LEVERAGING GENETICS AND FEATURE ENGINEERING TO BOOST PLACEMENT PREDICTABILITY FOR SEED PRODUCT SELECTION AND RECOMMENDATION BY FIELD

• US 20200134486A1
• Filed: 10/24/2019
• Published: 04/30/2020
• Est. Priority Date: 10/24/2018
• Status: Active Grant

• Current Assignee: Climate LLC (Bayer AG)
• Original Assignee: The Climate Corporation (Bayer AG)
• Inventors: Jiang, Dongming, Ssegane, Herbert, Moore, III, James C., Bull, Jason K., Wen, Liwei, Reich, Timothy, Ehlmann, Tonya S., Yang, Xiao, Wang, Xuefei, Lutz, Brian, Wang, Guomei
• Granted Patent: US 11,593,674 B2
• Time in Patent Office: Days
• CPC Class Codes: A01C 21/005 Following a specific plan, e.g. pattern
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 20/20 Ensemble learning
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G16B 10/00 ICT specially adapted for evolutionary bioinformatics, e.g. phylogenetic tree construction or analysis
• CPC Class Codes: G16B 20/00 ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
• CPC Class Codes: G16B 20/20 Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
• CPC Class Codes: G16B 40/00 ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
• CPC Class Codes: G16B 40/20 Supervised data analysis

Abstract

An example computer-implemented method includes receiving agricultural data records comprising a first set of yield properties for a first set of seeds grown in a first set of environments, and receiving genetic feature data related to a second set of seeds. The method further includes generating a second set of yield properties for the second set of seeds associated with a second set of environments by applying a model using the genetic feature data and the agricultural data records. In addition, the method includes determining predicted yield performance for a third set of seeds associated with one or more target environments by applying the second set of yield properties, and generating seed recommendations for the one or more target environments based on the predicted yield performance for the third set of seeds. In the present example, the method also includes causing display, on a display device communicatively coupled to the server computer system, the seed recommendations.

Claims

1. A computer-implemented method comprising:

receiving, over a digital data communication network at a server computer system, agricultural data records comprising a first set of yield properties for a first set of seeds grown in a first set of environments;

receiving, over the digital data communication network, genetic feature data related to a second set of seeds, wherein the second set of seeds includes the first set of seeds;

generating, using the server computer system, a second set of yield properties for the second set of seeds associated with a second set of environments by applying a model using the genetic feature data and the agricultural data records, wherein the second set of yield properties fills one or more data gaps from the first set of yield properties;

determine, using the server computer system, predicted yield performance for a third set of seeds associated with one or more target environments by applying the second set of yield properties;

generating, using the server computer system, seed recommendations for the one or more target environments based on the predicted yield performance for the third set of seeds; and

causing display, on a display device communicatively coupled to the server computer system, the seed recommendations.

2. The computer-implemented method of claim 1, wherein the genetic feature data includes genomic marker data, and wherein generating the second set of yield properties includes applying the model using the genomic marker data.

3. The computer-implemented method of claim 1, wherein the genetic feature data includes a pedigree-based kinship matrix, and wherein generating the second set of yield properties includes applying the model using the pedigree-based kinship matrix.

4. The computer-implemented method of claim 1, wherein the genetic feature data includes genomic cluster relationship data, and wherein generating the second set of yield properties includes applying the model using the genomic cluster relationship data.

5. The computer-implemented method of claim 1, wherein the genetic feature data includes a gene marker-based kinship matrix, and wherein generating the second set of yield properties includes applying the model using the gene marker-based kinship matrix.

6. The computer-implemented method of claim 1, wherein generating the predicted yield performance for the third set of seeds includes applying inbred coding to associate genomic-by-environmental features with different seeds.

7. The computer-implemented method of claim 1, generating seed recommendations for the one or more target environments is further based on one or more of hybrid or inbred genetics heterotic groups, genetic markers associated with biotech traits or quantitative trait loci, whole genome genetics markers, long-shaped haplotype, inbred BLUP-GCA (best linear unbiased predication—

general combining ability) yield, yield related phenotypes, or hybrid or inbred disease characteristics.

