NON-FINAL REJECTION, THIRD DETAILED ACTION
Status of Prosecution
The present application 17/948,362, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
The application was filed in the Office on September 20, 2022 and claims priority to Chinese application CN202210451977.X, which was filed on April 27, 2022.
The Office mailed a non-final rejection on August 12, 2025.
Applicant filed amendments and remarks and arguments on November 11, 2025.
The Office mailed a final rejection on Dec. 5, 2025.
Applicant filed an after final request with amendments and remarks and arguments on Feb. 4, 2026. The Office mailed an advisory action on Feb. 20, 2026.
Applicant filed a request for continued examination on March 4, 2026.
Claims 1-7, and 9-11 are pending and are all rejected in this rejection. Claim 8 is canceled. Claim 1 is the sole independent claim.
Status of Claims
Claims 1, 9-11 are rejected under 35 USC § 103 as being unpatentable over non-patent literature Jacquemoud et al. (“Jacquemoud”), “PROSPECT+SAIL models: A review of use for vegetation characterization,” published 2009 in view of non-patent literature Chen et al. (“Chen”), “Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery,” published August 2018.
Claims 2-5 are rejected under 35 USC § 103 as being unpatentable over non-patent literature Jacquemoud et al. (“Jacquemoud”), “PROSPECT+SAIL models: A review of use for vegetation characterization,” published 2009 in view of non-patent literature Chen et al. (“Chen”), “Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery,” published August 2018 in view of non-patent literature Verhoef, “Light Scattering by Leaf Layers with Application to Canopy Reflectance Modeling: The SAIL Model, published in 1984 in view of non-patent literature Taniguchi et al. (“Taniguchi”), “Derivation and approximation of soil isoline equations in the red–near-infrared reflectance subspace,” published June 3, 2014 and in further view of non-patent literature de Sá et al., (“de Sá”), “Exploring the Impact of Noise on Hybrid Inversion of PROSAIL RTM on Sentinel-2 Data,” published Feb. 11, 2021.
Claim 6 is rejected under 35 USC § 103 as being unpatentable over non-patent literature Jacquemoud et al. (“Jacquemoud”), “PROSPECT+SAIL models: A review of use for vegetation characterization,” published 2009 in view of non-patent literature Chen et al. (“Chen”), “Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery,” published August 2018 in view of non-patent literature Jacquemond et al., (“Jacquemond 1990”), “PROPSECT: A Model of Leaf Optical Properties Spectra” published 1990.
Claim 7 is rejected under 35 USC § 103 as being unpatentable over non-patent literature Jacquemoud et al. (“Jacquemoud”), “PROSPECT+SAIL models: A review of use for vegetation characterization,” published 2009 in view of non-patent literature Chen et al. (“Chen”), “Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery,” published August 2018 in view of non-patent literature Jacquemond et al., (“Jacquemond 1990”), “PROPSECT: A Model of Leaf Optical Properties Spectra” published 1990 in further view of non-patent literature Salam et al. (“Salam”), “A comparison of activation functions in multilayer neural network for predicting the production and consumption of electricity power,” published February 2021.
Claim 8 is canceled.
Request for Continued Examination
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on March 4, 2026 has been entered.
Response to Remarks and Arguments
Examiner thanks Applicant for the remarks and arguments submitted.
Regarding the § 103 rejection has newly rejected the claims as noted below. Examiner has maintained the grounds for claim 1. Applicant contends that the reference Jacquemond fails to teach the technical feature of the remote sensing data is of vegetation leaves (Remarks: pp. 8-9). Examiner respectfully disagrees. While the last Office action noted that that the remot sensing data dealt with “Earth” reflection, that was a generalization for different reflected values including vegetation as disclosed by Jacquemond (Jacquemoud: Sec. 3, sensors measure the Earth’s radiance and that data is fed into a SAIL model; Abstract the canopy spectral and directional reflectance (i.e. data of the vegetation leaves)). Examiner is not persuaded by the arguments.
The claims stand rejected.
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 of this title, 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.
A.
Claims 1, 9-11 are rejected under 35 USC § 103 as being unpatentable over non-patent literature Jacquemoud et al. (“Jacquemoud”), “PROSPECT+SAIL models: A review of use for vegetation characterization,” published 2009 in view of non-patent literature Chen et al. (“Chen”), “Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery,” published August 2018.
