Applications of machine learning algorithms for the improvement of breeding programs in the dairy industry
Bibliographic record
Abstract
In this thesis, Machine Learning (ML) algorithms were applied to improve breeding programs in the dairy industry, with emphasis on two types of traits: conformation and fertility. Firstly, multiple polynomial regression and principal component analyses were used to assess the association of 26 conformation traits with the Pro$ selection index, providing information to guide the dairy industry on which traits are more important from a monetary standpoint and which could likely be removed from genetic evaluation or recording programs. Secondly, a flexible and robust methodology to vectorize any text-based Breeding Protocol Descriptions (BPD) and develop ML classification models to identify Timed Artificial Insemination (TAI) protocols was developed. Timed Artificial Insemination masks an animal’s true fertility performance, reducing the accuracy of genetic evaluations for fertility traits. Mitigating this potential bias is challenging since there is a lack of specificity and uniformity in the recording of BPD by dairy farmers. Correct identification of TAI protocols would open the opportunity for unbiased genetic evaluation of animals based on their natural fertility. Lastly, in a third study, decision tree-based algorithms were applied to correctly determine the outcome of historical insemination records as open, pregnant, or aborted. The current Canadian Data Exchange System currently stores insemination records performed by artificial insemination (AI) technicians, but those do not include the Insemination Outcome (IO), which is recorded on the farmers’ herd management software. Therefore, researchers and geneticists do not have access to IO on a national scale for fertility research and genetic evaluations. Therefore, classification models proposed could have a positive impact on the dairy industry by using high performance predictions of IO to broaden the opportunity for new fertility research and genetic evaluations. Altogether, this thesis leveraged ML algorithms to improve breeding programs in the industry dairy by providing understanding on the monetary importance of individual conformation traits, a robust methodology to identify breedings that used hormonal synchronization protocols, and models to correctly determine the outcome of historical insemination records.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.023 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".