas “[t]ime-consuming human assessment limits the ability to
monitor forest change at large scale” ¶3. Success is expected because all three references operate on the same class of imagery and the same index quantities. KSR Int'l Co. v. Teleflex Inc., 550 U.S. 398 (2007).
Claim 2.
The combination of Wolfson, Xiao, and Khatami teaches the system of claim 1, wherein obtaining the vegetation image data associated with the geographic region includes obtaining satellite imagery data of the geographic region, including near infrared light data (Wolfson ¶
71; ¶ 28: the Sentinel-2 multi-spectral instrument has “four VNIR bands (i.e., blue at 490 nm, green at 560 nm, red at 665 nm, and near-infrared at 842 nm) at 10 m resolution”).
Claim 3.
The combination of Wolfson, Xiao, and Khatami teaches generating the vegetation index data points using the obtained vegetation image data includes generating Normalized Difference Vegetation Index (NDVI) data points (Wolfson ¶ 75: “planting date determination program 122 calculates the NDVI of the crop(s) growing at the plurality of points captured in the one or more observed signatures”; ¶ 11).
Claim 7.
The combination of Wolfson, Xiao, and Khatami teaches the forest preservation action includes at least one of the following: generating a notification indicating that a forest fire is in close proximity to the geographic region, scheduling periodic monitoring of boundaries of the forest in the geographic region, or generating a notification indicating significant change in the monitored boundaries of the forest in the geographic region (Khatami ¶ 7: “a method of monitoring forest cover is disclosed. The method includes, by a processor of an electronic device, receiving boundary information of a land area”; ¶ 27: “the program may continually monitor the subregions to detect changes to the forest cover”; the claim is an “at least one or” recitation, and Khatami's continual monitoring of a land area whose boundary information the system receives, repeated over successive image acquisitions, satisfies the second alternative of scheduling periodic monitoring of boundaries of the forest.).
Claim 4 is rejected under 35 U.S.C. § 103 as being unpatentable over Wolfson in view of Xiao, Khatami, and Brown US 2023/0091677 A1 (hereinafter “Brown”).
Claim 4 recites a "threshold" without a stated measurand or value. The term is broad rather than indefinite, and under the broadest reasonable interpretation it is treated as any bound that limits the identified coordinates to the region described by the target coordinates. MPEP § 2III.
Claim 4.
The system of claim 1, wherein generating vegetation index data points using the obtained vegetation image data includes: identifying a set of coordinates for which obtained vegetation image data exists, wherein the identified set of coordinates are within a threshold of the obtained target coordinates (Wolfson ¶ 72: “planting date determination program 122 selects a plurality of points across the area of interest”; ¶ 60: the area of interest is inputted into a control file by the user; the selected points lie within the bound of the user-supplied area of interest, which is the claimed threshold relative to the target coordinates.);
calculating vegetation index data points associated with the set of coordinates using the obtained vegetation image data, wherein vegetation index data points are calculated for each coordinate in the set of coordinates over a time period (Wolfson ¶ 75; ¶ 71.); and
Wolfson, Xiao, and Khatami do not teach generating average vegetation index data points; however, Brown in the same field of endeavor teaches the limitation (Brown ¶ 54: "generating a time series of average vegetation index values by averaging together all vegetation index values, for each time point in a range of time within the period of time, from all of the reconstructed time series of vegetation index values; and generating the crop growth curve based on the time series of average vegetation index values.”).
It would have been obvious to a person of ordinary skill in the art before the effective filing date to average the per-point Vegetation Index values of the Wolfson, Xiao, and Khatami combination as taught by Brown, for the reason given for claims 11 and 17 and for the further reason that the combination classifies a single geographic region as forest or non-forest, so a single averaged value per capture time is the form in which the region level classification input is needed. MPEP § 2143(1)(C). The motivation, benefit, and expectation of success are as set out for claims 11 and 17 below.
Claims 11 and 17 are rejected under 35 U.S.C. § 103 as being unpatentable over Wolfson in view of Brown et al., US 2023/0091677 A1 (hereinafter “Brown”).
