DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 3/20/2026 has been entered.
Claims 1, 3-9, 11-14, 16-17, 19-20 have been presented for examination based on the application filed on 3/20/2026.
Claims 2, 10, 15 and 18 are cancelled.
Claims 1, 9, and 17 are amended.
Rejections under 35 USC 101 are WITHDRAWN in view claim amendment and applicant’s persuasive remarks on Pgs. 8-9.
Rejections under 35 USC 112(a), in view of claimed interpretation, are WITHDRAWN based on applicant’s persuasive remarks on Pgs. 7 and the amendments.
Claim(s) 1, 3-9, 11-14,16-17, 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over US PGPUB No. US 20220074994 A1 by Senn; Melanie et al., in view of US PGPUB No. US 20220067249 A1 by Steingrimsson; Baldur Andrew, further in view of US PGPUB No. US 20200321080 A1 by RAVIKUMAR; Bharath et al.
This action is made Non-Final.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1, 3-9, 11-14, 16-17, 19-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Senn’s deficiency about molecular dynamics simulation and trajectories is complemented by Steingrimsson specifically teaching molecular dynamics simulation as LAMMPS simulation (as mapped in [0405]-[0408]). This is also mapped in new secondary art Ravikumar ([0074]-[0075], [0110]-[0123]).
The reranking aspect is further complemented in Ravikumar in Figs.6, 2A-B, [0030], [0044], [0108] ranking, reranking as repeating in [0063]; [0110]-[0132] showing progressive at 2 ps trajectory evaluation and property determination/ranking.
Although Dynamic resource management is taught in Senn as mapped now, Dynamic resource management in LAMMPS simulation, which is a parallel simulation, shown in Steingrimsson and Ravikumar would enable starting and stopping simulation individually of parallel resources as inherent with any parallel computation.
Examiner respectfully finds applicant arguments unpersuasive and maintains the rejection under the new grounds.
---- This page is left blank after this line ----
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claim(s) 1, 3-9, 11-14,16-17, 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over US PGPUB No. US 20220074994 A1 by Senn; Melanie et al., in view of US PGPUB No. US 20220067249 A1 by Steingrimsson; Baldur Andrew, further in view of US PGPUB No. US 20200321080 A1 by RAVIKUMAR; Bharath et al.
Regarding Claims 1 & 9 (Updated 6/12/2026)
Senn teaches (Claim 1) A method of closed loop simulation for accelerated material discovery (Senn: Fig.2 & [0031] and Fig.8 & [0065]-[0070]) , comprising:/
(Claim 9) A non-transitory computer-readable medium having program code recorded thereon (Senn : [0075]-[0076] medium and [0079] & [0085] program instructions) for compositional feature representation learning of closed loop simulation for accelerated material discovery (Senn: Fig.2 & [0031] and Fig.8 & [0065]-[0070]), the program code being executed by a processor (Senn: [0072]-[0073]) and comprising:
ranking a plurality of candidate systems according to corresponding properties of interest predicted by a first prediction model (Senn: Fig.2 AI model 200 as first prediction model; ranking in [0061] "... All candidates of the multiple screening studies are ranked by their uncertainty and the top (most uncertain) N=1000 candidates are selected for execution in the simulation tools. ..."; [0069] "... Thus, millions of candidates can be screened, and the promising candidates selected from that original list of material combinations. The selection is implemented with priority queues which are data structures that contain an array most promising candidates sorted by their priority....") ; simulating a first top-N of the plurality of candidate systems according to the corresponding properties of interest predicted by the first prediction model (Senn: Fig.2 AI model 200 running first simulation; [0061] "... All candidates of the multiple screening studies are ranked by their uncertainty and the top (most uncertain) N=1000 candidates are selected for execution in the simulation tools. ..."; [0023]) ;
