Generating digital models of crop yield based on crop planting dates and relative maturity values

Patent metadata

Field	Value
Publication number	US-10694686-B2
Application number	US-201916375589-A
Country	US
Kind code	B2
Filing date	Apr 4, 2019
Priority date	Jan 7, 2016
Publication date	Jun 30, 2020
Grant date	Jun 30, 2020

Abstract

A method for generating digital models of potential crop yield based on planting date, relative maturity, and actual production history is provided. In an embodiment, data representing historical planting dates, relative maturity values, and crop yield is received by an agricultural intelligence computer system. Based on the historical data, the system generates spatial and temporal maps of planting dates, relative maturity, and actual production history. Using the maps, the system creates a model of potential yield that is dependent on planting date and relative maturity. The system may then receive actual production history data for a particular field. Using the received actual production history data, a particular planting date, and a particular relative maturity value, the agricultural intelligence computer system computes a potential yield for a particular field.

First claim

What is claimed is:

1. A computer-implemented method for improving performance of a computing system used to model potential crop yield, the method comprising:
storing, at a server computer system a model of potential crop yield, the model of potential crop yield comprising generated digital modeling data used to compute potential yield as a function of location, planting date, and relative maturity, the model of potential crop yield having been generated from actual production history maps, relative maturity maps, and planting date maps;
receiving, over a network at the server computer system, electronic digital data comprising a plurality of values representing actual production history for a particular field; and
computing, from the model of potential crop yield, a particular potential yield for the particular field based, at least in part, on the plurality of values representing actual production history for the particular field.

2. The method of claim 1 , further comprising:
receiving, over the network at the server computer system, electronic digital data comprising a plurality of values representing past weather observations for a specific geo-location;
computing one or more crop stress index values from the plurality of values representing past weather observations to create one or more geo-specific crop stress indices;
creating, for each specific geographic area, a covariate matrix in computer memory comprising the one or more geo-specific crop stress indices; and
computing, for a particular location, a geographic area specific crop yield based, at least in part, on the covariate matrix comprising the one or more geo-specific crop stress indices and the particular potential yield for the particular field.

3. The method of claim 2 , further comprising;
receiving, over the network at the server computer system, an indication that one or more crops have been planted on the particular field;
receiving, over the network at the server computer system, electronic digital data comprising a plurality of values representing observed agricultural data points for the particular field at a particular time, wherein the observed agricultural data points include at least one of an observed temperature record, soil moisture record, and precipitation record;
computing updated crop stress index values from the observed agricultural data points to create one or more updated geo-specific crop stress indices, wherein each of the updated geo-specific crop stress indices includes one or more calculated crop stress index values for the particular field over a specified period of time;
creating, for the particular field, an updated covariate matrix in computer memory comprising the one or more updated geo-specific crop stress indices; and
computing an updated geographic area specific crop yield based, at least in part, on the updated covariate matrix and the particular potential yield for the particular field.

4. The method of claim 1 , further comprising:
storing, in digital memory of the server computer system, crop relative maturity data comprising a plurality of seed types and a plurality of associated relative maturity values;
receiving, over the network at the server computer system, a proposed planting date for the particular field;
determining, from the model of potential crop yield, the proposed planting date for the particular field, and the plurality of values representing actual production history for the particular field, a particular relative maturity value that maximizes a potential yield for the particular field;
identifying, in the crop relative maturity data, a particular seed type corresponding to the particular relative maturity value; and
sending, over the network to a field manager computing device, a recommendation of the particular seed type for the proposed planting date for the particular field.

5. The method of claim 1 , further comprising:
receiving, over the network at the server computer system, a proposed relative maturity value for the particular field;
determining, from the model of potential crop yield, the proposed relative maturity value for the particular field, and the plurality of values representing actual production history for the particular field, a particular planting date that maximizes a potential yield for the particular field; and
sending, over the network to a field manager computing device, a recommendation of the particular planting date for the proposed relative maturity for the particular field.

6. The method of claim 5 , further comprising:
storing, in digital memory of the server computer system, crop relative maturity data comprising a plurality of seed types and a plurality of associated relative maturity values;
determining that the particular planting date has passed;
receiving, over the network at the server computer system, an indication that a crop has not been planted on the particular field;
determining, from the model of potential crop yield, the plurality of values representing actual production history for the particular field, and one or more of a current date or a proposed future planting date, a particular relative maturity value that is different than the proposed relative maturity value and maximizes a potential yield for the particular field;
identifying, in the crop relative maturity data, a particular seed type corresponding to the particular relative maturity value; and
sending, over the network to a field manager computing device, a recommendation of the particular seed type for the proposed future planting date for the particular field.

7. The method of claim 1 , further comprising:
receiving, over the network at the server computer system, electronic digital data comprising a plurality of values representing trial planting dates and trial relative maturities at a plurality of fields;
receiving, over the network at the server computer system, electronic digital data comprising a plurality of values representing observed agricultural events at the plurality of fields;
computing a modeled crop yield for each field of the plurality of fields based, at least in part, on the trial planting dates, trial relative maturities, observed agricultural events, and the model of potential crop yield;
receiving, over the network at the server computer system, electronic digital data comprising a plurality of values representing an observed crop yield for each field of the plurality of fields; and
computing an updated model of potential crop yield based, at least in part, on the modeled crop yield for each field of the plurality of fields and the observed crop yield for each field of the plurality of fields.

8. The method of claim 1 , further comprising, generating the model of potential crop yield as a linear function comprising a constant term multiplied by a set of covariates.

9. The method of claim 8 wherein the set of covariates include a planting date term, a square of the planting date term, a relative maturity term, a square of the relative maturity term, and an actual production history term.

10. The method of claim 1 , further comprising:
determining, based, at least in part, on one or more relative maturity maps, one or more planting date maps, and one or more actual production history maps, a dependence of potential yield on location; and
generating the model of potential crop yield as a linear function comprising a constant term multiplied by a location dependent set of covariates.

11. One or more non-transitory computer readable media storing instructions which, when executed by one or more processors, cause performance of a method comprising the steps of:
storing, at a server computer system a mod

Assignees

• Climate Corp

Inventors

• Xu Ying
• Andrejko Erik

Classifications

• A01C21/005 Primary

  Following a specific plan, e.g. pattern · CPC title

• G06Q10/04

  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) · CPC title

• H04L43/045

  for graphical visualisation of monitoring data · CPC title

• H04L67/12

  specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks · CPC title

• A01G22/00 Primary

  Cultivation of specific crops or plants not otherwise provided for · CPC title