Claims 11 and 17.
Wolfson teaches wherein generating vegetation index data points using the obtained vegetation data includes:
identifying a set of coordinates for which obtained vegetation data exists, wherein the identified set of coordinates is representative of the geographic region (Wolfson ¶ 72: “planting date determination program 122 selects a plurality of points across the area of interest. The number of points selected is dependent on the overall acreage of the area of interest ... Each point represents a sample of a crop growing in the area of interest.”);
calculating vegetation index data points associated with the set of coordinates using the obtained vegetation data, wherein vegetation index data points are calculated for each coordinate in the set of coordinates over a time period (Wolfson ¶ 75: the Vegetation Index is calculated for “the crop(s) growing at the plurality of points captured in the one or more observed signatures”; ¶ 71: images are received “at a predetermined interval of time, e.g., every five days for X number of days”); and
Wolfson does not teach generating average vegetation index data points; however, Brown in the same field of endeavor teaches “generating average vegetation index data points using the calculated vegetation index data points associated with the set of coordinates” and plotting the curve from those averages (Brown ¶ 54: “vegetation index data ... operation 208 comprises: generating a time series of average vegetation index values by averaging together all vegetation index values, for each time point in a range of time within the period of time, from all of the reconstructed time series of vegetation index values; and generating the crop growth curve based on the time series of average vegetation index values ... some embodiments can take, from a gap-filled and reconstructed time series of vegetation index values, all the daily pixel observations for each field and average them to create the time series for each field to eventually generate a crop growth curve ... for the farm field of interest.”; Brown averages the per-pixel vegetation index values at each time point across the season and generates the curve from those averages, which is the claimed generation of average vegetation index data points and the plotting of the signature curve using them.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to average Wolfson's per-point Vegetation Index values across the area of interest as taught by Brown, because Wolfson already computes an index value at each of a plurality of sample points in one area of interest over one season and already reduces those points to a single classification for the area as a whole (Wolfson ¶ 84, identifying one “winning crop” for the area of interest), so averaging the per-point values at each capture time is the application of a known technique to a method ready for that improvement. MPEP § 2143(I)(C). Averaging as Brown teaches it also yields a more complete curve. Brown states that because its gap filling is at the pixel level the method can “can avoid having to remove any pixels from each day (e.g., as being missing or cloudy)” ¶54, whereas Wolfson discards pixels affected by clouds and shadows (Wolfson ¶74). Success is expected because Brown averages the same quantity Wolfson computes.
Claims 12 and 18 are rejected under 35 U.S.C. § 103 as being unpatentable over Wolfson in view of Freitag et al., US 2018/0189564 A1 (hereinafter “Freitag”).
Claims 12 and 18.
Claims 12 and 18 recites that classifying vegetation in the geographic region using the plotted signature curve includes: providing the plotted signature curve to a trained model as input; generating a model query requesting classification of vegetation in the geographic region; and generating, by the trained model, vegetation classification output in response to the generated model query.
Wolfson does not teach these limitations in full; however, Wolfson contemplates a
machine learning classifier operating on its signature data (Wolfson ¶ 69: “The observation points from a plurality of historical reference signatures are used by the ML to identify the crop type grown in the area of interest.”) and Freitag in the same field of endeavor teaches “providing the plotted signature curve to a trained model as input; generating a model query requesting classification of vegetation in the geographic region; and generating, by the trained model, vegetation classification output in response to the generated model query” (Freitag ¶ 5: “generating a set of temporal sequences of vegetation indices having corresponding timestamps from the plurality of remote sensing measurements, wherein each temporal sequence is associated with a respective pixel location within a satellite image and a crop season ... training a classifier using a set of historical temporal sequences of vegetation indices with respect to the modified temporal variable as training features and corresponding historically known crop types as training labels, identifying at least one crop type for each pixel location within the satellite images using the trained classifier"; the temporal sequence of vegetation indices supplied to the trained classifier is the plotted signature curve of the parent claim, and the act of applying the trained classifier to that sequence to obtain a crop type is the generation of a model query and the return of a vegetation classification output.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to add the trained classifier of Freitag to the classification step of Wolfson. Wolfson at ¶ 69 already states that a machine learning component uses the observation points of its reference signatures to identify the crop type, but does not describe how that component is trained or applied; Freitag supplies these details for the same quantity, a temporal sequence of vegetation indices. MPEP § 2143(I)(G). The classifier is added to, and does not replace, Wolfson's cross-correlation, so Wolfson's phase angle and its resulting estimated date of planting (Wolfson ¶ 83, 88) are preserved and Wolfson remains suitable for its stated purpose. Adding the classifier also makes the identification more accurate, which is the advantage Freitag states for it, “The present invention advantageously provides a user a more accurate crop type identification and estimation of crop acreage based on satellite observation and weather data” ¶59. Success is expected because both references classify vegetation from a seasonal series of vegetation index values.