re-ranking the plurality of candidate systems according to the corresponding properties of interest predicted by a second prediction model (Senn: [0069] & [0061] showing ranking process being iterative as in [0067] "...An iterative process can be undertaken by determining whether the selected battery microstructures meet defined energy profiles 74. If not, then the entire microstructure candidates can be omitted and a new microstructure can be proposed until one or more microstructure are found. ..."; Fig.2 and Fig.8) based on an input of available trajectory data1 (Senn : trajectories are related to coordinates of individual atoms involved in simulation – which is taught in Senn as cell data [0022]-[0063]-[0064] which evolves based on their uncertainty; [0033] "... [0033] Accordingly, simple AI models can be used for screening (e.g. optimize average particle size) and the complex AI models can be used for design (e.g. optimize each particle's size and location). As such, the simple and complex AI models for microstructure property prediction can be independent from each other in this embodiment....") of a material's partial progression during the simulating of the first top-N (Senn: [0023] "... The model uncertainty can be used to efficiently create new simulation data samples for incremental model improvements...."- as partial progression; [0061]-[0067] ) , wherein the available trajectory data comprises a dataset collection of the coordinates and the evolution in time (Senn : trajectories are related to coordinates of individual atoms involved in simulation – which is taught in Senn as cell data [0022]-[0063]-[0064] which evolves based on their uncertainty; [0033]); and simulating a second top-N of the plurality of candidate systems according to the corresponding properties of interest predicted by the second prediction model (Senn: [0061] "... All candidates of the multiple screening studies are ranked by their uncertainty and the top (most uncertain) N=1000 candidates are selected for execution in the simulation tools. ..."; Simulating second top-N of the plurality of candidates can also be considered as duplication of process for second top-N of candidates (as this is an iterative evaluation method if one set fails as shown in [0067]"... the entire microstructure candidates can be omitted and a new microstructure can be proposed until one or more microstructure are found...."); Alternately, Second simulation being the detailed simulation as shown in Fig.2 complex AI model 300); and starting, stopping, pausing, or resuming computer resources for the simulating based on the re- ranking of the plurality of candidate systems based on an input of available trajectory data of a material's partial progression (Senn : eliminating and selecting new microstructure for simulation in reassigning and reprioritizing [0067] "... [0067] An iterative process can be undertaken by determining whether the selected battery microstructures meet defined energy profiles 74. If not, then the entire microstructure candidates can be omitted [first top-N] and a new microstructure can be proposed [second top-N] until one or more microstructure are found. I..."; [0070] next sample; [0027] reprioritization/ reassignment as changing the weights, or selection of top candidates for simulation that means it takes away resources from non-selected candidates as in [0061], [0067]) during the simulating of the second top-N (Senn: [0067] "... [0067] An iterative process can be undertaken by determining whether the selected battery microstructures meet defined energy profiles 74. If not, then the entire microstructure candidates can be omitted and a new microstructure can be proposed until one or more microstructure are found. ..." shows that the entire new (second top-N) can be iteratively simulated [0062] "... [0062] The incremental model improvement workflow starts from the initial simulation data set [starting] . First, models are trained and evaluated by their uncertainty. The difficult candidates are run with the simulation tools and the models are retrained for improvement based on the incremental data. Then, the retrained models are again evaluated by their uncertainty [stopping and restarting with incremental data] . This iterative improvement is continued until the uncertainty does not improve (decrease) significantly any more...." ; Alternately, taking second top-N set can also considered as duplication of process).
Senn does not specifically teach newly amended limitation of executing, by a molecular dynamics simulation cluster that runs parallel molecular dynamics simulations, the simulating of the first top-N to generate, as immediate simulation results, collections of coordinates of individual atoms involved in the simulating and an evolution in time of the coordinates; and wherein the available trajectory data comprises a dataset collection of the coordinates and the evolution in time.
