Smart farming algorithm optimizes transport of perishable crops

Smart farming algorithm optimizes transport of perishable crops

Technology News |
By Rich Pell

Growers of such high-value perishable fresh produce, such as strawberries, face greater challenges than other producers looking to employ ‘smart farming’ technologies. Currently, most such technologies – which help growers harvest their crops faster and more efficiently – focus primarily on row crops like corn and soybeans.

“The large machines used to harvest row crops such as wheat, corn, and soybeans provide a natural platform for improving efficiency,” says Richard Sowers, a professor of industrial and enterprise systems engineering and of mathematics at the University of Illinois. “However, the story is radically different in high-value, hand-picked crops like strawberries, which may be many times more valuable per acre than corn. With hand-picked crops, precision agriculture lags significantly behind.”

A hundred acres of corn may have a value of $800,000, while the same number of acres in strawberries may be worth $7.5 million, say the researchers. “Yet,” says Devasia Manuel, a recent Illinois alumnus and currently a machine learning researcher with Google, “strawberry harvesters use little to no precision agriculture techniques. It’s quite astonishing.”

After observing workers harvesting strawberries, the researchers developed an algorithm that explored the spoilage a grower might incur if – instead of waiting until the trucks were loaded to capacity to transport the fruit to cold storage – they sent partially loaded trucks to the cooling stations. Hand-picked fruits like strawberries begin to decay immediately after being harvested, and their market value may decline by as much as ten percent per hour if the harvested produce is allowed to sit in the hot sun waiting to be transported to refrigerated storage, say the researchers.

“Growers would like to transport their crops to cooling stations according to an optimal policy,” says Sowers, “but that policy has to reflect a trade-off between the loss in quality and the rate of harvest.” Complicating the matter, the researchers note, is that unlike machine-harvested crops, the harvesting of hand-picked crops varies from worker to worker and by time of day as workers become hot and fatigued.

“If your workers pick 90 percent of a load in just 15 minutes and then slow down because of the heat, it would make sense to get the load to cold storage even though the truck is only partially full,” Sowers says. “That’s a very simplified picture, but that’s what we were trying to get at. We thought through how to model these trade-offs and did some optimization and simulations, and we found that some significant savings might be possible.”

The findings were encouraging, say the researchers, and the potential financial rewards should motivate researchers and crop producers to explore opportunities to apply precision agriculture techniques to the management of hand-picked and specialty crops. For more, see “Optimal Transport to Cold Chain in Perishable Hand-Picked Agriculture.”

Related articles:
Tractor maker buys AI startup in smart farming push
Qualcomm invests in digital farming
Leaf sensor tells farmers when plants are thirsty
Drone sensor for precision agriculture data collection
Cargill invests in animal facial recognition for smart farming

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News


Linked Articles