As to Claim 1, Jacquemoud teaches: An apparatus for inverting parameters of vegetation leaves based on remote sensing, comprising:
an input module, configured to input remote sensing data of the vegetation leaves to a SAIL-Net sub-network (Jacquemoud: Sec. 3, sensors measure the Earth’s radiance and that data is fed into a SAIL model; Abstract the canopy spectral and directional reflectance (i.e. data of the vegetation leaves));
the SAIL-Net network, configured to obtain a reflectivity and a transmittance of the vegetation leaves based on the remote sensing data and output the reflectivity and the transmittance of the vegetation leaves (Jacquemoud: Sec. 3 leaf reflectance and transmittance are three wavelength-dependent input variables of SAIL);
a PROSPECT-Net network, configured to obtain parameters of the vegetation leaves based on the reflectivity and the transmittance (Jacquemoud: Sec. 2; at the leaf level, PROSPECT pioneered the simulation of directional hemispherical reflectance and transmittance) and
an output module, configured to output the parameters of the vegetation leaves, (Jacquemoud: sec. 1, generally the models deal with leaf properties), wherein the parameters of the vegetation leaves comprise a leaf structure parameter N, a dry matter parameter Cm, a leaf equivalent water content thickness parameter C, and a chlorophyll a+b concentration parameter Cab of the vegetation leaves (Jacquemond: each of these parameters are noted in Table 1).
Jacquemoud may not explicitly state or disclose: that the SAIL and PROSPECT networks are sub-networks. Jacquemoud does discuss the coupling of the PROPSECT and the use of machine learning techniques such as artificial neural networks to operationally invert models (Jacquemoud: Fig. 2 depicts the coupling of the PROSAIL model between PROSPECT and SAIL; sec. 7.2 discusses the use of machine learning techniques). Examiner asserts that a person having ordinary skill in the art would have understood and implemented the coupling of the two different models in their networks as “sub-networks.”
PNG
media_image1.png
526
570
media_image1.png
Greyscale
Such a person would have been motivated to do so with a reasonable expectation of success to allow for the realization of the benefits of higher computational speeds in receiving the outputs thereof (Jacquemoud: sec. 7.2).
Jacquemoud further teaches: wherein the SAIL-Net sub-network and the PROSPECT-Net sub-network form a PROSAIL-Net network (Jacquemoud: Abstract, the SAIL And PROSPECT models are combined to form the PROSAIL model).
Jacquemoud may not explicitly teach: the back propagation comprises: calculating an error of each of layers of the PROSAIL-Net network, calculating an error gradient based on the error of each of the layers, and updating weights based on the error gradient.
Chen teaches in general concepts related to utilizing Sentinel imagery for estimation of above-ground forest biomass using machine learning algorithms (Chen: Abstract). Specifically, Chen teaches that backpropagation techniques using iterative descent algorithms to minimize errors for a multi-layer perception neural network is used (Chen: Sec. 3.2.1).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the application to have modified the Jacquemoud disclosures and teachings by implementing a backpropagation technique with gradient descent algorithm as taught by Chen. Such a person would have been motivated to do so with a reasonable expectation of success to allow for the better minimization of errors in the neural network.
As to Claim 9, Jacquemoud and Chen teach: A method for inverting parameters of vegetation leaves based on remote sensing, comprising:
obtaining remote sensing data of the vegetation leaves (Jacquemoud: section 1, introduction, remote sensing data is acquired); and
obtaining inversion parameters of the vegetation leaves based on the a PROSAIL-Net network according to claim 1 and the remote sensing data (see claim 1).
As to Claim 10, Jacquemoud and Chen teach: An electronic device, comprising: a memory, storing a program; and a processor, configured to execute the program to perform the method for inverting parameters of vegetation leaves based on remote sensing according to claim 9 (See Claim 9, Examiner also notes that machine learning as discussed include discussion of machines and computational speeds for instance, which are suggestive of electronic devices with conventional memory, processors).
As to Claim 11, Jacquemoud and Chen teach: A readable storage medium storing a computer program, wherein the computer program, when executed by a processor, causes the processor to perform the method for inverting parameters of vegetation leaves based on remote sensing according to claim 9(See Claim 9, Examiner also notes that machine learning as discussed include discussion of machines and computational speeds for instance, which are suggestive of electronic devices with conventional memory, processors).
B.
Claims 2-5 are rejected under 35 USC § 103 as being unpatentable over non-patent literature Jacquemoud et al. (“Jacquemoud”), “PROSPECT+SAIL models: A review of use for vegetation characterization,” published 2009 in view of non-patent literature Chen et al. (“Chen”), “Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery,” published August 2018 in view of non-patent literature Verhoef, “Light Scattering by Leaf Layers with Application to Canopy Reflectance Modeling: The SAIL Model, published in 1984 in view of non-patent literature Taniguchi et al. (“Taniguchi”), “Derivation and approximation of soil isoline equations in the red–near-infrared reflectance subspace,” published June 3, 2014 and in further view of non-patent literature de Sá et al., (“de Sá”), “Exploring the Impact of Noise on Hybrid Inversion of PROSAIL RTM on Sentinel-2 Data,” published Feb. 11, 2021.
