Crop Insurance Today Fourth Quarter 2020 - 18

GPS and geotagging allow for data collection down to the square foot and even square inch level. When combined with data analytics, producers
can optimize the output of every acre on their farm.

resources. If too late, farmers lose money due to
more costly repairs that could have been prevented, or by inefficiently tending for their crop with
sub-standard equipment. Predictive maintenance
on the other hand determines the condition of the
equipment and notifies the farmer that machinery
parts need to be replaced, greased, sharpened, etc.
How does this work? On board sensors and electronic measurement devices that monitor physical activities within the equipment and determine
that something is not working correctly. It could
be as simple as detecting excess vibration or temperature within a part of the equipment that is indicative of worn or damaged parts.
Another application of machine learning and
artificial intelligence being tested is the application of pesticides. Fields vary in many aspects,
including weed species and level of infestation.
Smart herbicide application systems that employ
computer vision can recognize the presence and
species of weeds. If the system does not recognize weed presence, herbicides are not applied.
If weeds are detected, the herbicide rate can be
adjusted accordingly to the size of weeds and level of infestation. This can reduce costs, improve
application efficiency, and more accurately target
these pests.

The Biggest

Predictive agriculture has become a buzzword at research institutions worldwide-even to
the extent that Crop Science, the journal of the
Crop Science Society of America, devoted a special issue on the subject this year. In a nutshell,
predictive agriculture is crop modeling for the
future. Decades ago, the term " predictive agri18

FOURTHQUARTER2020

culture " was relegated to simple models that were
supported by, at the time, the nascent field of
computer science and computing capacity. Fast
forward to today-with the integration of data
science, supercomputing, and machine learning
techniques predictive modeling is becoming an
accurate reality.
Thousands and even millions of data points
from soil sensors, imaging, satellites, weather
station networks, etc., are now integrated into
simulation models. The models can identify key
management and environmental inputs and forecast plant growth and yield in real-time throughout the growing season. The models can integrate past, current, and forecasted weather data
to drive simulations to predict future yield and
which plant growth variables are most susceptible to adverse conditions. Models can determine,
for instance, how the genes in a corn hybrid will
perform across a region over the course of the
next 10 or 20 years. And, using the probability
of differing weather conditions, the constraint of
soil types locally and regionally, the probability
of how well that hybrid will perform relative to
other hybrids can be determined.
While much of this is esoteric, models can
identify producer management that will affect
the outcome of the prediction. The probability
that activities such as planting date, seeding rate,
and fertilizer rates will have on yield given the
probability of differing weather conditions can
be known. When combined with differing soil
conditions across a farm, model predictions can
improve the likelihood that growers will optimize
their inputs, and farm-level economics.
In the end, these technologies based on data

analytics will improve productivity, manage environmental challenges, create cost savings, and
provide for better input management. Some systems go so far as to optimize grain cart travel
paths, how many employees will be needed for
specific fields to get the grain in the bin, and,
given current and forecasted yields on regional
and national scales, determine projected prices,
and the optimum time for farmers to market
their crops.

And Crop Insurance

The interplay with crop insurance should not
need too much explanation. The vagaries of nature that breeders are preparing future varieties
and hybrids for are those same perils that crop
insurance indemnifies-insects, disease, drought,
water-logging, cold, heat, etc. From that standpoint, these breeding technologies are crucial to
reduce yield loss in future, uncertain climates,
at both local and regional scales. Further, smart
machinery that reduces yield loss, improves grain
quality, increases harvest speed, and improves pest
management will increase production to count in
the bin and reduce yield and revenue loss claims.
On a grand scale, now that sensors, imagery, onfarm monitoring, ag weather networks, and precision ag are commonplace, predictive modeling
shows great promise in replacing the art of farming with science-based decision support tools.
By themselves or together, these technologies are
rapidly developing and will further improve in the
future. They are making agriculture more responsive to current and future challenges, and, from
that standpoint, what is good for growing crops is
most likely also good for crop insurance.