Claim 5 is rejected under 35 U.S.C. § 103 as being unpatentable over Wolfson in view of Xiao, Khatami, and Freitag.
Claim 5.
Claim 5 recites that classifying vegetation in the geographic region as a forest using the plotted signature curve includes: providing the plotted signature curve to a trained model as input; generating a model query requesting classification of vegetation in the geographic region; and generating, by the trained model, vegetation classification output in response to the generated model query.
The combination of Wolfson; Xiao, and Khatami does not teach these limitations in full; however, Freitag in the same field of endeavor teaches them (Freitag ¶ 5: “training a classifier using a set of historical temporal sequences of vegetation indices ... identifying at least one crop type for each pixel location within the satellite images using the trained classifier.”) Xiao supplies the forest classification that is the output of the model in claim 5, and does so with a trained classification model of the same kind (Xiao ¶ 72: “A decision tree classification algorithm that uses time series constructed of LSWI and EVI data may be used to identify the evergreen land cover type 206.”)
The motivation, benefit,
and the expectation of success are as set out for claims 12 and 18. MPEP § 2143(I)(G).
Claims 13 and 19 are rejected under 35 U.S.C. § 103 as being unpatentable over Wolfson in view of Melaas et al., US 2024/0257515 A1 (hereinafter “Melaas”).
Claims 13 and 19.
Claim 13 recites analyzing, and claim 19 recites that the computer-executable instructions cause the processor to at least analyze, the obtained vegetation data using at least one of a cropland data layer (CDL) data set or a wildfire historical data set, wherein classifying the vegetation in the geographic region and causing the vegetation management action to be performed are based on analyzing the obtained vegetation data.
Wolfson does not teach analysis using a cropland data layer data set; however, Melaas in the same field of endeavor teaches the limitation (Melaas ¶ 85: “an additional input to the cover crop prediction module includes the USDA Cropland Data Layer ('CDL'). CDL provides annual predictions of crop type, which can be used to alter the logic imposed for detecting cover crops on a calendar basis (e.g., winter wheat vs. corn). An additional input to the cover crop prediction module may also include median VI time series across all fields of a given crop type during a single year ... In some embodiments, the VI of the median time series profile is NDVI.”; ¶ 57: “Field-level zonal summary time series of crop type are generated, for example from the USDA Cropland Data Layer (CDL), which provides annual predictions of crop type.”; Melaas analyzes an NDVI time series together with the CDL, and the CDL analysis alters the determination the module reaches, so in Melaas the vegetation determination is based on the analysis using the CDL as the claim requires.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to analyze Wolfson's Vegetation Index data using the CDL as taught by Melaas. Wolfson’s classification turn on where in the season its index values fall. Applying the CDL to Wolfson’s index analysis is the combination of prior art elements according to known methods to yield the predictable result of a crop determination informed by a known crop type prior, and makes the determination reliable for crops of similar seasonal timing, which is the use Melaas states for the CDL, it is “used to alter the logic imposed for detecting cover crops on a calendar basis (e.g., winter wheat vs. corn)” ¶85. MPEP § 2143(I)(A). Success is expected because Melaas applies the CDL to NDVI time series of the same kind Wolfson computes.