As to Claim 2, Jacquemoud and Chen teach the elements of claim 1.
Jacquemoud further teaches: wherein the SAIL-Net sub-network comprises:
a first module, configured to perform an inverse process of an SAIL model for solving the reflectivity based on the remote sensing data (Jacquemoud: Sec. 7, “The remote sensing inverse problem is critical when the radiometric signal has to be interpreted in terms of canopy biophysical characteristics.”);
a second module, configured to perform an inverse process of the SAIL model for solving a bidirectional reflection parameter r, and a directional reflection parameter ro of a diffuse reflection (Jacquemoud: section 3, bidirectional parameter reflectance ρc, table 1, SKYL is a parameter of a ratio of diffuse to total incident radiation);
a seventh module, configured to perform an inverse process of the SAIL model for solving the reflectivity and the transmittance of the vegetation leaves (Jacquemoud: section 2, At the leaf level, PROSPECT pioneered the simulation of directional–hemispherical reflectance and transmittance).
Jacquemoud and Chen may not explicitly teach: a third module, configured to perform an inverse process of the SAIL model for solving a first coefficient;
a fourth module, configured to perform an inverse process of the SAIL model for solving an extinction coefficient and a scattering coefficient.
Verhoef is a journal article discussing scattering the derivation of the scattering and extinction coefficients of the SAIL model (Verhoef: Abstract). Verhoef discloses calculations to determine these coefficient values (Verhoef: Section 4, extinction, section 5, scattering).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the application to have modified the Jacquemoud-Chen disclosures and teachings by calculating various coefficients necessary for canopy inverse understanding. Such a person would have been motivated to do so with a reasonable expectation of success to better project the vegetation cover for particular coefficients related to the canopy layer.
Jacquemoud, Chen and Verhoef may not explicitly teach: a fifth module, configured to perform an inverse process of the SAIL model for solving a singular point.
Taniguchi teaches in general concepts related to derivation of an expression for the relationship between red and near-infrared reflectances, called soil isolines (Taniguchi: Abstract). Specifically, the soil isolines often contain a singular point on a dark soil background, which are difficult to model using polynomial forms (Taniguchi: Abstract). The PROSAIL model is used for its inversion process in conjunction (Taniguchi: p. 2, the reflectance spectrum is simulated using PROSAIL, which is then used for the modeling of the soil isolines).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the application to have modified the Jacquemoud—Chen-Verhoef disclosures and teachings by consolidating the steps for the analysis of the singular points as taught and suggested by Taniguchi. Such a person would have been motivated to do so with a reasonable expectation of success to better model and understand the vegetation conditions, including the difficult-to-model soil isolines.
Jacquemoud, Chen Verhoef and Taniguchi may not explicitly teach: a sixth module, configured to perform an inverse process of the SAIL model for solving a hot spot.
de Sá teaches in general concepts related to a hybrid approach of retrieving biophysical variables using remote sensing and combining it with machine learning algorithms (de Sá: Abstract). Specifically, de Sá teaches that the hot spot parameter of SAIL is an input one and that inversion of that data may be done with the hybrid approach (de Sá: Table 1 parameter, Sec. 2.6, RTM inversion).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the application to have modified the Jacquemoud-Chen-Verhoef-Taniguchi disclosures and teachings by including the hot spot parameter as an inversion parameter to be solved as well as taught by de Sá. Such a person would have been motivated to do so with a reasonable expectation of success to also solve for this parameter.
As to Claim 3, Jacquemoud, Chen Verhoef, Taniguchi and de Sá to claim 2,
de Sá as combined further teaches and suggests: wherein the first module comprises a convolution layer and a ReLU layer;
the second module comprises a transposed convolution layer and a ReLU layer;
the third module comprises a convolution layer and a ReLU layer;
the fourth module comprises a convolution layer and a ReLU layer;
the fifth module comprises a convolution layer and a ReLU layer;
the sixth module comprises a convolution layer and a ReLU layer; and
the seventh module comprises a maximum pooling layer, a convolution layer, and a ReLU layer (de Sá: Table 2, ReLu layers are used; Sec. 2.7, Fig. 2 spectral convolution is used).
As to Claim 4, Jacquemoud, Chen Verhoef, Taniguchi and de Sá to claim 3,
de Sá as combined further teaches and suggests: wherein data outputted from the first module is inputted to the second module;
data outputted from the second module is inputted to the third module and the fifth module; and
data outputted from the third module is inputted to the fourth module and the sixth module (Examiner notes that each of these modules may be interchangeably coupled per de Sá’s RTM inversion hybrid process).
