C Magazine July/August 2015 : Page 14

Menu
  • Page View
  • Contents View
  • Archive
  • Advertisers
  • News Feed
  • CHSInc.com
  • YouTube
  • Flickr
  • Twitter
  • LinkedIn

North Dakota farmer Bob Runck, left, and CHS Regional YieldPoint® Specialist Nathan Kosbau use data analysis to determine where to boost management inputs for maximum return on investment. > given farm. Tapping outside sources for analysis, such as area weather information, government data or even yield information from neighboring acres, can paint an even clearer picture of what’s happening at the farm to help owners make better decisions and greater profi t. Today, talk of the “cloud” is more than just about the rain. Plotting Innovation How would you defi ne big data? Multi-farm data integration is one way, says David Black, senior vice president and chief information offi cer, CHS. Much of big data’s potential has yet to bear fruit, but many of the larger agricultural companies, including Deere & Company and The Climate Corporation, recently acquired by Monsanto, are investing in the infrastructure and analytics to make it happen. Even if they are successful, such agriculture giants might only do one thing well, says Black. “They are using big data to make a seeding recommendation only, or a fertilizer recommendation only. 14 JULY/AUGUST 2015 The reality is that there is so much complexity for a farmer to deal with, and farmers don’t make any of those decisions independently. In fact, when they look at yield at the end of the year, they don’t look back and say it was just because of seed, or just because of chemistry, or just because of the weather — it was because of all those things.” The average farmer makes more than 35 important decisions each year, says Black, which begin in the planning stage and continue throughout preplanting, planting, in season and harvest. Each of those decisions aff ects the others. That’s where CHS comes in, he says, as the cooperative develops its plan for big data. “Often we’re right there with them whenever they’re making those decisions,” says Black, “and that can occur either through our retail channel or through the agronomist network. And if you layer on top of that a set of tools based on analytics and all the information that can be aggregated, that’s the value CHS brings.” At his farm one mile north of Casselton, N.D., fourth-generation farmer Bob Runck has gathered harvest data from his combine to measure yield on his 2,000 acres of corn and soybeans. Working with Nathan Kosbau, CHS Regional YieldPoint® Specialist, Runck has identifi ed the sweet spots on his fi eld and has begun to use variable-rate fertilizer applications and variable-rate planting populations according to the data. “It was hard for me to take that concept, because I truly didn’t believe there was much diff erence in my land,” says Runck. “But we are fi nding diff erences, so we’re trying to use that information to make us better farmers.” To learn how some of the pieces of big data might fi t together, CHS created the CHS Innovation Plot. Using 620 acres of Runck’s land, CHS Key Agronomist Tim Swanson and says Swanson. “The technology is going to open doors to verify and quantify our fi ndings, and we aren’t just randomly going about it. We can go back and monitor one spot throughout the season if we choose.” Mature Decisions As data volume and analytics capabilities grow, so will information value, says Black. Current capabilities put agriculture at step two on a fi ve-step graph he dubs “the maturity of decision making.” Today’s data technology reports what has happened, such as yield. It also allows users to analyze why something happened: Did weather, crop inputs or farming practices impact my results? In the future, increased access to information will allow farmers to predict yield outcomes from the right mix of inputs, measure what is happening at the fi eld in real time and act on prescriptive farming to maximize yield. “Farmers are overwhelmed with data as opposed to being overwhelmed with information to make decisions.” — David Black Kosbau created zones to be tested using multiple variables of seed, fertilizer and other applications. More than 400 treatments will be evaluated using data directly collected from John Deere and Case IH equipment, among others. Overlaid atop that data will be YieldPoint information “to get one big picture,” says Kosbau. This fi rst eff ort at collecting and analyzing specifi c information will begin to show big data’s promise to agronomists and farmers alike, “As a cooperative, we exist to do things for farmers they can’t do for themselves. It’s fundamental,” says Black. “This big data and analytics space is right in our wheelhouse. Farmers are overwhelmed with data as opposed to being overwhelmed with information to make decisions. We can play a role in helping them sort through that noise. It is core to what a cooperative is.” Yet as agriculture moves faster to take advantage of big data, some barriers remain. CHSINC.COM

Issue Articles

Issue List

Spring 2021

Winter 2021

Fall 2020

Summer 2020

Spring 2020

Winter 2020

Fall 2019

Summer 2019

Spring 2019

Special Issue

Winter 2019

Fall 2018

Summer 2018

Spring 2018

Winter 2018

September/October 2017

July/August 2017

May/June 2017

March/April 2017

January/February 2017

November/December 2016

September/October 2016

July/August 2016

May/June 2016

March/April 2016

January/February 2016

November/December 2015

September/October 2015

July/August 2015

May/June 2015

March/April 2015

January/February 2015

November/December 2014

September/October 2014

July/August 2014

May/June 2014

March/April 2014

January/February 2014

November/December 2013

September/October 2013

July/August 2013

May / June 2013

March/April 2013

January/February 2013

November/December 2012

September/October 2012

July/August 2012

May/June 2012

March/April 2012

January/February 2012

November/December 2011

September/October 2011

July/August 2011

May/June 2011

March/April 2011

January/February 2011

November/December 2010

September/October 2010

July/August 2010

May/June 2010

March/April 2010

January/February 2010

November/December 2009

September/October 2009

July/August 2009

May/June 2009

March/April 2009

January/February 2009

November/December 2008

September/October 2008

July/August 2008

May/June 2008

March/April 2008

January/February 2008

December 2007

Previous  Next


Library