8. The computer-implemented method of claim 1, wherein generating the predicted yield performance for the third set of seeds includes applying feature engineering to develop genomic-by-environmental features, and using the genomic-by-environmental features in a machine learning model to generate the predicted yield performance.

9. The computer-implemented method of claim 8, wherein feature engineering further includes:

transforming continuous environmental features into one or more distinct feature classes;

using the one or more distinct feature classes to characterize environmental features associated with the agricultural data records;

using the characterized environmental features in the machine learning model to generate the predicted yield performance.

10. The computer-implemented method of claim 9, wherein feature engineering further includes using the one or more distinct feature classes to characterize environmental features associated with the agricultural data records for only one or more agricultural data records with multiple seeds grown in a given environment.

11. One or more non-transitory computer-readable storage media storing instructions which when executed by one or more processors cause performing operations comprising:

receiving agricultural data records comprising a first set of yield properties for a first set of seeds grown in a first set of environments;

receiving genetic feature data related to a second set of seeds, wherein the second set of seeds includes the first set of seeds;

generating a second set of yield properties for the second set of seeds associated with a second set of environments by applying a model using the genetic feature data and the agricultural data records, wherein the second set of yield properties fills one or more data gaps from the first set of yield properties;

determining predicted yield performance for a third set of seeds associated with one or more target environments by applying the second set of yield properties;

generating seed recommendations for the one or more target environments based on the predicted yield performance for the third set of seeds; and

causing display of the seed recommendations.

12. The one or more non-transitory computer-readable storage media of claim 11, wherein the genetic feature data includes genomic marker data, and wherein the operation of generating the second set of yield properties includes applying the model using the genomic marker data.

13. The one or more non-transitory computer-readable storage media of claim 11, wherein the genetic feature data includes a pedigree-based kinship matrix, and wherein the operation of generating the second set of yield properties includes applying the model using the pedigree-based kinship matrix.

14. The one or more non-transitory computer-readable storage media of claim 11, wherein the genetic feature data includes genomic cluster relationship data, and wherein the operation of generating the second set of yield properties includes applying the model using the genomic cluster relationship data.

15. The one or more non-transitory computer-readable storage media of claim 11, wherein the genetic feature data includes a gene marker-based kinship matrix, and wherein the operation of generating the second set of yield properties includes applying the model using the gene marker-based kinship matrix.

16. The one or more non-transitory computer-readable storage media of claim 11, wherein the operation of generating the predicted yield performance for the third set of seeds includes an operation of applying inbred coding to associate genomic-by-environmental features with different seeds.

17. The one or more non-transitory computer-readable storage media of claim 11, wherein the operation of generating seed recommendations for the one or more target environments is further based on one or more of hybrid or inbred genetics heterotic groups, genetic markers associated with biotech traits or quantitative trait loci, whole genome genetics markers, long-shaped haplotype, inbred BLUP-GCA (best linear unbiased predication—

general combining ability) yield, yield related phenotypes, or hybrid or inbred disease characteristics.

18. The one or more non-transitory computer-readable storage media of claim 11, wherein the operation of generating the predicted yield performance for the third set of seeds includes operations of:

applying feature engineering to develop genomic-by-environmental features; and

using the genomic-by-environmental features in a machine learning model to generate the predicted yield performance.

19. The one or more non-transitory computer-readable storage media of claim 18, wherein the operation of applying feature engineering further includes operations of:

transforming continuous environmental features into one or more distinct feature classes;

using the one or more distinct feature classes to characterize environmental features associated with the agricultural data records;

using the characterized environmental features in the machine learning model to generate the predicted yield performance.

20. The one or more non-transitory computer-readable storage media of claim 11, wherein the operation of applying feature engineering further includes an operation of using the one or more distinct feature classes to characterize environmental features associated with the agricultural data records for only one or more agricultural data records with multiple seeds grown in a given environment.