The solution to the current fertility crisis faced by the dairy industry lies in data according to Professor Geert Opsomer, associate professor of bovine herd health at Ghent University. This drive towards the use of data and technology to improve both productivity and welfare in the dairy industry, is highlighted in a pioneering project by the University of Wisconsin.
In this unique study, a multi-disciplinary team of researchers aim to apply data to all aspects of dairy farming. Using artificial intelligence they aim to integrate all data which can be collected on a diary farm in one place. A huge variety of data will be sampled, from feed efficiency, to rumination activity, to milk prices, before being integrated on a “virtual dairy farm brain”. This will allow the data collected to be examined as a whole, allowing better farmer feedback to be provided so they can make more informed decisions based on what is happening at that moment. If it is successful this project will revolutionize the use of role of data in dairy farming.
Here at eCow, the use of technology to provide solutions to the dairy industry is something we are also passionate about. Our VetPack can be used to detect Subclinical Acute Rumen Acidosis (SARA) by deploying boluses to continually measure rumen pH. The data fed back by the boluses can then be used to advise nutrition and management practices to minimize the risk of SARA. Our boluses have also been mentioned in a recent article in the Journal of Dairy Research which examined the crucial role engineering and technology play in the welfare of dairy animals.
A group of US researchers are working on a dairy data management project to aid efficient production.
The multi-disciplinary team from the University of Wisconsin (UW)-Madison are developing a “virtual dairy farm brain” that will collect and integrate all of a farm’s data streams in real time. The system will then use artificial intelligence to analyze the data with the aim of helping farmers improve management decisions.
The UW team includes dairy scientists, agricultural economists and computer scientists, in collaboration with UW’s Center for High Throughput Computing. They have begun the project by streaming data on around 4,000 cows, in three Wisconsin herds, to a campus-based server.
The university explained dairy farms generate various types of data from many sources. Data can include pounds of feed consumed, amount of milk produced, rumination, activity levels and aspects such as internal temperature. In addition, farms have other data relating to each cow such as sire records and genomic tests, and off-farm data like the weather, and prices of milk and feed.
Mitch Breunig, one of the dairy producers involved in the project, commented: “We’re generating a lot of data every day from a bunch of different systems – a feed system, a milk system, how much milk you actually ship. And none of those systems talk to each other.
“You can enter it by hand but you haven’t got the time, so you don’t do it for a week and then you go back and do the data and you cram it in. Unless you’re doing it every day it’s hard to get it right. You’re always looking way too far in the rear-view mirror. The data is generated every day. We should be able to look at it every day.”
Victor Cabrera, a UW-Madison dairy science professor who develops software that helps dairy farmers evaluate management options and team leader on the project, said: “Dairy farms have embraced a lot of technologies that generate vast amounts of data. The problem is that farmers haven’t been able to integrate this information to improve whole-farm decision-making.
“It’s not just a matter of having access to systems that can handle big data sets. We also need the expertise to filter it. We are collecting a lot of data but a lot of it is repetitious or not relevant. We need to be able to filter out the noise and attach identifiers to each type of data. To do this in real time is not a trivial thing.”
Second phase focuses on prediction
After the initial data streaming, the project’s second phase will be using artificial intelligence to improve accuracy in predicting the outcome of various management options. Computer scientists working on the team will generate algorithms that analyze what is happening on farms to see how they can improve predictions.
The final phase of the project will be to apply what the researchers have learned to create intuitive, cloud-based decision-support tools, enabling farmers to use real-time data to make smarter management decisions.
Prof Cabrera said: “We called this project the virtual dairy farm brain because we’re trying to mimic the thinking of a very good dairy farm manager. We’re going to start by seeing what the manager decides to do with the data and then see what our system would come up with as potentially the best decision.
“We think the methodology should apply to any farm. It could be adjusted to suit whatever data are available. The basic approach would be very similar on a 100-cow farm or an 8,000-cow operation. The concept would not be different as long as you have good quality data. And every farm is generating data. It’s just a question of how it’s used.”
The project will span two years and when complete, Prof Cabrera is aiming to follow it with a larger study involving 100-200 farms that representing various sizes and management styles.
Adoption of data tools for livestock
In the last few years, the use of data in animal health has been a hot topic. In the livestock space, dairy farming seems to be an area where data and technology innovations are particularly prominent.
In July this year, Dairy health specialist SomaDetect presented at the VetHealth Global conference in Canada, with the aim of identifying partners to take its in-line milk quality and herd health system to commercialization. The SomaDetect system is designed to enable real-time, automated analysis of milk quality.
Last year, Cargill signed an exclusive deal with Dairy Data Warehouse for the provision of global dairy farm data services to the animal nutrition industry.
Additionally, speaking at Bayer Animal Health’s Dairy Summit 2017 in April, associate professor of bovine herd health at Ghent University Geert Opsomer said dairy herd health is “undergoing a period of radical change”. He said dairy fertility solutions now lie in data, genetics and nutrition.