Steingrimsson teaches executing, by a molecular dynamics simulation cluster that runs parallel molecular dynamics simulations, the simulating of the first top-N to generate (Steingrimsson: [0451] & Table 6 accounts for using molecular dynamics simulation as LAMMPS simulation which is known to include to predict polymer properties like diffusion [0405]-[0408]), as immediate simulation results, collections of coordinates of individual atoms involved in the simulating and an evolution in time of the coordinates2 (Steingrimsson: [0406] "... [0406] As most classical molecular dynamics simulators, LAMMPS requires the initial positions of the particles as input, LAMMPS can automatically generate initial positions for simple crystals or accept data files provided by user for materials with complex atomic structures. When provided with initial positions and velocities of the particles together with corresponding interatomic potentials, LAMMPS can simulate a wide variety of materials. While simulating a given material, LAMMPS can utilize statistical mechanics to convert atomic trajectories into macroscopic properties such as temperature, volume, pressure and density. LAMMPS can allow the user to specify which properties are desired as outputs....") ; and wherein the available trajectory data comprises a dataset collection of the coordinates and the evolution in time (Steingrimsson: [0406]).
Although Senn and Steingrimsson discuss trajectories (Senn: [0022], [0063]-[0064]; Steingrimsson: [0406]), they do not explicitly teach collections of coordinates of individual atoms involved in the simulating and an evolution in time of the coordinates.
Ravikumar teaches executing, by a molecular dynamics simulation cluster that runs parallel molecular dynamics simulations (Ravikumar: [0074]-[0075] molecular dynamics simulation as LAMMPS simulation; [0110]) , the simulating of the first top-N to generate, as immediate simulation results (Ravikumar: [0075] "... Solver Module: MD simulation package such as LAMMPS, GROMACS, and TINKER etc. is selected to run these simulations. The simulation software provides trajectory files as output. These trajectory files are post-processed using the codes built in the system to evaluate the ionic conductivity. Result: The ionic conductivity value of the electrolyte is displayed on the screen or written into the memory....") , collections of coordinates of individual atoms involved in the simulating and an evolution in time of the coordinates (Ravikumar: [0111] "... [0111] 1. Dielectric constant: The dielectric constant is computed to determine its ability to dissociate the salt ions. From the atom positions obtained from the simulation trajectory of the electrolyte molecular system and their pre-determined partial charges, the dipole moment of the entire system is computed at regular time intervals, for e.g. every picosecond (ps). Further, the ensemble and time averaged dipole moment fluctuation (Δμ.sup.2) is computed using developed C++ codes. The system 100 considers the regime wherein fluctuations are stabilized to compute Δμ.sup.2, which is then substituted in the below equation to obtain the dielectric constant (ε)...." – showing evolution in time of the coordinates as the atom position is evaluated at every 2 picosecond; [0111]-[0123] positioning with atom/ion and time progression);
collections of coordinates of individual atoms involved in the simulating and an evolution in time of the coordinates (Ravikumar: [0111] "... [0111] 1. Dielectric constant: The dielectric constant is computed to determine its ability to dissociate the salt ions. From the atom positions obtained from the simulation trajectory of the electrolyte molecular system and their pre-determined partial charges, the dipole moment of the entire system is computed at regular time intervals, for e.g. every picosecond (ps). Further, the ensemble and time averaged dipole moment fluctuation (Δμ.sup.2) is computed using developed C++ codes. The system 100 considers the regime wherein fluctuations are stabilized to compute Δμ.sup.2, which is then substituted in the below equation to obtain the dielectric constant (ε)...." – showing evolution in time of the coordinates as the atom position is evaluated at every 2 picosecond; the collection of coordinates means collection of positions are used to determine stabilized property like dielectric constant; other uses of the tranjectory/position also are disclosed . e.g. molar conductivity: [0114] "...2. Molar conductivity: In order to compute molar conductivity, the positions data extracted and stored from the simulation trajectory as mentioned in, (1) Dielectric constant, are utilized....").
Ravikumar also teaches ranking and reranking aspect (Ravikumar: Figs.6, 2A-B, [0030], [0044], [0108] – additionally addressing applicant’s concerns in remarks Pg.10 about ranking and reranking would be repeating the exercise as in [0063]; [0110]-[0132] showing progressive at 2 ps trajectory evaluation and property determination/ranking).
