Methods and systems for identifying hybrids for use in plant breeding

1. A method for use in identifying hybrids for use in a plant breeding pipeline, the method comprising:

accessing a data structure including data representative of a pool of hybrids, each hybrid in the pool of hybrids including one male line and one female line, wherein the male lines and the female lines of the hybrids in the pool of hybrids define a pool of male lines and a pool of female lines;

determining, by at least one computing device, a prediction score for at least a portion of the hybrids included in the pool of hybrids based on the data included in the data structure, the prediction score indicative of a probability of selection and/or a probability of success of the hybrid based on historical data;

selecting, by the at least one computing device, a group of hybrids from the pool of hybrids based on the prediction score;

identifying, by the at least one computing device, a set of hybrids, from the group of hybrids, based on: an expected performance of the set of hybrids, a diversity of usage of the male and female lines in the set of hybrids, and one or more factors associated with the hybrids and/or the male and female lines; and

directing the set of hybrids to a further iteration in a phase of the breeding pipeline or to a different phase of the breeding pipeline.

2. The method of claim 1 , wherein the historical data includes historical phenotypic data related to a plurality of hybrids and/or to the male and female lines of the plurality of hybrids and historical selections for each hybrid in the plurality of hybrids; and

further comprising generating, by the at least one computing device, a prediction model based on the historical phenotypic data and the historical selections, wherein the plurality of hybrids and/or the male and female lines of the plurality of hybrids are associated with plant material of a type consistent with a plant type of the pool of hybrids; and

wherein determining the prediction score for the at least a portion of the hybrids included in the pool of hybrids includes determining the prediction score based on the prediction model.

3. The method of claim 1 , wherein the one or more factors includes one or more of: line distribution for the pool of male lines, line distribution for the pool of female lines, trait(s) or trait profiles, market segmentation, risk, product cost, trait availability, or trait readiness.

4. The method of claim 1 , wherein identifying the set of hybrids is based on:

diversity of usage of the female lines, as maximization of:

λ p ( b i f ) T y * f −λ d ( y * f ) T S f y * f ,

where b i f is a probability of success of the female line, and S f is a pairwise matrix of homology of the pool of female lines, subject to:

1 T y * f =1, 0≤ y * f ≤1; and

diversity of usage of the male lines, as maximization of:

λ p ( b i m ) T y * m −λ d ( y * m ) T S m y * m

where b i m is a probability of success of the male line, and S f is a pairwise matrix of homology of the pool of male lines, subject to:

1 T y * m =1,0≤ y * m ≤1.

5. The method of claim 1 , wherein the data includes phenotypic data representative of the pool of hybrids; and

wherein selecting the group of hybrids includes selecting the group of hybrids when the prediction score of the selected hybrid satisfies one or more thresholds.

6. The method of claim 1 , wherein directing the set of hybrids to a different phase of the breeding pipeline includes including a plant product in a growing space of the breeding pipeline, after the set of hybrids is identified, the plant product based on at least one hybrid in the identified set of hybrids.