# US 2023/0054908 A1 · Machine learning optimization through randomized autonomous crop planting > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0054908 A1 - Document ID: US20230054908A1 - Status: Published application - Kind: A1 - Application number: 17/408,398 - Filed: 2021-08-21 - Published: 2023-02-23 - Earliest claimed: 2021-08-21 - Assignees: Deere & Company - Applicants: Deere & Company - Inventors: Michael D. Stellpflug; Angela L. Bowman - Web page: https://patentgrep.com/patent/US20230054908A1 ## CPC - A01B 69/008: {automatic} - A01C 7/06: Seeders combined with fertilising apparatus - A01C 21/005: {Following a specific plan, e.g. pattern} - A01C 21/007: {Determining fertilization requirements} - A01G 25/09: Watering arrangements making use of movable installations on wheels or the like - A01G 25/16: Control of watering - A01M 7/0089: {Regulating or controlling systems (the delivery being related to the movement of a vehicle B05B9/06)} - G06N 20/00: Machine learning - A01B: SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL (making or covering furrows or holes for sowing, planting or manuring A01C5/00; mowers convertible to soil working apparatus or capable of soil working A01D42/04; mowers combined with soil working implements A01D43/12; soil working for engineering purposes E01, E02, E21) - A01C: PLANTING; SOWING; FERTILISING (parts, details or accessories of agricultural machines or implements, in general A01B51/00 - A01B75/00) - A01G: HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING (picking of fruits, vegetables, hops or the like A01D46/00; propagating unicellular algae C12N1/12) - A01M: CATCHING, TRAPPING OR SCARING OF ANIMALS (appliances for catching swarms or drone-catching A01K57/00; fishing A01K69/00 - {A01K99/00}; biocides, pest repellants or attractants A01N); APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Systems and methods automate the design and execution of randomized experiments. Portions of a field are planted using an agricultural vehicle configured to randomly vary planting parameters when planting a portion of the field. A resulting crop outcome across each portion or sub-portion of the field is observed. A training set of data is generated that includes the varied planting parameters and the associated crop outcomes for each portion of the field. A machine-learned model is trained using the training set of data and is configured to predict a crop outcome for a portion of the field based on historical and forecast conditions and a set of planting parameters applied to a portion of the field. For subsequent iterations, for a target portion of the field, the machine-learned model can be applied to identify a set of planting parameters for planting the target portion of the field to optimize a desired crop outcome. ## Claims ### Claim 1 A method for cultivating a field, comprising: planting each of a plurality of portions of the field, each portion of the field planted using one or more agricultural vehicles configured to randomly vary each of a plurality of planting parameters before or during planting the portion of the field, the planting parameters including at least a planting depth, a planting spacing, a type of treatment applied when planting, and an amount of treatment applied when planting; determining, for each portion of the field, a resulting crop outcome across the portion of the field; generating a training set of data comprising the varied planting parameters and the determined crop outcome for each of the portions of the field; training a machine-learned model using the generated training set of data, the machine-learned model configured to predict a crop outcome for a portion of the field based on a set of planting parameters used to plant the portion of the field; and for a subsequent iteration, for a target portion of the field, applying the machine-learned model to identify a set of planting parameters for planting the target portion of the field to optimize a desired crop outcome. ### Claim 2 (depends on 1) The method of claim 1, wherein the agricultural vehicle is an autonomous vehicle. ### Claim 3 (depends on 1) The method of claim 1, wherein each portion of the field comprises a plurality of sub-portions, each sub-portion associated with a set of field characteristics, and wherein sets of field characteristics across each portion of the field are substantially homogenous. ### Claim 4 (depends on 1) The method of claim 1, wherein the plurality of planting parameters further includes at least one of: a seed rate, a seed type, an amount of irrigation, an environmental condition, a sun exposure, a fertilizer type and/or rate, an herbicide type and/or rate, a pesticide type and/or rate, a soil composition, a land use type, a crop rotation, or a cover crop type. ### Claim 5 (depends on 1) The method of claim 1, wherein each portion of the field is associated with a same crop type being planted within the portion of the field. ### Claim 6 (depends on 1) The method of claim 1, wherein the desired crop outcome includes at least one of: a desired yield, a desired yield rate, a desired cost to plant, a desired amount of fertilizer used, a desired amount of herbicide used, a desired amount of pesticide used, a desired amount of irrigation used, a desired time to harvest, a desired soil condition, a desired nitrogen efficiency, a desired environmental impact, a desired water quality, a land use, or a financial subsidy. ### Claim 7 (depends on 1) The method of claim 1, further comprising: planting, in the subsequent iteration, the target portion of the field using the identified set of planting parameters ### Claim 8 (depends on 1) The method of claim 1, further comprising: planting, in the subsequent iteration, the target portion of the field using a set of randomly varied planting parameters, wherein the set of randomly varied planting parameters are based on the identified set of planting parameters, and wherein a value distribution of the planting parameters in the set of randomly varied planting parameters is refined based on planting parameter outcomes associated with a preceding or related iteration. ### Claim 9 (depends on 1) The method of claim 1, further comprising: generating a second training set of data, the second training set of data comprising outcome data associated with the subsequent season for one or more