It would have been obvious to one (e.g. a designer) of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Steingrimsson to Senn to add more accurate data using the molecular dynamics simulation (Steingrimsson: [0405]-[0408]. The motivation to combine would have been that Steingrimsson also teaches complementing the LAMMPS (molecular dynamic) simulation with the training the neural network and predicting individual properties of materials (Steingrimsson: [0447]-[0454]). Further motivation to combine would be that Steingrimsson and Senn are analogous arts to the instant claim in the field of accelerated design/discovery of new materials using machine learning (Steingrimsson: Abstract; Senn: Abstract). Also See Steingrimsson "... [0222] There can be great benefits derived from combining ML with physics-based modeling approaches for energetic materials, for improved prediction accuracy....").
It would have been obvious to one (e.g. a designer) of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Ravikumar to Steingrimsson & Senn to add more details of how the LAMMPS data (molecular dynamics simulation) is used to determine position/location of each atom (Ravikumar: [0074]-[0075][0110]-[0123] ) to determine properties of electrolytes in a battery (Ravikumar: Abstract). Further motivation to combine would have been that Ravikumar, Senn and Steingrimsson are analogous art in to the instant claim in the field of battery modeling using molecular dynamics/LAMMPS based simulation (Ravikumar: [0074]-[0075][0110]-[0123]; Senn: Abstract; Steingrimsson: Abstract).
Regarding Claims 2 & 10 (Cancelled)
Regarding Claims 3 & 11
Senn teaches the method of claim 1, further comprising re-training the first prediction model and/or the second prediction model in response to availability of a latest ground- truth data (Senn: [0047]) .
Regarding Claims 4 & 12
Senn teaches the method of claim 1, further comprising computing a conductivity and a diffusivity of lithium (Li+) ions in the plurality of candidate systems (Senn: [0047]"... Additionally, the complex models can be incrementally improved for high-dimensional use cases. These include application to experimental data (like SEM images) or generative design with optimization of individual microstructure particle sizes, shapes and locations....")- SEM images as ground truth data being used to incrementally improve on; [0024] using experimental data) .
Regarding Claims 5 & 13
Senn teaches the method of claim 4, in which ranking comprises: predicting of property estimates for a diffusivity property and a conductivity property of the plurality of candidate systems and an associated measure of prediction uncertainty (Senn: [0035] "... The received microstructure generation parameters are inputted to a first simple artificial intelligence model to generate the microstructure statistics 32. The microstructure statistics can include active surface area, effective diffusivity, conductivity of electrolyte, volume fraction of active material, volume fraction of binder material, volume fraction of electrolyte, and combinations thereof....") ; and ranking the plurality of candidate systems according to the predicting of property estimates for the diffusivity property and the conductivity property of the plurality of candidate systems (Senn: [0039] [0061][0067][0069] as mapped above for ranking based on microstructure statistics generation for purposes of simulation) .
Regarding Claims 6 & 14
Senn teaches the method of claim 1, in which the second prediction model predicts a conductivity and a diffusivity of lithium (Li+) ions in a partially completed material candidate simulation (Senn: [0039] & claim 6; Fig.2 the simple AI model 200 can be partially completed material candidate simulation as discussed in [0035] which has effective diffusivity & conductivity of electrolyte as output) .
Regarding Claims 7
Senn teaches the method of claim 1, in which an interval and frequency at which the second prediction model is applied is a predetermined parameter to start/continue a molecular dynamics simulation of the second top-N of the plurality of candidate systems (Senn: [0061], [0067] & Fig.8 flow and specifically element 76 physics based simulation as molecular dynamic simulation) .
Senn does not specifically teach molecular dynamic simulation.
Steingrimsson teaches molecular dynamics simulation of the second top-N of the plurality of candidate systems [0405]-[0408] [0447]-[0454]).
