Farm specific estimates of forage variability result in larger optimal control limits for forage quality monitoring.

Variation in forage composition decreases the accuracy of diets delivered to dairy cows. However, variability of forages can be managed using a renewal reward model (RRM) and genetic algorithm (GA) to optimize sampling and monitoring practices for farm conditions. Specifically, use of quality-control-charts to monitor forage composition can identify changes in composition for which adjustment in the formulated diet will result in a better match of the nutrients delivered to cows. The objectives of this study were 1) assess the use of a clustering algorithm to estimate the mean time the process is stable or in-control (d) (TStable) and the magnitude of the change in forage composition between stable periods (ΔForage) for corn silage and alfalfa-grass silage which are input parameters for the RRM; 2) compare optimized farm-specific sampling practices (number of samples (n), sampling interval (TSample) and control limits (ΔLimit) using previously proposed defaults and our estimates for the TStable and ΔForage input parameters; and 3) conduct a simulation study to compare the number of recommended diet changes costs of quality control under the proposed sampling and monitoring protocols. We estimated the TStable and ΔForage parameters for corn silage NDF and starch and alfalfa-grass silage NDF and CP using a k-means clustering approach applied to forage samples collected from 8 farms, 3x/week during a 16-week period. We compared 4 sampling and monitoring protocols that resulted from the 2 methods for estimating TStable and ΔForage (default values and our proposed method) and either optimizing only the control limit (Optim1) or optimizing the control limits, the number of samples, and the number of days between sampling (Optim2). We simulated the outcomes of implementing the optimized monitoring protocols using a quality control chart for corn silage and alfalfa-grass silage of each farm. Estimates of T^Stable and Δ^Forage from the k-means clustering analysis were, respectively, shorter and larger than previously proposed default values. In the simulated quality control monitoring, larger Δ^Forage estimates increased the optimized ΔLimit resulting in fewer detected shifts in composition of forages and a lower frequency of false alarms and a lower quality control cost ($/d). Recommended diet reformulation intervals from the simulated quality control analysis were specific for the type of forage and farm management practices. The median of the diet reformulation intervals for all farms using our optimal protocols was 14 d (Q1 = 8, Q3 = 26) for corn silage and 16 d (Q1 = 8, Q3 = 26) for alfalfa-grass silage.

Partitioning of nutrient variation in alfalfa and corn silage by source on New York dairy farms.

Variation in feed components contributes to variation and uncertainty of diets delivered to dairy cows. Forages often have a high inclusion rate (50 to 70% of DM fed) and variable composition, thus are an important contributor to nutrient variability of delivered diets. Our objective was to quantify the variation and identify the main sources of variability in corn silage and alfalfa-grass haylage composition at harvest (fresh forage) and feed-out (fermented forage) on NY dairy farms. Corn silage and alfalfa-grass haylage were sampled on 8 NY commercial dairy farms during harvest in the summer and fall of 2020 and during their subsequent feed-out in the winter and spring of 2021. At harvest, a composite sample of fresh chopped forage of every 8-ha section of individual fields was collected from piles delivered for silo filling. During a 16-week feed-out period, 2 independent samples of each forage were collected 3 times per week. The fields-of-origin of each forage sample during feed-out were identified and recorded using silo maps created at filling. A mixed-model analysis quantified the variance of corn silage DM, NDF, and starch and haylage DM, NDF, and CP content. Fixed effects included soil type, weather conditions, and management practices during harvest and feed-out while random effects were farm, silo unit, field, and day. At harvest, between-farm variability was the largest source of variation for both corn silage and haylage, but within-farm sources of variation exceeded farm-to-farm variation for haylage at feed-out. At feed-out, haylage DM and NDF content had higher within-farm variability than corn silage. In contrast, corn silage starch showed higher within-farm variation at feed-out than haylage CP content. For DM content at feed-out, day-to-day variation was the most relevant source of within-farm variation for both forages. However, for the nutrient components at feed-out (NDF and CP for haylage; NDF and starch for corn silage) silo-to-silo variation was the largest source of variability. Weather conditions systematically explained a proportion of the farm-to-farm variability for both forages at harvest and feed-out. We concluded that because of the high farm-to-farm variation, corn silage and haylage must be sampled on individual farms. We also concluded that due to the high silo-to-silo variability, and the still significant day-to-day and field-to-field variability within-farm, corn silage and haylage should be sampled within individual silos to better capture changes in forage components at feed-out.

Graduate Student Literature Review: Considerations for nutritional grouping in dairy farms.

