EP-4734746-A2 - SYSTEMS AND METHODS FOR SELECTING SEED PRODUCTS FOR PLANTING IN GROWING SPACES

EP4734746A2EP 4734746 A2EP4734746 A2EP 4734746A2EP-4734746-A2

Abstract

Systems and methods for planting specified seed products in target growing spaces. An example method includes receiving a request for a planting recommendation related to seeding of a target growing space and, in response, determining, using one or more seed placement prediction models, a prediction output including a predicted yield for multiple seed products at the target growing space at each of one or more different weather conditions. The method also includes determining, using an optimization model, a seed planting recommendation output, based on at least the prediction output and at least one grower constraint parameter associated with the target growing space, where the seed planting recommendation output includes at least one of the multiple seed products, and then directing planting of the at least one of the multiple seed products at the target growing space based on the seed planting recommendation output.

Inventors

BEELER, Charlie
KARACA, MESERRET
KIM, MINKYU
LAU, MATTHEW
LIU, BING
MUKHERJEE, NILOY
NAVARRO, Martin
OSTOVAR, Azadeh Sanayi
REJAILI, Rodrigo
SALVADOR, Matheus
SUNDARAMOORTHI, Durai
CAO, Liaoliao
TASLIMI, Bijan
TRAN, HUONG
VANDERKRAATS, NATHAN
WINDEMUTH, Diana
ZHANG, HONG
CASQUILHO, Camila
DONG, Lingxiu
GUERIN, LeAnna
IBERG, Michael
JI, Yixuan
JIANG, DONGMING
JOHNSON, MICHAEL

Assignees

Monsanto Technology LLC

Dates

Publication Date: 20260506
Application Date: 20240626

Claims (1)