portions of the field; and retraining the machine-learned model using the generated second training set of data. ### Claim 10 (depends on 1) The method of claim 1, wherein the varied planting parameter values are evenly distributed among a range of values. ### Claim 11 (depends on 1) The method of claim 1, wherein a variation of the varied planting parameters is distributed according to a Gaussian distribution, a face-centered cubic design, or a Box-Behnken design. ### Claim 12 (depends on 1) The method of claim 1, further comprising: planting, in a subsequent iteration, the target portion of the field using a set of randomly varied planting parameters, wherein the set of randomly varied planting parameters are based on the identified set of planting parameters, and wherein a Gaussian distribution of the planting parameters in the set of randomly varied planting parameters is refined based on planting parameter outcomes observed in a preceding iteration. ### Claim 13 (depends on 1) The method of claim 1, wherein, for at least one planting parameter of the plurality of planting parameters, the agricultural vehicle is more likely to select under-represented values of at least one planting parameter when planting each of the plurality of portions of the field. ### Claim 14 (depends on 13) The method of claim 13, further comprising: planting, in the subsequent iteration, the target portion of the field using a set of randomly varied planting parameters, wherein the set of randomly varied planting parameters are based on the identified set of planting parameters, and wherein sub-optimal values of the planting parameters in the set of randomly varied planting parameters are less likely to be selected than in a preceding iteration. ### Claim 15 A non-transitory computer-readable medium comprising memory with instructions encoded thereon, the instructions, when executed by one or more processors, causing the one or more processors to perform operations, the instructions comprising instructions to: plant each of a plurality of portions of a field, each portion of the field planted using an agricultural vehicle configured to randomly vary each of a plurality of planting parameters when planting the portion of the field, the planting parameters including at least a planting depth, a planting spacing, a type of treatment applied when planting, and an amount of treatment applied when planting; determine, for each portion of the field, a resulting crop outcome across the portion of the field; generate a training set of data comprising the varied planting parameters and the determined crop outcome for each of the portions of the field; train a machine-learned model using the generated training set of data, the machine-learned model configured to predict a crop outcome for a portion of the field based on a set of planting parameters used to plant the portion of the field; and for a subsequent iteration, for a target portion of the field, apply the machine-learned model to identify a set of planting parameters for planting the target portion of the field for a desired crop outcome. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the instructions further comprise instructions to: plant, in the subsequent iteration, the target portion of the field using a set of randomly varied planting parameters, wherein the set of randomly varied planting parameters are based on the identified set of planting parameters, and wherein a value distribution of the planting parameters in the set of randomly varied planting parameters is refined based on outcomes associated in a season. ### Claim 17 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein a variation of the varied planting parameters is distributed according to a Gaussian distribution, face centered cubic design, or Box-Behnken design. ### Claim 18 An agricultural vehicle comprising one or more hardware processors and a non-transitory computer-readable storage medium storing executable instructions that, when executed by the one or more hardware processors, cause the agricultural vehicle to perform steps comprising: planting each of a plurality of portions of a field, each portion of the field planted using an agricultural vehicle configured to randomly vary each of a plurality of planting parameters when planting the portion of the field, the planting parameters including at least a planting depth, a planting spacing, a type of treatment applied when planting, and an amount of treatment applied when planting; determining, for each portion of the field, a resulting crop outcome across the portion of the field; generating a training set of data comprising the varied planting parameters and the determined crop outcome for each of the portions of the field; training a machine-learned model using the generated training set of data, the machine-learned model configured to predict a crop outcome for a portion of the field based on a set of planting parameters used to plant the portion of the field; and for a subsequent iteration, for a target portion of the field, applying the machine-learned model to identify a set of planting parameters for planting the target portion of the field for a desired crop outcome. ### Claim 19 (depends on 18) The agricultural vehicle of claim 18, the executable instructions further causing the agricultural vehicle to perform steps comprising: planting, in the subsequent season, the target portion of the field using a set of randomly varied planting parameters, wherein the set of randomly varied planting parameters are based on the identified set of planting parameters, and wherein a value distribution of the planting parameters in the set of randomly varied planting parameters is narrower than a distribution of planting parameters associated with a preceding iteration. ### Claim 20 (depends on 18) The agricultural vehicle of claim 18, the executable instructions further causing the agricultural vehicle to perform steps comprising: planting, in the subsequent season, the target portion of the field using a set of randomly varied planting parameters, wherein the set of randomly varied planting parameters are based on the identified set of planting parameters, and wherein a distribution of the planting parameters in the set of randomly varied planting parameters is refined based on planting parameters associated with a preceding iteration.