Crop Insurance Today Fourth Quarter 2020

Table of Contents for the Digital Edition of Crop Insurance Today Fourth Quarter 2020

No label
Crop Insurance Today Fourth Quarter 2020 - No label
Crop Insurance Today Fourth Quarter 2020 - Cover2
Crop Insurance Today Fourth Quarter 2020 - 1
Crop Insurance Today Fourth Quarter 2020 - 2
Crop Insurance Today Fourth Quarter 2020 - 3
Crop Insurance Today Fourth Quarter 2020 - 4
Crop Insurance Today Fourth Quarter 2020 - 5
Crop Insurance Today Fourth Quarter 2020 - 6
Crop Insurance Today Fourth Quarter 2020 - 7
Crop Insurance Today Fourth Quarter 2020 - 8
Crop Insurance Today Fourth Quarter 2020 - 9
Crop Insurance Today Fourth Quarter 2020 - 10
Crop Insurance Today Fourth Quarter 2020 - 11
Crop Insurance Today Fourth Quarter 2020 - 12
Crop Insurance Today Fourth Quarter 2020 - 13
Crop Insurance Today Fourth Quarter 2020 - 14
Crop Insurance Today Fourth Quarter 2020 - 15
Crop Insurance Today Fourth Quarter 2020 - 16
Crop Insurance Today Fourth Quarter 2020 - 17
Crop Insurance Today Fourth Quarter 2020 - 18
Crop Insurance Today Fourth Quarter 2020 - 19
Crop Insurance Today Fourth Quarter 2020 - 20
Crop Insurance Today Fourth Quarter 2020 - 21
Crop Insurance Today Fourth Quarter 2020 - 22
Crop Insurance Today Fourth Quarter 2020 - 23
Crop Insurance Today Fourth Quarter 2020 - 24
Crop Insurance Today Fourth Quarter 2020 - 25
Crop Insurance Today Fourth Quarter 2020 - 26
Crop Insurance Today Fourth Quarter 2020 - 27
Crop Insurance Today Fourth Quarter 2020 - 28
Crop Insurance Today Fourth Quarter 2020 - Cover3
Crop Insurance Today Fourth Quarter 2020 - Cover4
https://www.nxtbook.com/allen/cint/55-3
https://www.nxtbook.com/allen/cint/55-2
https://www.nxtbook.com/allen/cint/55-1
https://www.nxtbook.com/allen/cint/54-4
https://www.nxtbook.com/allen/cint/54-3
https://www.nxtbook.com/allen/cint/54-2
https://www.nxtbook.com/allen/cint/54-1
https://www.nxtbook.com/allen/cint/53-4
https://www.nxtbook.com/allen/cint/53-03
https://www.nxtbook.com/allen/cint/53-02
https://www.nxtbook.com/allen/cint/53-01
https://www.nxtbook.com/allen/cint/52-04
https://www.nxtbook.com/allen/cint/52-03
https://www.nxtbook.com/allen/cint/52-02
https://www.nxtbook.com/allen/cint/52-01
http://www.brightcopy.net/allen/cint/51-04
http://www.brightcopy.net/allen/cint/51-03
http://www.brightcopy.net/allen/cint/51-02
http://www.brightcopy.net/allen/cint/51-01
http://www.brightcopy.net/allen/cint/50-04
http://www.brightcopy.net/allen/cint/50-3
http://www.brightcopy.net/allen/cint/50-2
http://www.brightcopy.net/allen/cint/50-1
http://www.brightcopy.net/allen/cint/49-4
http://www.brightcopy.net/allen/cint/49-3
http://www.brightcopy.net/allen/cint/may2016
http://www.brightcopy.net/allen/cint/february2016
http://www.brightcopy.net/allen/cint/november2015
http://www.brightcopy.net/allen/cint/september2015
https://www.nxtbook.com/allen/cint/may2015
https://www.nxtbook.com/allen/cint/february2015
https://www.nxtbook.com/allen/cint/november2014
https://www.nxtbook.com/allen/cint/september2014
https://www.nxtbook.com/allen/cint/may2014
https://www.nxtbook.com/allen/cint/february2014
https://www.nxtbook.com/allen/cint/november2013
https://www.nxtbook.com/allen/cint/august2013
https://www.nxtbook.com/allen/cint/may2013
https://www.nxtbook.com/allen/cint/february2013
https://www.nxtbook.com/allen/cint/november2012
https://www.nxtbook.com/allen/cint/august2012
https://www.nxtbook.com/allen/cint/may2012
https://www.nxtbook.com/allen/cint/february2012
https://www.nxtbook.com/allen/cint/44-4
https://www.nxtbookmedia.com