Building a Fitbit for Cows

Precision agriculture tools developed through open source frameworks are enabling researchers17 and citizen scientists18 alike to build upon, adapt, and customize free software for their own specific needs. From Tanzania21 and Japan22 to the U.S., the agricultural community is leveraging data and benefiting from free machine learning platforms, like TensorFlow and CaffeNet, to improve the health of their plants and animals while maximizing productivity.

Whether it’s farmers relying on Farm Hack to share DIY tech tools or home gardeners using FarmBots to plant seeds and kill weeds in their backyards, these collaborative innovations are changing the landscape of food production in the digital age. And while many small and medium-sized American farms have yet to fully adopt machine learning tools, that may be changing. Dairy farmers in the U.S. have been facing a crisis, with milk prices at an all-time low.23 Hart Dairy Farm in Waynesboro, Georgia is the first U.S. farm to develop and implement a machine learning application using TensorFlow for tracking their livestock. Their application, called IDA, continues to improve over time by regularly collecting and analyzing data from sensors attached to cow udders. By using remote-control sized transmitters, owners can know when their Holsteins or Guernseys are chewing cud, feeling sick, or ready for insemination. The volume of data captured and processed by Hart’s software is astounding: originally trained on the equivalent of 600 years of cow data, it can replicate that volume every two-and-a-half months or so, given that the equivalent of eight years of cow data is created and collected every day.24

Melissa Brandao, CEO and founder of HerdDogg, originally developed smart herd monitoring tools to be a kind of “Fitbit for cows,” measuring everything from a cow’s ear temperature to their activity levels via a Bluetooth-enabled tag clipped to their floppy ear. (Brandao says she focused on developing ear tags because it’s the only “real estate” on a cow that developers have been granted access to.) Using this data, the tag can then tell farmers or researchers whether cows are in heat, missing, or about to become sick.

In addition to the ear clips, HerdDogg manufactures what they call DoggBones— small, passive readers that can collect data about a herd anytime and anywhere, no WiFi or cellular connection required. Combining both allows farmers to get a granular look at the lives of their dairy-makers, giving the average small farmer access to as much as 100,000,000 rows of data per year.


Melissa Brandao

“Cows are funny… They have all these unique personalities. There are loner cows and busy body cows, active cows and boring cows.”

“We realized that every cow has their own unique personalities and biorhythms,” she says. “One might be really low activity-level and slow-moving, while another is a social butterfly.”

Brandao is able to glean these insights from HerdDogg’s wearables, which attach to cows’ ears. From a sensor the size of a button, the HerdDogg tag can tell not only how far a cow has traveled that day, but also whether they’re sick or in heat. This data can help farmers with livestock to adjust their practices based on the health of their herds, boosting productivity and increasing their bottom lines in the process.

“Oh my gosh, cows are funny,” Jeff Mitchel, who serves as Director of Data Science at HerdDogg, chimes in. “They have all these unique personalities. There are loner cows and busy body cows, active cows and boring cows.”

The HerdDogg tag measures the temperature of a cow’s outer ear, but that’s enough data for farmers to diagnose a whole host of conditions. “Cows maintain their core temperature by using their extremities, like their ears,” Brandao explains. “When there’s a disruption in homeostasis, it’s really magnified in their ears.”

It was important for Brandao to ensure that farmers have control over their own data. If they’d like to, farmers can compare their cows to those on other farms, but they can also choose to keep their data private. “Producers can still get a lot out of the HerdDogg platform even if they want to use it in a vacuum,” says Mitchel. “We see our product as the first step to more data-driven analytics.”

Brandao first piloted the technology by working with the Dairy Farmers of America, who have seen how data is helping to improve the overall health of their herds with hands-free medical diagnosis.

And with robust service and data available to anyone, anywhere, it’s a system that isn’t reliant on proximity to broadband, which is ideal for rural farmers. “It even runs on batteries,” adds Brandao. “It’s pretty much the swiss army knife of wearables.”

It also helps alleviate the cows’ stress. Instead of being wrangled or put into a headlock to have their temperature taken, they can continue their grass-munching in peace. “It’s such a rewarding feeling knowing that you’re doing something beneficial for their well-being,” says Brandao. In fact, HerdDogg allows farmers to create profile pages for their cows, giving them a sense of their heffers’ entire medical history at a single glance. The software even allows farmers to compare their herds to others around the world through a crowdsourced tool that they call the “Happy Herd Index.” (Yes, part of the goal is to inspire farmer FOMO.)

  1. Matt Simon, “Phone-powered AI spots sick plants with remarkable accuracy,” Wired, October 2, 2017.
  2. Emily Matchar, “AI plant and animal identification helps us all be citizen scientists,”, June 7, 2017.
  3. Electronic Frontier Foundation: Surveillance Self-Defense, “Open-source software,” Electronic Frontier Foundation, 2018.
  4. Simon Phipps, “Open Source and Crowdsourcing Are Not Synonyms,”, June 23, 2016.
  5. Chuck Gill, “Penn State-developed plant-disease app recognized by Google,”, April 2, 2018.
  6. Kaz Sato, “How a Japanese cucumber farmer is using deep learning and TensorFlow,”, August 31, 2016.
  7. J. R. Sullivan, “America’s Farmers Are in Crisis, and They’re Looking to Trump for Relief,” The New Yorker, January 23, 2018.
  8. Harwell, Drew, “’Cow Fitbits’ and artificial intelligence are coming to the dairy farm,” The Washington Post. April 8, 2018.
  9. Jared Diamond, Guns, Germs and Steel: The Fates of Human Societies, W.W. Norton & Company, 1997.


Computer scientist and open source advocate Simon Phipps defines crowdsourcing as “the leveraging of the marginal interest and free time of a large group of people to complete a task that otherwise could not be economically completed. The result typically benefits the initiator hugely, without significantly compensating
the participants.”