# US 10,769,733 B2 · Forecasting national crop yield during the growing season using weather indices > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,769,733 B2 - Document ID: US10769733B2 - Status: Granted - Kind: B2 - Application number: 16/734,813 - Filed: 2020-01-06 - Published: 2020-05-14 - Granted: 2020-09-08 - Earliest claimed: 2016-01-22 - Assignees: Climate LLC - Applicants: The Climate Corporation - Inventors: Lijuan Xu; Ying Xu - Web page: https://patentgrep.com/patent/US10769733B2 ## CPC - G06Q 50/02: Agriculture; Fishing; Forestry; Mining - Y02A 10/40: Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping - 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 - Y02A: TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE ## Abstract A method for determining national crop yields during a growing season is accomplished using a server computer system that receives observed agricultural data records for a specific geo-location at a specific time. The server calculates weather index values from the agricultural data records that represent crop stress on plants. Geo-specific weather indices are generated from the weather index values, which then are aggregated to generate aggregated weather index data series. Representative features are selected from each aggregated weather index data series to create a covariate matrix for each geographic area. Crop yield for the geographic area is calculated using a linear regression model based on the covariate matrix for the specific geographic area. The server determines a national crop yield for the specific year as a sum of the crop yields for the specific geographic areas nationally adjusted using national yield adjustment instructions. ## Claims ### Claim 1 A computer-implemented method comprising: receiving, by a server computer system, one or more agricultural data records that represent observed agricultural data points for a specific geo-location at a specific time; calculating, by the server computer system, weather index values from the one or more agricultural data records to generate one or more geo-specific weather indices for specific geo-locations over specified periods of time; aggregating, by the server computer system, the one or more geo-specific weather indices to generate one or more aggregated weather indices that represent specific geographic areas, from a subset of the one or more geo-specific weather indices; selecting, by the server computer system, representative features from the one or more aggregated weather indices and creating, for each specific geographic area, a covariate matrix in computer memory comprising the representative features selected from the one or more aggregated weather indices; determining, by the server computer system, a geographic area specific crop yield for a specific year by using a linear regression model to calculate the geographic area specific crop yield from the covariate matrix that represents the geographic area for that specific year; determining, by the server computer system, a national crop yield for the specific year by calculating a sum of the geographic area specific crop yields for the specific year, nationally adjusted using national yield adjustment instructions in the server computer system; and based on the national crop yield for the specific year, modifying an operating parameter of an agricultural equipment used for treatment of one or more fields. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the observed agricultural data points include at least one of an observed temperature record, soil moisture record, and precipitation record. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein calculating the weather index values from the one or more agricultural data records to generate the one or more geo-specific weather indices comprises calculating a flood stress index as a sum of daily water runoff above a specific threshold value over a specific time period. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein calculating the weather index values from the one or more agricultural data records to generate the one or more geo-specific weather indices comprises calculating an early drought stress index as a sum of daily precipitation minus runoff, using daily precipitation not to exceed 2.5 inches (625 mm) over a specific time period. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein calculating the weather index values from the one or more agricultural data records to generate the one or more geo-specific weather indices comprises calculating a drought stress index as a sum of a fraction of soil moisture below a specified threshold over a specific time period. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein calculating the weather index values from the one or more agricultural data records to generate the one or more geo-specific weather indices comprises calculating a daytime heat stress index as a sum of a number of degrees that a maximum daily temperature is above a specified threshold over a specific time period. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein calculating the weather index values from the one or more agricultural data records to create the one or more geo-specific weather indices comprises calculating a nighttime heat stress index as a sum of a number of degrees that a minimum daily temperature is above a specified threshold over a specific time period. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein determining the geographic area specific crop yield for the specific year using the linear regression model comprises calculating one or more regression parameters for the linear regression model, wherein the one or more regression parameters are based upon observed agricultural data points from multiple measured geographic areas captured on or before a specified observation date. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein determining the geographic area specific crop yield for the specific year using the linear regression model comprises calculating one or more regression parameters for the linear regression model, wherein the one or more regression parameters are based upon observed agricultural data points from the specific geographic area captured after a specified observation date. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein selecting the representative features from the one or more aggregated weather indices comprises selecting, for each type of weather index within the one or more aggregated weather indices, one of: a median value for each type of weather index from the aggregated weather indices, or a mean value for each type of weather index from the aggregated weather indices. ### Claim 11 One or more non-transitory computer-readable storage media storing instructions which, when executed by one or more computing devices, cause the one or more computing devices to execute a method comprising: receiving one or more agricultural data records that represent observed agricultural data points for a specific geo-location at a specific time; calculating weather index values from the one or more agricultural data records to generate one or more geo-specific weather indices for specific geo-locations over specified periods of time; aggregating the one or more geo-specific weather indices to generate one or more aggregated weather indices that represent specific geographic areas, from a subset of the one or more geo-specific weather indices; selecting representative features from the one or more aggregated weather indices and creating, for each specific geographic area, a covariate matrix in computer memory comprising the representative features selected from the one or more aggregated weather indices; determining a geographic area specific crop yield for a specific year by using a linear regression model to calculate the geographic area specific crop yield from the covariate matrix that represents the geographic area for that specific year; determining a national crop yield for the specific year by calculating a sum of the geographic area specific crop yields for the specific year, nationally adjusted using national yield adjustment instructions; and based on the national crop yield for the specific year, modifying an operating parameter of an agricultural equipment used for treatment of one or more fields. ### Claim 12 (depends on 11) The one or more non-transitory computer-readable storage media of claim 11, wherein the observed agricultural data points include at least one of an observed temperature record, soil moisture record, and precipitation record. ### Claim 13 (depends on 11) The one or more non-transitory computer-readable storage media of claim 11, wherein the instructions which when executed cause calculating the weather index values from the one or more agricultural data records to generate the one or more geo-specific weather indices comprise instructions which when executed cause calculating a flood stress index as a sum of daily water runoff above a specific threshold value over a specific time period. ### Claim 14 (depends on 11) The one or more non-transitory computer-readable storage media of claim 11, wherein the instructions which when executed cause calculating the weather index values from the one or more agricultural data records to generate the one or more geo-specific weather indices comprise instructions which when executed cause calculating an early drought stress index as a sum of daily precipitation minus runoff, using daily precipitation not to exceed 2.5 inches (625 mm) over a specific time period. ### Claim 15 (depends on 11) The one or more non-transitory computer-readable storage media of claim 11, wherein the instructions which when executed cause calculating the weather index values from the one or more agricultural data records to generate the one or more geo-specific weather indices comprise instructions which when executed cause calculating a drought stress index as a sum of a fraction of soil moisture below a specified threshold over a specific time period. ### Claim 16 (depends on 11) The one or more non-transitory computer-readable storage media of claim 11, wherein the instructions which when executed cause calculating the weather index values from the one or more agricultural data records to generate the one or more geo-specific weather indices comprise instructions which when executed cause calculating a daytime heat stress index as a sum of a number of degrees that a maximum daily temperature is above a specified threshold over a specific time period. ### Claim 17 (depends on 11) The one or more non-transitory computer-readable storage media of claim 11, wherein the instructions which when executed cause calculating the weather index values from the one or more agricultural data records to create the one or more geo-specific weather indices comprise instructions which when executed cause calculating a nighttime heat stress index as a sum of a number of degrees that a minimum daily temperature is above a specified threshold over a specific time period. ### Claim 18 (depends on 11) The one or more non-transitory computer-readable storage media of claim 11, wherein the instructions which when executed cause determining the geographic area specific crop yield for the specific year using the linear regression model comprise instructions which when executed cause calculating one or more regression parameters for the linear regression model, wherein the one or more regression parameters are based upon observed agricultural data points from multiple measured geographic areas captured on or before a specified observation date. ### Claim 19 (depends on 11) The one or more non-transitory computer-readable storage media of claim 11, wherein the instructions which when executed cause determining the geographic area specific crop yield for the specific year using the linear regression model comprise instructions which when executed cause calculating one or more regression parameters for the linear regression model, wherein the one or more regression parameters are based upon observed agricultural data points from the specific geographic area captured after a specified observation date. ### Claim 20 (depends on 11) The one or more non-transitory computer-readable storage media of claim 11, wherein the instructions which when executed cause selecting the representative features from the one or more aggregated weather indices comprise instructions which when executed cause selecting, for each type of weather index within the one or more aggregated weather indices, one of: a median value for each type of weather index from the aggregated weather indices, or a mean value for each type of weather index from the aggregated weather indices.