As to Claim 5, Jacquemoud, Chen, Verhoef, Taniguchi and de Sá to claim 4.
Jacquemoud as combined further teaches and suggests: wherein the SAIL-Net sub-network further comprises:
a splicing module, configured to splice data outputted from the fourth module, data outputted from the fifth module and data outputted from the sixth module, and input spliced data to the seventh module (Jacquemoud: Fig. 4, different combinations of different input variables may be used to determine effects on the model development and inversion).
C.
Claim 6 is rejected under 35 USC § 103 as being unpatentable over non-patent literature Jacquemoud et al. (“Jacquemoud”), “PROSPECT+SAIL models: A review of use for vegetation characterization,” published 2009 in view of non-patent literature Chen et al. (“Chen”), “Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery,” published August 2018 and in view of non-patent literature Jacquemond et al., (“Jacquemond 1990”), “PROPSECT: A Model of Leaf Optical Properties Spectra” published 1990.
As to Claim 6, Jacquemoud and Chen teach the elements of claim 1.
Jacquemoud further teaches: an eleventh layer, configured to perform an inverse process of the PROSPECT model for solving parameters N, Cm, C, and Cab of the vegetation leaves (Jacquemoud: Sec. 2; at the leaf level, PROSPECT pioneered the simulation of directional hemispherical reflectance and transmittance).
Jacquemond may not explicitly teach: wherein the PROSPECT-Net sub-network comprises:
an eighth layer, configured to perform an inverse process of a PROSPECT model for solving a transmittance and a refractive index of the vegetation leaves in a case of N ≠ 1;
a ninth layer, configured to perform an inverse process of the PROSPECT model for solving a transmittance ρa and a refractive index ra of the vegetation leaves in a case of N= 1;
a tenth layer, configured to perform an inverse process of the PROSPECT model for solving a transmission coefficient θ; and
Jacquemond 1990 is the original PROSPECT paper detailing the model and inversion calculations that may take place. Specifically, Jacquemond 1990 notes the same equations recited in the Specification for the instances of N=1 and N ≠ 1, as claimed in the eight and ninth layers of the instant claim (Jacquemond 1990: eqs. 1, 2, and 7, 8, which are the resulting ones from the conditions of the leaf structure). The transmittance coefficient is also discussed as a parameter in the equations 1 and 2 (Jacqemond: 1990: p. 77).
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the application to have modified the Jacquemond-Chen disclosures and teachings by allowing for the inversion processes for the conditions and solving for the values as taught by Jacquemond 1990. Such a person would have been motivated to do so with a reasonable expectation of success to do so, recognizing that the Jacquemond 1990 reference is the basis for the later-Jacqeumond reference, inter alia.
D.
Claim 7 is rejected under 35 USC § 103 as being unpatentable over non-patent literature Jacquemoud et al. (“Jacquemoud”), “PROSPECT+SAIL models: A review of use for vegetation characterization,” published 2009 in view of non-patent literature Chen et al. (“Chen”), “Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery,” published August 2018 in view of non-patent literature Jacquemond et al., (“Jacquemond 1990”), “PROPSECT: A Model of Leaf Optical Properties Spectra” published 1990 in further view of non-patent literature Salam et al. (“Salam”), “A comparison of activation functions in multilayer neural network for predicting the production and consumption of electricity power,” published February 2021.
As to Claim 7, Jacquemoud, Chen and Jacquemond 1990 teach the elements of claim 6.
Jacquemoud, Chen and Jacquemond 1990 may not explicitly teach: wherein each of the eighth layer, the ninth layer, the tenth layer and the eleventh layer comprises a fully connected layer and a LeakReLU layer.
Salam is a research paper focused on predicting electricity power using multilayer neural network models (Salam: Abstract). Of interest is the different acvitation functions used with the models (Salam: Abstract). Rectified linear unit (ReLU is defined as a simple and fast activation function that “rectifies vanishing gradient problem” (Salam: sec. 2). A Leak rectified linear unit activation function (LeakReLU) is similar to ReLU with only a difference that addresses the problem of “dead neurons” in ReLU.
It would have been obvious to a person having ordinary skill in the art at a time before the effective filing date of the application to have modified the Jacquemond-Chen-Jacquemond- 1990 disclosures and teachings by utilizing the LReLU activation function as taught by Salam. Such a person would have been motivated to do so with a reasonable expectation of success as a choice for an activation problem that allows for some activation at low x values allowing for better model results.
Conclusion
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAMES T TSAI whose telephone number is (571)270-3916. The examiner can normally be reached M-F 8-5 Eastern.
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, Viker Lamardo can be reached on 571-270-5871. 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.
/JAMES T TSAI/ Primary Examiner, Art Unit 2147