Attorney Docket No. 5089C-000170-WO-POA CLAIMS What is claimed is: 1. A computer-implemented method for directing seed products to growing spaces, the computer-implemented method comprising: receiving, by a computing device, a request for a planting recommendation related to seeding of a target growing space, the request including seed product data and location data relating to the target growing space, the seed product data including multiple identifiers each associated with a different one of multiple seed products available for planting at the target growing space; accessing, by the computing device, one or more seed placement prediction models consistent with the location data; determining, by the computing device, using the one or more seed placement prediction models, a prediction output, based, at least, on the location data and on weather data, the prediction output including a predicted yield for the multiple seed products at each of one or more different weather conditions, seed densities, and/or planting dates; accessing, by the computing device, an optimization model consistent with the target growing space; determining, by the computing device, using the optimization model, a seed planting recommendation output, based on at least the prediction output and at least one grower constraint parameter associated with the target growing space, the seed planting recommendation output including at least one of the multiple seed products; and directing, by the computing device, planting of the at least one of the multiple seed products at the target growing space, based on the seed planting recommendation output. 2. The computer-implemented method of claim 1, further comprising training the one or more seed placement prediction models, based on historical data associated with multiple growing spaces and a set of multiple seed products. 3. The computer-implemented method of claim 2, wherein the set of multiple seed products includes the multiple seed products. Attorney Docket No. 5089C-000170-WO-POA 4. The computer-implemented method of claim 2, wherein inputs for training the one or more seed placement prediction models include, for each of the multiple growing spaces: a location of the growing space; and a yield of one or more of the multiple seed products at the growing space. 5. The computer-implemented method of claim 4, wherein the inputs for training the one or more seed placement prediction models include, for each of the multiple growing spaces, at least one of soil data of the growing space, weather data associated with the growing space, and hybrid/genetic seed data associated with seed products planted in the growing space. 6. The computer-implemented method of claim 1, further comprising training the optimization model, based on historical seed portfolio data associated with multiple growing spaces and multiple seed product types. 7. The computer-implemented method of claim 6, wherein inputs for training the optimization model include, for each of the multiple growing spaces: a location of the growing space; and a yield of a portfolio including at least two of the multiple seed product types at the growing space. 8. The computer-implemented method of claim 7, wherein the inputs for training the optimization model include, for each of the multiple growing spaces, at least one of field information of the growing space, available seed supply list information associated with the growing space, weather information associated with the growing space, and grower constraint information associated with the growing space. 9. The computer-implemented method of claim 8, wherein the grower constraint information includes at least one of a grower seeding rate preference, a grower relative maturity spread preference, a preferred range of different varieties, a minimum and maximum product volume preference, a trait mix preference, and a brand mix preference. Attorney Docket No. 5089C-000170-WO-POA 10. The computer-implemented method of claim 1, wherein: determining, by the computing device, using the one or more seed placement prediction models, the prediction output includes generating a three-dimensional matrix output of yield predictions, the three dimensions of the matrix output including seed type, weather condition(s), and predicted yield. 11. The computer-implemented method of claim 1, wherein the one or more seed placement prediction models include a multilayer perceptron neural network and/or an XGBoost model. 12. The computer-implemented method of claim 1, wherein the seed planting recommendation output includes a portfolio having more than one of the multiple seed product types available for planting at the target growing space. 13. The computer-implemented method of claim 1, further comprising seeding the target growing space in response to the seed planting recommendation output. 14. The computer-implemented method of claim 13, further comprising: receiving, at a communication device of a user associated with the target growing space, the seed planting recommendation output; and causing operation of one or more agricultural apparatuses at the target growing space to apply the at least one of the multiple seed products to the target growing space. 15. A system for use in directing seed products to growing spaces, the system comprising at least one computing device configured to: receive a request for a planting recommendation related to seeding of a target growing space, the request including seed product data and location data relating to the target growing space, the seed product data including multiple identifiers each associated with a different one of multiple seed products available for planting at the target growing space; access one or more seed placement prediction models consistent with the location data; Attorney Docket No. 5089C-000170-WO-POA determine, using the one or more seed placement prediction models, a prediction output, based, at least, on the location data and on weather data, the prediction output including a predicted yield for the multiple seed products at each of one or more different weather conditions, seed densities, and/or planting dates; access an optimization model consistent with the target growing space; determine, using the optimization model, a seed planting recommendation output, based on at least the prediction output and at least one grower constraint parameter associated with the target growing space, the seed planting recommendation output including at least one of the multiple seed products; and direct planting of the at least one of the multiple seed products at the target growing space, based on the seed planting recommendation output. 16. The system of claim 15, wherein the at least one computing device is further configured to train the one or more seed placement prediction models, based on historical data associated with multiple growing spaces and a set of multiple seed products. 17. The system of claim 16, wherein the set of multiple seed products includes the multiple seed products; and wherein inputs for training the one or more seed placement prediction models include, for each of the multiple growing spaces: a location of the growing space; and a yield of one or more of the multiple seed products at the growing space. 18. The system of claim 17, wherein the inputs for training the one or more seed placement prediction models include, for each of the multiple growing spaces, at least one of soil data of the growing space, weather data associated with the growing space, and hybrid/genetic seed data associated with seed products planted in the growing space. 19. The system of any one of claim 15, wherein the at least one computing device is further configured to train the optimization model, based on historical seed portfolio data associated with multiple growing spaces and multiple seed product types; and Attorney Docket No. 5089C-000170-WO-POA wherein inputs for training the optimization model include, for each of the multiple growing spaces: a location of the growing space; and a yield of a portfolio including at least two of the multiple seed product types at the growing space. 20. The system of any claim 15, wherein the at least one computing device is configured, in order to determine the prediction output, to generate a three-dimensional matrix output of yield predictions, the three dimensions of the matrix output including seed type, weather condition(s), and predicted yield. 21. The system of claim 15, further comprising an agricultural apparatus configured to plant the at least one of the multiple seed products at the target growing space; and wherein the agricultural apparatus is configured to receive the seed planting recommendation output from the at least one computing device and plant the at least one of the multiple seed products at the target growing space in response to the seed planting recommendation output. 22. The system of claim 21, further comprising a communication device associated with the user, the communication device configured to receive the seed planting recommendation output from the at least one computing device, and whereby the agricultural apparatus is configured to plant the at least one of the multiple seed products at the target growing space in response to the seed planting recommendation.