It would have been obvious to one (e.g. a designer) of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Steingrimsson to Senn to add more accurate data using the molecular dynamics simulation (Steingrimsson: [0405]-[0408]. The motivation to combine would have been that Steingrimsson also teaches complementing the LAMMPS (molecular dynamic) simulation with the training the neural network and predicting individual properties of materials (Steingrimsson: [0447]-[0454]). Further motivation to combine would be that Steingrimsson and Senn are analogous arts to the instant claim in the field of accelerated design/discovery of new materials using machine learning (Steingrimsson: Abstract; Senn: Abstract). Also See Steingrimsson "... [0222] There can be great benefits derived from combining ML with physics-based modeling approaches for energetic materials, for improved prediction accuracy....")
Additionally, Motivation to combine would be that physics based modeling can be molecular dynamics simulation as detailed in (Steingrimsson: Claim 13 "... where the prediction module supports a hybrid structure, one that combines physics-based modeling with standard machine learning prediction, and where the physics-based modeling comprises calculations of thermo-physical or thermo-chemical properties, first-principle (ab initio) calculations, molecular dynamics simulations or group additivity methods....").
Regarding Claims 8 & 16
8. The method of claim 1, further comprises selecting one or more polymers, one or more salts, a concentration of each component, and a temperature to identify a suitable polymer electrolyte material to use in a battery from the second top-N of the plurality of candidate systems (Senn: [0061][0067]-[0068]) .
Regarding Claim 17 (Updated 6/12/2026)
Senn teaches A system (Senn : [0065]-[0085] & Fig.9) for compositional feature representation learning of closed loop simulation for accelerated material discovery (Senn: Fig.2 & [0031] and Fig.8 & [0065]-[0070]), the system comprising at least one processor to execute (Senn: [0072]-[0073]) :
a first prediction model to rank a plurality of candidate systems according to corresponding properties of interest predicted by the first prediction model (Senn: Fig.2 AI model 200 as first prediction model; ranking in [0061] "... All candidates of the multiple screening studies are ranked by their uncertainty and the top (most uncertain) N=1000 candidates are selected for execution in the simulation tools. ..."; [0069] "... Thus, millions of candidates can be screened, and the promising candidates selected from that original list of material combinations. The selection is implemented with priority queues which are data structures that contain an array most promising candidates sorted by their priority...."); a candidate systems according to the corresponding properties of interest predicted by the first prediction model (Senn: Fig.2 AI model 200 running first simulation; [0061] "... All candidates of the multiple screening studies are ranked by their uncertainty and the top (most uncertain) N=1000 candidates are selected for execution in the simulation tools. ..."; [0023]);
a second prediction model to re-rank the plurality of candidate systems according to the corresponding properties of interest predicted by the second prediction model (Senn: Second simulation being the detailed simulation as shown in Fig.2 complex AI model 300 ; [0069] & [0061] showing ranking process being iterative as in [0067] "...An iterative process can be undertaken by determining whether the selected battery microstructures meet defined energy profiles 74. If not, then the entire microstructure candidates can be omitted and a new microstructure can be proposed until one or more microstructure are found. ..."; Fig.2 and Fig.8) based on an input of available trajectory data3 (Senn : trajectories are related to coordinates of individual atoms involved in simulation – which is taught in Senn as cell data [0022]-[0063]-[0064] which evolves based on their uncertainty; [0033] "... [0033] Accordingly, simple AI models can be used for screening (e.g. optimize average particle size) and the complex AI models can be used for design (e.g. optimize each particle's size and location). As such, the simple and complex AI models for microstructure property prediction can be independent from each other in this embodiment....") of a material's partial progression during the simulating of the first top-N (Senn: [0023] "... The model uncertainty can be used to efficiently create new simulation data samples for incremental model improvements...."