194 Evaluation of a method to optimize diets of individual dairy cows to maximize income over feed cost
Bibliographic record
Abstract
Abstract Recent optimization methods have demonstrated the potential to maximize marginal profits in beef (Marques et al., 2020) and dairy (Campos et al., 2023) by optimizing diet formulation. These methods present an opportunity to explore how diets could be optimized for individual dairy cows, such as in a closed-loop precision feeding system. Therefore, our objectives were to 1) compare individual income over feed costs (IOFC), calculated with observed dry matter intake (DMI), milk yield (MY), milk protein and milk fat, with a predicted IOFC for the same diet and cows using the NASEM (2021) model, and 2) optimize the inclusion rate of ingredients in the diet to maximize predicted IOFC. Previously, 20 multiparous (lactation 2 through 4) and 9 primiparous cows, ranging from 22 to 472 d in milk (DIM), were housed in a free-stall pen at the Ontario Dairy Research Centre (Canada) equipped with sensors to record DMI, body weight (BW; walk-over-weight) and body condition score (BCS; DeLavel 3D camera), in addition to daily MY, weekly milk component tests, and 4 X/d respiratory gas exchange measurements (GreenFeed, C-Lock Inc, USA) for estimation of daily energy flows (Kedzierski, 2020). Weekly means for each cow were used to evaluate IOFC in this study (n = 116). Each IOFC was calculated as milk revenue minus total feed cost. Milk revenue was calculated from milk fat, protein and other solids, consistent with pricing on Canadian dairy farms. The observed IOFC was calculated using the observed MY, milk components and DMI, and the same diet formulation and costs for all cows, whereas the predicted IOFC estimated these values using the NASEM (2021) model with all available observed animal inputs (e.g., BW, BCS, DIM). However, the observed DMI and MY had to be provided initially for the model, as the DMI prediction equation requires a target MY, but the prediction of MY requires DMI. Final predicted DMI and MY values were used in the calculation of predicted IOFC. The differential evolution algorithm from the ‘SciPy’ package (v 1.11.4) in python (v 3.12.0) was used to maximize IOFC by adjusting the inclusion of wheat straw, alfalfa silage, corn silage and high moisture corn grain, while fixing minerals to their original proportions. Overall, the concordance correlation coefficient (CCC) indicated moderate agreement (0.62) between the predicted IOFC and observed IOFC and good agreement (0.99) between the predicted IOFC and the optimized IOFC, suggesting the optimization method was able to select diets to meet a similar objective. Results indicate that a strategy is needed to minimize the residual error between predicted and observed values for individual cows, such as algebraic reparameterization of the NASEM model, before using an optimization method to automatically formulate diets.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".