Claim 6 is rejected under 35 U.S.C. § 103 as being unpatentable over Wolfson in view of Xiao, Khatami, and Melaas.
Claim 6.
Claim 6 recites that the memory and the computer program code are configured to further cause the processor to analyze the obtained vegetation image data using at least one of a cropland data layer (CDL) data set or a wildfire historical data set, wherein classifying the vegetation in the geographic region and causing the forest preservation action to be performed are based on analyzing the obtained vegetation image data.
The combination of Wolfson, Xiao, and Khatami does not teach analysis using a cropland data layer data set; however, Melaas in the same field of endeavor teaches it (Melaas ¶ 85: "an additional input to the cover crop prediction module includes the USDA Cropland Data Layer ('CDL'). CDL provides annual predictions of crop type, which can be used to alter the logic imposed for detecting cover crops on a calendar basis"; ¶ 57.)
It would have been obvious to one ordinary skill in the art before the effective filing date to analyze the vegetation image data of the combination using the CDL as taught by Melaas. Xiao classifies a region as forest by excluding the locations that are water-related, non-vegetated, or cropland (Xiao ¶ 57), so a data set of annual crop type predictions is directly probative of which locations are cropland and, by exclusion, which are forest. Applying the CDL to that determination is the combination of prior art elements according to known methods to yield a predictable result, and makes the forest determination more reliable for the reasons given for claims 13 and 19. MPEP § 2143(I)(A). Success is expected because CDL is a raster on the same geographic grid the combination already processes.
Claims 14 and 20 are rejected under 35 U.S.C. § 103 as being unpatentable over Wolfson in view of Brown.
Claims 14 and 20.
Claim 14 / claim 20 recites that the vegetation management action includes at least one of the following: generating a notification indicating that a forest fire is in close proximity to the geographic region, triggering a crop watering operation to be performed in the geographic region, triggering a crop fertilizing operation to be performed in the geographic region, or displaying a graphical user interface (GUI) of the geographic region including an indication of a vegetation type within the geographic region.
Wolfson does not teach any of the recited alternatives; however, Brown in the same field of endeavor teaches “displaying a graphical user interface (GUI) of the geographic region including an indication of a vegetation type within the geographic region” (Brown ¶ 74: “a region map 604 with boundaries displayed can be presented to the user and, through the region map 604, the user can view multiple farm fields/crops in a mesoregion and click on (e.g., select) on their farm field of interest”; ¶ 43: the system provides “in-season crop identification, which can generate an in-season crop map for different types of crop, such as maize, wheat or soybean”; ¶ 56: the processor “causes presentation of the crop growth band ... and the crop growth curve ... on a client user interface (e.g., graphical user interface)”; the claim is an “at least one of” recitation, and Brown's displayed region map bearing an in-season crop map identifying the crop type present satisfies the fourth alternative.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to display the classification result of Wolfson on a region map as taught by Brown, because Wolfson already outputs the identified crop to a user interface (Wolfson ¶ 89; ¶ 57). This is the combination of prior art elements according to known methods to yield the predictable result of a map-based presentation of the classification, and is the more useful presentation because Brown states its map interface can “permit the user to monitor the progress of one or more fields of interest” ¶ 33. MPEP § 2143(I)(A). Success is expected because both references present index-derived crop determinations through a graphical user interface.
Conclusion
The prior art made of record but not relied, yet considered pertinent to the applicant’s disclosure, are Xian et al. (US 2021/0019522 A1) at ¶ 5 teaches summing pixel distribution signals across a growing season into a temporal representation of a management zone, ingesting it into a recurrent neural network to predict crop type, and transmitting a notification of the prediction to the grower. Gao et al. (WO 2023/108213 A1) teaches aggregating pixel-level NDVI time series to a field-level representative value for classification. All references cited in this action, whether relied upon or not, are listed on the accompanying PTO-892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Ross Varndell whose telephone number is (571)270-1922. The examiner can normally be reached M-F, 9-5 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, O’Neal Mistry can be reached at (313)446-4912. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Ross Varndell/Primary Examiner, Art Unit 2674
Prosecution Insights