AI Case Study
Connecterra increases dairy production by as much as 30% by tracking and analysing the health of cows with machine learning
The health of cows can dramatically impact their ability to produce milk. A healthy cow can product 30 litres of milk a day versus 10 for a cow in poorer health. Connectera launched the Intelligent Dairy Farmer's Assistant (IDA) to help track and monitor the movement and activity of cows - a "fitbit" for cows. Analysing the data with TensorFlow they were able to identify individual cows and tell if they were eating, resting or drinking. They could also predict problem such as digestive disorders. Using insights and suggestions farmers could see their dairy production rise by as much as 30% on farms
"The Intelligent Dairy Farmer's Assistant (IDA) uses a motion-sensing device attached to a cow's neck to transmit its movements to a program driven by AI. The sensor data, when aligned repeatedly with real-world behavior, eventually allows IDA to tell from data alone when a cow is chewing cud, lying down, walking, drinking or eating."
Those indicators can predict whether a particular cow is ill, has become less productive, or is ready to breed — alerting the farmer to changes in behavior that might otherwise be easily missed."
"'We had both spent many years working in the technology industry, and realized that the dairy industry was a sector where technology could make a dramatic impact. For instance, we saw that the only difference between cows that produce 30 liters of milk a day and those that produce 10 liters was the animal’s health. We wondered—could technology make cows healthier, and in doing so, help farmers grow their businesses?'"
"Using these insights, we're already seeing a 30 percent increase in dairy production on our customers’ farms."
"Individual US farmer feedback suggests that having AI identify which cows in his herd need attention could help improve farm productivity by as much as 10 percent. In this case, with a 2,000 strong herd, it could mean hundreds of thousands of dollars."
Underlying IDA is Google's open-source TensorFlow programming framework.
It "learns patterns about a cow’s movements from a wearable sensor. We use this data to train machine learning models in TensorFlow, and ultimately, Ida can detect activities from eating, drinking, resting, fertility, temperature and more. It’s not just tracking this information, though. We use Ida to predict problems early, detecting cases like lameness or digestive disorders, and provide recommendations to farmers on how to keep their cows healthy and improve the efficiency of their farms."
Cows movements from a wearable sensor.