# US 12,004,444 B2 · Predictive agricultural management system and method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,004,444 B2 - Document ID: US12004444B2 - Status: Granted - Kind: B2 - Application number: 18/138,584 - Filed: 2023-04-24 - Published: 2023-08-17 - Granted: 2024-06-11 - Earliest claimed: 2019-07-30 - Assignees: Root Applied Sciences Inc. - Applicants: Root Applied Sciences Inc. - Inventors: Sarah Anne Placella; Adam Ralph Zeilinger; Tyler Evan Schartel; Ken Yamaguchi - Web page: https://patentgrep.com/patent/US12004444B2 ## CPC - A01B 79/005: {Precision agriculture} - A01B 79/02: combined with other agricultural processing, e.g. fertilising, planting - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 20/00: Machine learning - G06N 20/20: Ensemble learning - G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) - G06Q 50/02: Agriculture; Fishing; Forestry; Mining - 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) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract Systems and methods for predictive management of plants. Agricultural (and natural resource) managers may have a multitude of data sets and data sources available, but often lack a meaningful or proven way to assimilate all available data and then conclusively select actions. For example, a vineyard manager may be able to collect data about local and regional weather, precipitation, disease prevalence, insect prevalence, pesticide use, crop varietal, cover crop selection and many other inputs to a predictive machine-learning vineyard management engine. As all this data is collected through local devices and third-party services, a prediction model may be used to determine specific outcomes or recommended actions based on the trained predictive model. For example, the model may be used to predict optimal harvest date, disease spread and vector spread, pest spread and impact, best pesticide use, irrigation plans, fruit quality, and the like. ## Claims ### Claim 1 A computer-implemented method for training a predictive model for crop management comprising: collecting a first data set about at least one global agricultural factor from a remote data collection service; collecting a second data set about at least one local agricultural factor from a local data collection device; assimilating the first and second data sets into a local database to create a first training data set comprising the collected first set of data and the collected second set of data; training a predictive model using the first training data set to produce one or more measurable outcomes for the crop; collecting a third data set about at least one global vineyard factor from the remote data collection service; collecting a fourth data set about at least one local vineyard factor from the local data collection device; and predicting a measurable crop outcome using the trained predictive model in response to the collected third data set and the collected fourth data set. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the first and second data sets are geo-referenced. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the first data set comprises a disease survey of a geographic region. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises historic yields of a crop from the local area. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises tannins or anthocyanins present in samples from a local crop. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the second data set comprises data about insects present at the local area. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises a crop varietal. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises a soil analysis of a local area. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises soil nutrients present in a local area. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises blade/petal analysis in a local area. ### Claim 11 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises pesticide use in a local area. ### Claim 12 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises evapotranspiration data for a local area. ### Claim 13 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises habitat suitability data in a local area. ### Claim 14 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises diagnostic companies and testing/sequencing companies involved in the local area and regional area. ### Claim 15 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises a crop yield. ### Claim 16 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises fruit quality. ### Claim 17 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises a zone of disease. ### Claim 18 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises an efficacy of management choice against costs. ### Claim 19 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises an optimal harvest date. ### Claim 20 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises a pesticide spray strategy. ### Claim 21 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises a cover crop selection. ### Claim 22 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises a disease risk. ### Claim 23 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises a disease spread probability. ### Claim 24 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises a level of harvest. ### Claim 25 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises a mapping one of the group comprised of: a habitat suitability, a suggested varietal to plant, an expected quality of a crop, or a potential plantable crop varietal. ### Claim 26 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises an optimal chemical or biological addition to a crop. ### Claim 27 A computer system for training a predictive model for plant management comprising: a first collection device configured to collect a first data set about at least one global plant factor from a remote data collection service; a second collection device configured to collect a second data set about at least one local plant factor from a local data collection device; and a plant management computing device, including a data assimilation engine configured to assimilate the first and second data sets into a local database to create a first training data set comprising the collected first set of data and the collected second set of data; a training engine configured to train a predictive model using the first training data set to produce one or more measurable outcomes for the crop; and a prediction engine configured to collect a third data set about at least one global vineyard factor from the remote data collection service and collect a fourth data set about at least one local vineyard factor from the local data collection device, the prediction engine further configured to output a prediction in response to analyzing the third and fourth data sets using the predictive model. ### Claim 28 (depends on 1) The computer-implemented method of claim 1, wherein the first data set comprises geo-referenced temperature data. ### Claim 29 (depends on 1) The computer-implemented method of claim 1, wherein the first data set comprises geo-referenced precipitation data. ### Claim 30 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises historical land use data in a local area. ### Claim 31 (depends on 1) The computer-implemented method of claim 1, wherein the second set of data comprises crop and root stock origin data used in a local area. ### Claim 32 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises an optimal varietal selection. ### Claim 33 (depends on 1) The computer-implemented method of claim 1, wherein the predictive output comprises a crop and field rotation strategy.