- as partial progression; [0061]-[0067] ), wherein the available trajectory data comprises a dataset collection of the coordinates and the evolution in time (Senn : trajectories are related to coordinates of individual atoms involved in simulation – which is taught in Senn as cell data [0022]-[0063]-[0064] which evolves based on their uncertainty; [0033]); and the (Senn: [0061] "... All candidates of the multiple screening studies are ranked by their uncertainty and the top (most uncertain) N=1000 candidates are selected for execution in the simulation tools. ..."; Second simulation being the detailed simulation as shown in Fig.2 complex AI model 300); and start, stop, pause, or resume computer resources for the simulating based on the re- ranking of the plurality of candidate systems based on an input of available trajectory data of a material's partial progression (Senn : eliminating and selecting new microstructure for simulation in reassigning and reprioritizing [0067] "... [0067] An iterative process can be undertaken by determining whether the selected battery microstructures meet defined energy profiles 74. If not, then the entire microstructure candidates can be omitted [first top-N] and a new microstructure can be proposed [second top-N] until one or more microstructure are found. I..."; [0070] next sample; [0027] reprioritization/ reassignment as changing the weights, or selection of top candidates for simulation that means it takes away resources from non-selected candidates as in [0061], [0067]) during the simulating of the second top-N (Senn: [0067] "... [0067] An iterative process can be undertaken by determining whether the selected battery microstructures meet defined energy profiles 74. If not, then the entire microstructure candidates can be omitted and a new microstructure can be proposed until one or more microstructure are found. ..." shows that the entire new (second top-N) can be iteratively simulated [0062] "... [0062] The incremental model improvement workflow starts from the initial simulation data set [starting] . First, models are trained and evaluated by their uncertainty. The difficult candidates are run with the simulation tools and the models are retrained for improvement based on the incremental data. Then, the retrained models are again evaluated by their uncertainty [stopping and restarting with incremental data] . This iterative improvement is continued until the uncertainty does not improve (decrease) significantly any more...." ; Alternately, taking second top-N set can also considered as duplication of process).
Senn does not specifically teach the simulation is molecular dynamics simulation.
Additionally, Senn does not specifically teach newly amended limitation of executing, by a molecular dynamics simulation cluster that runs parallel molecular dynamics simulations, the simulating of the first top-N to generate, as immediate simulation results, collections of coordinates of individual atoms involved in the simulating and an evolution in time of the coordinates; and wherein the available trajectory data comprises a dataset collection of the coordinates and the evolution in time.
Steingrimsson teaches A system for compositional feature representation learning of closed loop simulation for accelerated material discovery (Steingrimsson: Abstract) , the system comprising: a first prediction model to rank a plurality of candidate systems according to corresponding properties of interest predicted by the first prediction model (Steingrimsson: [0447]-[0454] use of neural network models with LAMMPS simulation as molecular dynamics simulation) ; a molecular dynamics simulation cluster to simulate a first top-N of the plurality of candidate systems according to the corresponding properties of interest predicted by the first prediction model (Steingrimsson: [0451] & Table 6 accounts for using molecular dynamics simulation as LAMMPS simulation which is known to include to predict polymer properties like diffusion [0405]-[0408]) ; a second prediction model to re-rank the plurality of candidate systems according to the corresponding properties of interest predicted by the second prediction model; and the molecular dynamics simulation cluster to simulate a second top-N of the plurality of candidate systems according to the corresponding properties of interest predicted by the second prediction model (Limitation taught in Senn but reiterated here as adding molecular simulation being repeatedly performed: Steingrimsson: molecular simulation as LAMMPS [0405]-[0408]; as teaching performing iteratively the ranking and simulation using various techniques [0447]-[0454]; [0468]"... [0468] It makes sense for the ICME to iteratively integrate ML modeling of phase fields, Calculation of Phase Diagrams (CALPHAD), Density Functional Theory (DFT), also referred to as first-principle calculations, multiscale (atomic, meso-scale and continuum-scale) modeling and simulation, as well as joint ML optimization of material properties, to accelerate the materials development, processing, and testing cycle....".).
