Predicting the amount of vegetables from a greenhouse harvest is a time-consuming process. Agronomists count samples of vegetables, leaves and flowers in a small area; that sample then serves to estimate the expected yield of the entire grow operation. Often imprecise, farmers are unsure if they will produce enough vegetables to meet contract obligations or know how much labour they will need to package their produce.
Using Motorleaf’s computer vision and machine-learning algorithms, their digital agronomist software can acquire data from indoor growing conditions and plant growth. In turn, their smart-algorithms learn growing patterns in the greenhouse, which then can predict the size of future harvests.
“Better yield prediction is only the beginning for Motorleaf’s value to this sector,” says Motorleaf CEO Alastair Monk. “We’re ultimately producing dynamic grower protocols, which help manage everything from light and nutrients to predicting crop diseases before they happen, and optimized growing conditions that increase ROI – all based on real-time data.”
Initial trials have been conducted in a Californian greenhouse cultivating tomatoes. Client SunSelect reduced its error in predicting weekly tomato yield by half, resulting in significant cost savings. As a result of the improved predictability, SunSelect has since abandoned manual yield predictions in favour of Motorleaf’s algorithms.
“Our custom-made algorithms eliminates hefty costs associated with producing too much or too little perishable goods,” says Monk. “Our hardware and software tools enable growers to use data insights on how best to manage their grow operations. Our technology enables automation in yield prediction so growers can focus their limited time on business development activities.”
Source: Motorleaf May 15, 2018 news release