Hybrid seed selection and seed portfolio optimization by field

Patent metadata

Field	Value
Publication number	US-12373752-B2
Application number	US-202318103061-A
Country	US
Kind code	B2
Filing date	Jan 30, 2023
Priority date	Nov 9, 2017
Publication date	Jul 29, 2025
Grant date	Jul 29, 2025

Abstract

Systems and methods are provided for managing hybrid seeds for planting. One example computer-implemented method includes receiving a first dataset of hybrid seeds for planting on a target field, where the first dataset includes probability of success values and historical agricultural data for the hybrid seeds, and selecting a subset of hybrid seeds of the first dataset based on the probability of success values. The method also includes generating representative yield values for the subset of hybrid seeds based on the historical agricultural data, generating risk values for the subset of hybrid seeds based on the historical agricultural data, and generating a second dataset of hybrid seeds for planting based on the risk values, the representative yield values, and properties for the target field. The method further includes causing displaying the representative yield values and the risk values related to the second dataset of hybrid seeds for planting.

First claim

What is claimed is:

1. A computer-implemented method of managing hybrid seeds for planting, the method comprising:
receiving, by a processor of an agricultural intelligence computer system, a first dataset of hybrid seeds for planting on one or more target fields, the first dataset including probability of success values and historical agricultural data for the hybrid seeds, the historical agricultural data including historical yield values, harvest time information, and relative maturity of a hybrid seed, the probability of success values representative of, for each hybrid seed, a probability of a successful yield relative to an average yield of other ones of the hybrid seeds with a same relative maturity;
selecting, by the processor, a subset of hybrid seeds of the first dataset of hybrid seeds based on the probability of success values relative to a target probability filtering threshold, the target probability filtering threshold indicative of a mean yield of other ones of the hybrid seeds of the first dataset, which are not selected into the subset of hybrid seeds;
generating, by the processor, a representative yield value for each hybrid seed in the subset of hybrid seeds based on one or more averages, per growth cycle, of the historical agricultural data for said hybrid seed;
generating, by the processor, risk values for the subset of hybrid seeds based on yield variability of the hybrid seeds over time as indicated in the historical agricultural data;

generating, by the processor, a second dataset of hybrid seeds for planting based on the risk values, the representative yield values, and one or more properties for the one or more target fields, wherein the second dataset includes ones of the hybrid seeds from the subset of hybrid seeds that have representative yield values above a specific yield threshold and risk values below a specific risk target, where the specific yield threshold and specific risk target are defined by a relative curve; and
in response to at least generating the second dataset of the hybrid seeds for planting, controlling, by the processor, an agricultural machine to plant, in the one or more target fields, hybrid seeds of the second dataset.

2. The computer-implemented method of claim 1 , wherein a higher risk value for a hybrid seed of the risk values is indicated by the yield variability based on-a higher year-to-year yield return.

3. The computer-implemented method of claim 1 , wherein generating the second dataset includes determining a relationship between the representative yield value for a specific hybrid seed and the risk value associated with the specific hybrid seed.

4. The computer-implemented method of claim 1 , wherein generating the second dataset includes determining an expected yield return for a specified amount of risk.

5. The computer-implemented method of claim 1 , wherein generating the second dataset includes selecting a first hybrid seed of the subset of hybrid seeds with a first risk value above a first threshold and a second hybrid seed of the subset of hybrid seeds with a second risk value below a second threshold; and
wherein the first hybrid seed and the second hybrid seed have corresponding yield values above a third threshold.

6. The computer-implemented method of claim 1 , wherein generating the second dataset includes fitting a frontier curve from the representative yield values and risk values such that a specific hybrid seed to which a specific point on the frontier curve corresponds that has a higher yield is associated with a higher risk.

7. The computer-implemented method of claim 1 , further comprising receiving, by the processor, geo-location information for the one or more target fields, the geo-location information including the one or more properties for the one or more target fields; and
wherein the subset of hybrid seeds is associated with a seed portfolio specific to a particular grower.

8. The computer-implemented method of claim 1 , further comprising:
causing display, on a display device of a field manager computing device in communication, via one or more networks, with the agricultural intelligence computer system, of the second dataset of hybrid seeds;
determining an allocation quantity for each of the second dataset of hybrid seeds based on an amount and location of each target field of the one or more target fields; and
causing, by the processor, display of, on the display of the field manager computing device, seed allotments and placement information for each of the hybrid seeds of the second dataset on a map for the one or more target fields; and
wherein controlling the agricultural machine is further in response to a user input to plant the one or more fields based on the displaying of the allotments and placement information for each of the hybrid seeds of the second dataset.

9. The computer-implemented method of claim 1 , wherein controlling the agricultural machine includes controlling the agricultural machine, via-an executable script transmitted to the agricultural machine, to cause the agricultural machine to plant one or more target fields with the second dataset of hybrid seeds.

10. A server computer system comprising an agricultural intelligence computer system, which includes: one or more processors; one or more non-transitory computer-readable storage media storing executable instructions which, when executed using the one or more processors, cause the one or more processors to perform:
receiving a first dataset of hybrid seeds for planting on one or more target fields, the first dataset including probability of success values and historical agricultural data for the hybrid seeds, the historical agricultural data including historical yield values, harvest time information, and relative maturity of a hybrid seed, the probability of success values representative of, for each hybrid seed, a probability of a successful yield relative to an average yield of other ones of the hybrid seeds with a same relative maturity;
selecting a subset of hybrid seeds of the first dataset of hybrid seeds based on the probability of success values relative to a target probability filtering threshold the target probability filtering threshold indicative of a mean yield of other ones of seeds of the first dataset, which are not selected into the subset of hybrid seeds;
generating a representative yield value for each hybrid seed in the subset of hybrid seeds based on one or more averages, per growth cycle, of the historical agricultural data for said hybrid seed;
generating risk values for the subset of hybrid seeds based on yield variability of the hybrid seeds over time as indicated in the historical agricultural data;
generating a second dataset of hybrid seeds for planting based on the risk values, the representative yield values, and one or more properties for the one or more target fields, wherein the second dataset includes ones of the hybrid seeds from the subset of hybrid seeds that have representative yield values above a specific yield threshold and risk values below a specific risk target, where the specific yield threshold and specific risk target are defined by a relative curve; and
in response to generating the second dataset of the hybrid seeds for planting, controlling an agricultural machine to plant, in the one or more target fields, hybrid seeds of the second dataset.

11. The server computer system of claim 10 , wherein a higher risk value for a hybrid seed of the risk values indicated by the yield variability based on a higher year-to-year yield return.

12. The server computer system of claim 10 , wherein the executable instructions, when executed using the one or mo

Assignees

• Climate Llc

Inventors

• Bull Jason Kendrick
• Ehlmann Tonya S
• Jiang Dongming
• Reich Timothy
• Wimbush Samuel Alexander
• Xie Yao
• Yang Xiao

Classifications

• A01B79/005

  Precision agriculture · CPC title

• G06Q50/02

  Agriculture; Fishing; Forestry; Mining · CPC title

• A01C21/005

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

• G06Q10/06313 Primary

  Resource planning in a project environment · CPC title