Steingrimsson teaches executing, by a molecular dynamics simulation cluster that runs parallel molecular dynamics simulations, the simulating of the first top-N to generate (Steingrimsson: [0451] & Table 6 accounts for using molecular dynamics simulation as LAMMPS simulation which is known to include to predict polymer properties like diffusion [0405]-[0408]), as immediate simulation results, collections of coordinates of individual atoms involved in the simulating and an evolution in time of the coordinates4 (Steingrimsson: [0406] "... [0406] As most classical molecular dynamics simulators, LAMMPS requires the initial positions of the particles as input, LAMMPS can automatically generate initial positions for simple crystals or accept data files provided by user for materials with complex atomic structures. When provided with initial positions and velocities of the particles together with corresponding interatomic potentials, LAMMPS can simulate a wide variety of materials. While simulating a given material, LAMMPS can utilize statistical mechanics to convert atomic trajectories into macroscopic properties such as temperature, volume, pressure and density. LAMMPS can allow the user to specify which properties are desired as outputs....") ; and wherein the available trajectory data comprises a dataset collection of the coordinates and the evolution in time (Steingrimsson: [0406]).
Although Senn and Steingrimsson discuss trajectories (Senn: [0022], [0063]-[0064]; Steingrimsson: [0406]), they do not explicitly teach collections of coordinates of individual atoms involved in the simulating and an evolution in time of the coordinates.
Ravikumar teaches executing, by a molecular dynamics simulation cluster that runs parallel molecular dynamics simulations (Ravikumar: [0074]-[0075] molecular dynamics simulation as LAMMPS simulation; [0110]) , the simulating of the first top-N to generate, as immediate simulation results (Ravikumar: [0075] "... Solver Module: MD simulation package such as LAMMPS, GROMACS, and TINKER etc. is selected to run these simulations. The simulation software provides trajectory files as output. These trajectory files are post-processed using the codes built in the system to evaluate the ionic conductivity. Result: The ionic conductivity value of the electrolyte is displayed on the screen or written into the memory....") , collections of coordinates of individual atoms involved in the simulating and an evolution in time of the coordinates (Ravikumar: [0111] "... [0111] 1. Dielectric constant: The dielectric constant is computed to determine its ability to dissociate the salt ions. From the atom positions obtained from the simulation trajectory of the electrolyte molecular system and their pre-determined partial charges, the dipole moment of the entire system is computed at regular time intervals, for e.g. every picosecond (ps). Further, the ensemble and time averaged dipole moment fluctuation (Δμ.sup.2) is computed using developed C++ codes. The system 100 considers the regime wherein fluctuations are stabilized to compute Δμ.sup.2, which is then substituted in the below equation to obtain the dielectric constant (ε)...." – showing evolution in time of the coordinates as the atom position is evaluated at every 2 picosecond; [0111]-[0123] positioning with atom/ion and time progression);
collections of coordinates of individual atoms involved in the simulating and an evolution in time of the coordinates (Ravikumar: [0111] "... [0111] 1. Dielectric constant: The dielectric constant is computed to determine its ability to dissociate the salt ions. From the atom positions obtained from the simulation trajectory of the electrolyte molecular system and their pre-determined partial charges, the dipole moment of the entire system is computed at regular time intervals, for e.g. every picosecond (ps). Further, the ensemble and time averaged dipole moment fluctuation (Δμ.sup.2) is computed using developed C++ codes. The system 100 considers the regime wherein fluctuations are stabilized to compute Δμ.sup.2, which is then substituted in the below equation to obtain the dielectric constant (ε)...." – showing evolution in time of the coordinates as the atom position is evaluated at every 2 picosecond; the collection of coordinates means collection of positions are used to determine stabilized property like dielectric constant; other uses of the tranjectory/position also are disclosed . e.g. molar conductivity: [0114] "...2. Molar conductivity: In order to compute molar conductivity, the positions data extracted and stored from the simulation trajectory as mentioned in, (1) Dielectric constant, are utilized....").
Ravikumar also teaches ranking and reranking aspect (Ravikumar: Figs.6, 2A-B, [0030], [0044], [0108] – additionally addressing applicant’s concerns in remarks Pg.10 about ranking and reranking would be repeating the exercise as in [0063], [0110]-[0132] showing progressive at 2 ps trajectory evaluation and property determination/ranking).
