Planting Seeds of Autonomous Farming

When Israeli farm management company Fieldin started almost ten years ago, much of its work was about improving visibility for farmers through the use of sensors.

As co-founder and chief autonomy officer Yonatan Horovitz explains, this visibility was only the first layer in developing precision farming. It helps to save on cost and time and drives greater productivity.

“The first layer of visibility is part of the steps to autonomy,” says Horovitz. “You capture everything about the machine. What exactly did it do and at what speed.”

From there, Fieldin takes all of this data and aggregates and analyzes it to produce recommendations on what can be done better.

AI training

According to Horovitz, the company has around 49 million hours of data.

Even though much of it was collected before the deployment of AI, it is part of the ongoing AI training that drives more accurate analysis and better recommendations.

This is available to subscribers who access the databases through an API and then use an analytical layer. Connectivity in remote farming areas is often an issue, but low bandwidth local base stations that connect all the eco-system layers are addressing it.

“When you aggregate all of this farm data, it’s like the biggest brain in agriculture,” says Horovitz.

“Because the first step is getting the data, and that starts with IoT and GPS tracking, and then you start to move up the stack, and the more data you have, the better AI training you have.”

The AI-based analysis is the second layer. But beyond that is autonomous equipment. Fieldin is now digitizing farms through retrofitting equipment onto tractors and sprayers to make them autonomous. This combines sensors and cameras, and controls for steering wheels and brakes.

Accelerating robotics

Fieldin has digitized hundreds of farms and over 10,000 tractors and pieces of farming equipment over the last eight years. 

Fieldin accelerated its autonomous capabilities last year with the acquisition of Midnight Robotics, a leader in autonomous driving in agriculture. The acquisition creates a first-of-its-kind combination of a sensor-based operational farming platform with autonomous driving technologies to empower growers in the day-to-day management of their farms. 

Layers four and five involves full data execution where the precise recommendations on implementation are executed, leading to the “re-imagining of farming.” This can be around how much to shake trees during harvesting, how much water to distribute, and the best farm machinery route to save time and fuel.

“When you aggregate all of this farm data, it’s like the biggest brain in agriculture”

One farmer, for example, was able to improve productivity by a quantifiable USD45 per acre through improving their process of driving harvesting equipment and the time spent shaking trees. This was based on analyzing data from the performance of other farmers with better results and essentially copying what they did.

Automation also produces significant labor savings, as one operator or machine might cover up to 80 acres on tasks that would once have required a much larger team effort.

Horovitz says Fieldin is now expanding globally into California and Australia. As a result, the data from farming operations in these markets will exponentially impact and improve AI training.

It’s a SaaS model brought to farming with a platform that uses sensor-based data to help growers worldwide improve production, operational transparency, and efficiency.

Fieldin, and digital farming, is on the move, and already 30% of U.S.-based lettuce crops and 20% of the world's almond crop run through their platform.

Lachlan Colquhoun is the Australia and New Zealand correspondent for CDOTrends and the NextGenConnectivity editor. He remains fascinated with how businesses reinvent themselves through digital technology to solve existing issues and change their entire business models. You can reach him at [email protected].

Image credit: iStockphoto/moiseXVII