April 2021 - 17

CONTROLLED ENVIRONMENT AGRICULTURE
provide recommendations and record
information to improve recipes in
future cycles. Cameras pick up details
and day to day changes unseen by the
human eye, so diseases are flagged
faster, giving growers the time they
need to find and fix problems.
When growers trust AI with pest
and disease detection, they also
become more efficient with their
time, eliminating hours spent on
" crop walks " checking on plants, and
reducing possible transmission of
such pests between facilities.
AI for yield prediction
AI can also drastically improve
yield predictions. Accurate forecasting
is a crucial component of running
a farm or greenhouse, as it directly
affects the ability to presell overage.
If there's a surplus of product and not
enough demand, profits shrink and
food waste increases.
Manual yield prediction is often
imprecise and inaccurate, despite
notebooks full of recipes, Excel
spreadsheets, and years of knowledge
and experience. Although growers
have refined the ability to offer
highly calculated guesses based on
prior crops and similar conditions,
the margin of error is significant.
Halfway through a growth cycle, yield
predictions can be overestimated or
underestimated by up to 30%.
Improved yield prediction is now
possible due to predictive technology
and AI. Just as a machine can be
taught to detect pests and pathogens
more accurately with more data,
machine learning software can
remember yields from prior harvests,
and improve forecasting accuracy over
time by making visual comparisons to
prior growth cycles.
" LUNA's yield forecasting changes
the game for growers, " said Adam
Greenberg, CEO of iUNU. " We are
able to predict yields with three times
more accuracy half way through the
growth cycle. "
The added time allows
organizations to presell expected
inventory or surplus and minimize
waste.
AI for space, resource use
Another benefit of AI is the
optimization of real estate and
inputs within facilities. For instance,
computer vision can ensure that light
is not wasted by recognizing foliage
gaps and presenting opportunities to
maximize space utilization.
Space utilization issues resulting
from manual observation and
planning can cost organizations up
to 10% of potential added revenue -
even two additional plants per bench
would make a significant difference
for a crop that turns six times per
year.
Computer vision AI has a detailed
memory. It can see how plants
change on a day-to-day basis and
how certain crop cycles compare
to others. As growers change their
recipes, macro and minute changes
are recorded and measured, not only
over time, but also against previous
yields at the same stage of a current
crop cycle. When certain plants are
underperforming, growers have
enough time to make changes before
a harvest to optimize the space for
profit.
Fueling the CEA growth boom
Computer vision can help CEA
with pest and disease detection,
accurate yield forecasting and the
maximization of space utility. With
big box customers driving prices
down and the cost of labor continuing
to increase, growers will soon
rely on the increased growth and
predictability that precision farming
brings so that CEA can function as
reliably as manufacturing.
Not only is AI becoming an
economic necessity, but it also
promises to support a positive shift
in the food industry. With increased
revenue and efficiency, indoor
facilities maximize sales and minimize
shrink. With increased profit they can
also build closer to urban areas and
increase the accessibility of locally
grown, healthy food for consumers.
Finally, with a reduced reliance on
manual or repetitive labor, as well as
recorded tribal knowledge, recipes
can be optimized and resource
utilization right-sized for generations
to come.
" AI will drive it all, " said Gabriel
Youtsey, chief innovation officer at
University of California, Agriculture
and Natural Resources. " On the
production side, the goal is trying
to control and understand all the
environmental factors that will help
empower the plant itself. Using AI,
over time we will get very good at
learning what the plant needs and
when it needs it, so the plant can give
us the yield and quality factors that
we are looking for. At the end of the
day I think it will be crop quality,
nutrition, sustainability and yield all
together. "
Carl Silverberg is senior vice
president of outreach and public
affairs for iUNU and can be reached
at csilverberg@iunu.com. Founded
in 2013, iUNU ( " you knew " ) is an
industrial computer vision company
headquartered in Seattle, with offices
in San Francisco and San Diego. VGN
GREENHOUSES
ANY CLIMATE,
ANY CROP
FOR OVER
40 YEARS
GROWSPAN HAS
BEEN HELPING
GROWERS
ENERGY-EFFICIENT DESIGNS
ENVIRONMENTAL CONTROL
EXPERT CONSULTATION
IN-HOUSE SERVICES
www.growspan.com
877.835.9996
VGN | APRIL 2021 | 17
http://www.growspan.com
April 2021

Table of Contents for the Digital Edition of April 2021
