SoylentNews is people
SoylentNews
from the probably-spotting-marijuana-as-well dept.
Corn and soybean fields look similar from space - at least they used to. But now, scientists have proven a new technique for distinguishing the two crops using satellite data and the processing power of supercomputers.
"If we want to predict corn or soybean production for Illinois or the entire United States, we have to know where they are being grown," says Kaiyu Guan, assistant professor in the Department of Natural Resources and Environmental Sciences at the University of Illinois, Blue Waters professor at the National Center for Supercomputing Applications (NCSA), and the principal investigator of the new study.
University of Illinois scientists used short-wave infrared bands from Landsat satellites to accurately distinguish corn and soybeans during the growing season.
The advancement, published in Remote Sensing of Environment, is a breakthrough because, previously, national corn and soybean acreages were only made available to the public four to six months after harvest by the USDA. The lag meant policy decisions were based on stale data. But the new technique can distinguish the two major crops with 95 percent accuracy by the end of July for each field - just two or three months after planting and well before harvest.
The researchers argue more timely estimates of crop areas could be used for a variety of monitoring and decision-making applications, including crop insurance, land rental, supply-chain logistics, commodity markets, and more.
[...] The article, "A high-performance and in-season classification system of field-level crop types using time-series Landsat data and a machine learning approach," is published in Remote Sensing of Environment [DOI: 10.1016/j.rse.2018.02.045]. Additional authors include Christopher Seifert, Brian Wardlow, and Zhan Li.
(Score: 2) by Runaway1956 on Monday April 09 2018, @11:25AM (8 children)
There is a small number of seed suppliers, who could have told these people where corn and soybeans are being grown. They could probably supply moderately detailed maps, showing each of the nation's crops. So, distinguishing, from space, where the crops are being grown seems to be redundant.
They COULD do something more useful, using this same idea. They could monitor the health of the crops from space. The crops are going to look quite different if they don't get enough water, or if they get too much water. Or, if they suffer a late freeze in the spring, or an early freeze in the autumn. A blight or pest infestation should also show up from space.
It's somewhat difficult to believe that cameras in space haven't been able to distinguish between corn and soybeans for decades already. Way back in the Cold War, both the US and Russia had optics good enough for that. Today, those same optics should be pretty affordable.
(Score: 2) by PiMuNu on Monday April 09 2018, @11:40AM (1 child)
> "who could have told these people"
Presumably this is commercially sensitive information, both for the seed producers and the farmers. Should the seed producers really share this information?
> "Way back in the Cold War"
Yes, but in the Cold War all the processing had to be done manually. Now they can get a computer to do it due to improved CPU speeds and digital photography. So the thing can be done by a couple of university researchers, rather than an army of data analysts.
(Score: 2) by Runaway1956 on Monday April 09 2018, @12:13PM
Actually, most of the seed is sold through farmer's coops. The coop has no commercial interest in hiding, or masking that information. In fact, the data is already supplied to the various state colleges and universities.
(Score: 4, Interesting) by c0lo on Monday April 09 2018, @12:51PM
Only seems so. It may be even highly probable. But it's not 100% accurate.
Useful for whom?
If accuracy and the cost of data acquisition is lower than doing the matching "by hand", then the guys stroke gold: do you imagine the prices the speculators at the commodity market will pay for improvements in the forecasts for their futures trading?
The guys only need to offer a premium package for premium prices offering realtime data on the crop status.
https://www.youtube.com/watch?v=aoFiw2jMy-0 https://soylentnews.org/~MichaelDavidCrawford
(Score: 1, Interesting) by Anonymous Coward on Monday April 09 2018, @01:23PM (3 children)
To determine which undesirable farming areas need a targetted pestilence in order to make them easier to purchase. Or to place strain on another country's self sufficiency in order to better offer them aid (with strings attached.) Or this could be used to help document an area where the shipped quantity of food doesn't match with the grown quantity of food bringing back the interstate commerce battle of the 1930s or 40s over whether keeping excess crops to feed your own livestock should be taxed as interstate commerce.
Expect to see the ugly side of Union over this, sooner or later.
(Score: 2) by Runaway1956 on Monday April 09 2018, @02:03PM
I never thought of that. But, you're right. What IS the primary purpose of fine grained monitoring, after all? Control - it's always about control. Even at my age, I'm so naive that I kinda assume that the researchers are trying to improve things, somehow.
(Score: 0) by Anonymous Coward on Monday April 09 2018, @02:13PM (1 child)
Privacy rights for plants! We demand to grow anonymously without being tracked!! After all, we are cash crops.
(Score: 1) by redneckmother on Monday April 09 2018, @03:12PM
Speaking of "cash crops"... the gubmit has a new tool to locate hemp fields...
Mas cerveza por favor.
(Score: 3, Interesting) by EvilSS on Monday April 09 2018, @02:38PM
There are companies that already do this, such as Satellite Imaging Corporation. What they did here was something novel by figuring out what particular crop was being grown without requiring human eyeballs. That capability will be licensed to companies like SIC to add to their stable of products.