Each cow in a group has different nutritional requirements even if the group is formed by cows of similar age, number of lactations, and lactation stage. Common dairy farm management setup does not support formulating a diet that accurately matches individual nutritional requirements for each cow; therefore, a proportion of cows in the group will be overfed and another proportion underfed. Overfeeding and underfeeding cows increases the risk of metabolic diseases, decreases milk production, and increases nutrient waste. Consequently, profitability of dairy farms and the environment are negatively affected. Nutritional grouping is a management strategy that aims to allocate lactating cows homogeneously according to their nutritional requirements. Groups of cows with more uniform nutritional requirements facilitates the formulation of more accurate diets for the group. Current availability of large data streams on dairy farms facilitates the design of algorithms to implement nutritional grouping. Our review summarizes important factors to consider when grouping cows, describes nutritional grouping approaches, and summarizes benefits of implementing nutritional grouping in dairy farms.

Improving nutritional accuracy and economics through a multiple ration-grouping strategy.

The objective of this study was to develop a model application to systematize nutritional grouping (NG) management in commercial dairy farms. The model has 4 sub-sections: (1) real-time data stream integration, (2) calculation of nutritional parameters, (3) grouping algorithm, and (4) output reports. A simulation study on a commercial Wisconsin dairy farm was used to evaluate our NG model. On this dairy farm, lactating cows (n = 2,374 ± 185) are regrouped weekly in 14 pens according to their parity and lactation stage, for which 9 diets are provided. Diets are seldom reformulated and nutritional requirements are not factored to allocate cows to pens. The same 14 pens were used to simulate the implementation of NG using our model, closely following the current farm criteria but also including predicted nutritional requirements (net energy for lactation and metabolizable protein; NEL and MP) and milk yield in an attempt to generate more homogeneous groups of cows for improved diet accuracy. The goal of the simulation study was to implement a continuous weekly system for cows' pen allocation and diet formulation. The predicted MP and NEL requirements from the NG were used to formulate the diets using commercial diet formulation software and the same feed ingredients, feed prices, and other criteria as the current farm diets. Diet MP and NEL densities were adjusted to the nutritional group requirements. Results from the simulation study indicated that the NG model facilitates the implementation of an NG strategy and improves diet accuracy. The theoretical diet cost and predicted nitrogen supply with NG decreased for low-nutritional-requirement groups and increased for high-nutritional-requirement groups compared with current farm groups. The overall average N supply in diets for NG management was 15.14 g/cow per day less than the current farm grouping management. The average diet cost was $3,250/cow per year for current farm management and $3,219/cow per year for NG, which resulted in a theoretical $31/cow per year diet cost savings.

Symposium review: Real-time continuous decision making using big data on dairy farms.

We are developing a real-time, data-integrated, data-driven, continuous decision-making engine, The Dairy Brain, by applying precision farming, big data analytics, and the Internet of Things. This is a transdisciplinary research and extension project that engages multidisciplinary scientists, dairy farmers, and industry professionals. Dairy farms have embraced large and diverse technological innovations such as sensors and robotic systems, and procured vast amounts of constant data streams, but they have not been able to integrate all this information effectively to improve whole-farm decision making. Consequently, the effects of all this new smart dairy farming are not being fully realized. It is imperative to develop a system that can collect, integrate, manage, and analyze on- and off-farm data in real time for practical and relevant actions. We are using the state-of-the-art database management system from the University of Wisconsin-Madison Center for High Throughput Computing to develop our Agricultural Data Hub that connects and analyzes cow and herd data on a permanent basis. This involves cleaning and normalizing the data as well as allowing data retrieval on demand. We illustrate our Dairy Brain concept with 3 practical applications: (1) nutritional grouping that provides a more accurate diet to lactating cows by automatically allocating cows to pens according to their nutritional requirements aggregating and analyzing data streams from management, feed, Dairy Herd Improvement (DHI), and milking parlor records; (2) early risk detection of clinical mastitis (CM) that identifies first-lactation cows under risk of developing CM by analyzing integrated data from genetic, management, and DHI records; and (3) predicting CM onset that recognizes cows at higher risk of contracting CM, by continuously integrating and analyzing data from management and the milking parlor. We demonstrate with these applications that it is possible to develop integrated continuous decision-support tools that could potentially reduce diet costs by $99/cow per yr and that it is possible to provide a new dimension for monitoring health events by identifying cows at higher risk of CM and by detecting 90% of CM cases a few milkings before disease onset. We are securely advancing toward our overarching goal of developing our Dairy Brain. This is an ongoing innovative project that is anticipated to transform how dairy farms operate.