Description

Attorney Docket No. 5089C-000170-WO-POA SYSTEMS AND METHODS FOR SELECTING SEED PRODUCTS FOR PLANTING IN GROWING SPACES CROSS-REFERENCE TO RELATED APPLICATION [0001] This application claims the benefit of, and priority to, U.S. Provisional Application No. 63/523,633, filed June 27, 2023. The entire disclosure of the above application is incorporated herein by reference. FIELD [0002] The present disclosure generally relates to systems and methods for planting specified seed products in growing spaces, and in particular, to systems and methods for use in selection of types of seed products for planting in the growing spaces based on predicted yield and variance for multiple seed products. BACKGROUND [0003] This section provides background information related to the present disclosure which is not necessarily prior art. [0004] It is known for seeds to be grown in fields for commercial purposes, whereby resulting plants, or parts thereof, are sold by the growers for business purposes. For example, soybeans may be grown by a grower in a field owned by the grower, and the soybeans grown and harvested from the field may then be sold. Similarly, in another example, corn may be grown by a grower in a field owned by the grower, and the corn grown and harvested from the field may then be sold. Consequently, growers often seek to plant particular seeds (e.g., corn versus soybeans, soybean seed type A versus soybean seed type B, etc.), based on specific aims of the growers, specific climate conditions (e.g., drought tolerance, etc.), and disease resistance. In addition, growers may also estimate future yield performance of different candidate crop types, in order to make decisions regarding which types of crop seeds to plant for a growing season. Attorney Docket No. 5089C-000170-WO-POA SUMMARY [0005] This section provides a general summary of the disclosure and is not a comprehensive disclosure of its full scope or all of its features. [0006] Example embodiments of the present disclosure generally relate to computer- implemented methods for use in determining types of seed products for planting in growing spaces and directing placement of such seed products in the growing spaces. In one example embodiment, a method for directing seed products to growing spaces generally includes: receiving, by a computing device, a request for a planting recommendation related to seeding of a target growing space, the request including seed product data and location data relating to the target growing space, the seed product data including multiple identifiers each associated with a different one of multiple seed products available for planting at the target growing space; accessing, by the computing device, one or more seed placement prediction models consistent with the location data; determining, by the computing device, using the one or more seed placement prediction models, a prediction output, based, at least, on the location data and on weather data, the prediction output including a predicted yield for the multiple seed products at each of one or more different weather conditions, seed densities, and/or planting dates; accessing, by the computing device, an optimization model consistent with the target growing space; determining, by the computing device, using the optimization model, a seed planting recommendation output, based on, at least, the prediction output and at least one grower constraint parameter associated with the target growing space, the seed planting recommendation output including at least one of the multiple seed products; and directing, by the computing device, planting of the at least one of the multiple seed products at the target growing space, based on the seed planting recommendation output. [0007] Example embodiments of the present disclosure generally relate to systems for use in directing seed products to growing spaces. In one example embodiment, such a system generally includes at least one computing device configured to: receive a request for a planting recommendation related to seeding of a target growing space, the request including seed product data and location data relating to the target growing space, the seed product data including multiple identifiers each associated with a different one of multiple seed products available for planting at the target growing space; access one or more seed placement prediction models consistent with the location data; determine, using the one or more seed placement prediction Attorney Docket No. 5089C-000170-WO-POA models, a prediction output, based, at least, on the location data and on weather data, the prediction output including a predicted yield for the multiple seed products at each of one or more different weather conditions, seed densities, and/or planting dates; access an optimization model consistent with the target growing space; determine, using the optimization model, a seed planting recommendation output, based on at least the prediction out