It would have been obvious to one (e.g. a designer) of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Steingrimsson to Senn to add more accurate data using the molecular dynamics simulation (Steingrimsson: [0405]-[0408]. The motivation to combine would have been that Steingrimsson also teaches complementing the LAMMPS (molecular dynamic) simulation with the training the neural network and predicting individual properties of materials (Steingrimsson: [0447]-[0454]). Further motivation to combine would be that Steingrimsson and Senn are analogous arts to the instant claim in the field of accelerated design/discovery of new materials using machine learning (Steingrimsson: Abstract; Senn: Abstract). Also See Steingrimsson "... [0222] There can be great benefits derived from combining ML with physics-based modeling approaches for energetic materials, for improved prediction accuracy....").
It would have been obvious to one (e.g. a designer) of ordinary skill in the art before the effective filing date of the claimed invention to apply the teachings of Ravikumar to Steingrimsson & Senn to add more details of how the LAMMPS data (molecular dynamics simulation) is used to determine position/location of each atom (Ravikumar: [0074]-[0075][0110]-[0123] ) to determine properties of electrolytes in a battery (Ravikumar: Abstract). Further motivation to combine would have been that Ravikumar, Senn and Steingrimsson are analogous art in to the instant claim in the field of battery modeling using molecular dynamics/LAMMPS based simulation (Ravikumar: [0074]-[0075][0110]-[0123]; Senn: Abstract; Steingrimsson: Abstract).
Regarding Claim 18 (Cancelled)
Regarding Claim 19
Senn teaches the system of claim 17, in which the first prediction model and/or the second prediction model to re-train in response to availability of a latest ground-truth data (Senn: [0047]"... Additionally, the complex models can be incrementally improved for high-dimensional use cases. These include application to experimental data (like SEM images) or generative design with optimization of individual microstructure particle sizes, shapes and locations....")- SEM images as ground truth data being used to incrementally improve on; [0024] using experimental data).
Regarding Claim 20
Senn teaches the system claim 17, in which the second prediction model is further to predict of property estimates for a diffusivity property and a conductivity property of the plurality of candidate systems and an associated measure of prediction uncertainty (Senn: [0035] "... The received microstructure generation parameters are inputted to a first simple artificial intelligence model to generate the microstructure statistics 32. The microstructure statistics can include active surface area, effective diffusivity, conductivity of electrolyte, volume fraction of active material, volume fraction of binder material, volume fraction of electrolyte, and combinations thereof...."; Fig.2 showing uncertainity), and to rank the plurality of candidate systems according to the predicting of property estimates for the diffusivity property and the conductivity property of the plurality of candidate systems (Senn: [0039] [0061][0067][0069] as mapped above for ranking based on microstructure statistics generation for purposes of simulation).
---- This page is left blank after this line ----
Communication
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AKASH SAXENA whose telephone number is (571)272-8351. The examiner can normally be reached Mon-Fri, 7AM-3:30PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, RYAN PITARO can be reached on (571) 272-4071. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
AKASH SAXENA
Primary Examiner
Art Unit 2188
/AKASH SAXENA/Primary Examiner, Art Unit 2188 Friday, June 12, 2026
1 Specification [0049] "...[0049] As described, dataset collections of coordinates of individual atoms involved in simulation and their evolution in time are referred to as trajectories. In practice, state-of-the-art and community-known algorithmic methods are applied to completed trajectories in order to compute macroscopic material properties of interest...."
2 Specification [0049] "...[0049] As described, dataset collections of coordinates of individual atoms involved in simulation and their evolution in time are referred to as trajectories. In practice, state-of-the-art and community-known algorithmic methods are applied to completed trajectories in order to compute macroscopic material properties of interest...."
3 Specification [0049] "...[0049] As described, dataset collections of coordinates of individual atoms involved in simulation and their evolution in time are referred to as trajectories. In practice, state-of-the-art and community-known algorithmic methods are applied to completed trajectories in order to compute macroscopic material properties of interest...."
4 Specification [0049] "...[0049] As described, dataset collections of coordinates of individual atoms involved in simulation and their evolution in time are referred to as trajectories. In practice, state-of-the-art and community-known algorithmic methods are applied to completed trajectories in order to compute macroscopic material properties of interest...."
Prosecution Insights