Case Study: SunSelect 

[fa icon="calendar"] January 30, 2018 11:26:55 AM EST / by Jonathan Feist

The Client

SunSelect grows different varieties of tomatoes and peppers, with approximately 70 sun-select-1.pngacres under glass in California.  Of those, about 40 acres are dedicated to tomatoes.  Producing the only carbon neutral produce in North America, SunSelect is constantly working to develop new ways to improve their growing methods and technology to produce great vegetables.

The Challenge

Like most large greenhouse vegetable growers, Victor Krahn and his team struggled to match their supply and demand dynamics to produce consistent, predictable crops for retailers.  

“The relationship with our retailers is very valuable. We want to make sure we keep our promise to deliver during different seasons. When we’re under or over producing, it makes it much harder to deliver on these promises, as our buyers then might have to look elsewhere to fill an order. By the same token, if we have sold only a certain amount and then, because of bad forecasting, suddenly end up overproducing, we’re going to take a hit just to flush our tomatoes through the market in order to keep our greenhouse going. At that point we’re selling for whatever we can get for them, and we’re losing out.”

-Victor Krahn, Co-Owner, SunSelect

Faced with the concern of under or over-producing, Victor approached us to see if there was a way to improve his operations.  With the millions of data points he has been collecting over the last ten years, along with new data that Motorleaf could capture, was there a way to receive more accurate yield predictions?

“I’ve already put all the energy into my crop, so the last million bucks is the closest thing to my pocket.  We know that at about 20% off the mark, our consultants are pretty good at their job, yet we’re often off by over 20%.”

-Victor Krahn, Co-Owner, SunSelect

A Graphical View Of Human Error

 The below graph shows the actual yields, in blue, compared with the average error that manual prediction offers.  We see numerous instances of yields being wildly off their mark.  This is a challenge for SunSelect, as matching their supply and demand pricing dynamics is crucial in maximizing revenues. char1.png


The Motorleaf Solution

Our yield prediction system is built upon crop data—such as variety of tomato, density, etc.—and environmental data—such as light levels, temperature, and C02. This is combined with visual data, captured by several cameras deployed in the greenhouse.  Finally, Motorleaf's hardware adds additional data not normally collected by greenhouses, such as RGB light spectrum.

With this information, Motorleaf created a unique machine learning algorithm for SunSelect.  Based on an ever-increasing amount of data captured week-by-week, the prediction generated by the system improved each week. This improvement in the algorithm’s ability to address problems and predict outcomes is what makes our machine learning algorithms for yield prediction a unique system in the greenhouse growing industry.  


“The latest algorithm is close to cutting our yield prediction error rates by half. It goes without saying it's a game changer that no one saw coming. Motorleaf is now our new standard for predicting yield.” 

-Victor Krahn, Co-Owner, SunSelect


Ongoing Support

Today, we continue to provide SunSelect with weekly yield predictions for their tomato plants.  In addition, because of the nature of machine learning algorithms, these predictions learn about SunSelect’s unique environment and improve over time.

We are committed to helping greenhouse operators match their supply with demand dynamics to help them optimize their marketing dollars, plan their labour needs, and increase bottom line profit margins. At its core, these are the data-driven, actionable insights that the Motorleaf software provides. 

Better Yield Predictions in 5 Easy Steps

  1. Secure client privacy - mutual NDA is logo 3-2.jpg
  2. Review environmental data history to find data gaps
  3. Send Motorleaf hardware
  4. Motorleaf AI department designs a custom growth algorithm for you (approximately 2 weeks)
  5. Begin receiving LIVE yield forecasts


For more information on how your facility can receive accurate, AI-driven yield predictions, get in touch!


About Motorleaf

Headquartered in the North American hub for artificial intelligence, Motorleaf is funded by Real Ventures, 500 Startups, and the Business Development Bank of Canada (BDC).  

Motorleaf is developing – a virtual agronomist for every greenhouse and indoor farmer in the world. With a varied mix of monitoring, control and predictive capabilities, Motorleaf is leveraging AI & Machine learning to deliver predictable, repeatable, improved crop production worldwide. 

For more information, visit or call 1888-687-5301.

All other marks are the property of their respective owners.

Patent Pending


Topics: agtech, technology, indoor agriculture, ai, data, artificial intelligence, food, machine learning, Software, greenhouse, tomato, virtual agronomist, agricultural technology, agriulture, grow journal, agronomy, peppers, yield prediction

Jonathan Feist

Written by Jonathan Feist

Subscribe to Email Updates

Recent Posts