Stories
Slash Boxes
Comments

SoylentNews is people

posted by Fnord666 on Monday October 21 2019, @05:44AM   Printer-friendly
from the picturing-plants-in-a-whole-new-light dept.

Maiken Mikkelsen wants to change the world by developing a small, inexpensive hyperspectral camera to enable worldwide precision farming practices that would significantly reduce water, energy, fertilizer and pesticide use while simultaneously increasing yields. While that goal sounds like a tall task for a simple camera, it's one that has now been greenlighted by a 2019 Moore Inventor Fellowship.

"The Moore Inventor Fellowship is opening a new avenue of research to me," said Mikkelsen, the James N. and Elizabeth H. Barton Associate Professor of Electrical and Computer Engineering at Duke University. "It is enabling me to explore new applications for my technology that could benefit the environment and mankind in a profound way, and I am grateful that the Moore Foundation allows me to pursue those."

The cameras most people think of and use every day only capture visible light, which is a small fraction of the available spectrum. Other cameras might specialize in infrared or X-ray wavelengths, for example, but few can capture light from disparate points along the spectrum. And those that can suffer from a myriad of drawbacks, such as complicated machinery that can break, slow functional speeds, bulkiness that can make them difficult to transport, handle by hand or place on drones, and costs that range from tens to hundreds of thousands of dollars.

Mikkelsen, however, is working on an approach can be implemented on a single chip, can snap a multispectral image in a few trillionths of a second, and produced and sold for just tens of dollars.

"It wasn't obvious at all that we could do this," said Mikkelsen. "It's quite astonishing actually that not only does this work in preliminary experiments, but we're seeing new physical phenomena that we did not expect that will allow us to speed up how fast we can do this detection by many orders of magnitude."

The physical phenomenon behind Mikkelsen's technology is called plasmonics—the use of nanoscale physical phenomena to trap certain frequencies of light.

[...] While the first proof-of-concept experiments will use a three-by-three grid capable of detecting nine frequencies, Mikkelsen plans on scaling up to a five-by-five grid for a total of 25 frequencies. And there's no shortage of applications that are primed to take advantage of such a device.

Surgeons can use hyperspectral imaging to tell the difference between cancerous and healthy tissue during surgery. Food and water safety inspectors can use it to tell when a chicken breast is contaminated with dangerous bacteria. But the application that Mikkelsen has set her sights on is precision agriculture. While plants may only look green or brown to the naked eye, the light reflected from their leaves and flowers outside of the visual spectrum contains a cornucopia of valuable information.

"Obtaining a 'spectral fingerprint' can precisely identify a material and its composition," said Mikkelsen. "Not only can it indicate the type of plant, but it can also determine its condition, whether it needs water, is stressed or has low nitrogen content, indicating a need for fertilizer. It is truly astonishing how much we can learn about plants by simply studying a spectral image of them."

Hyperspectral imaging could enable precision agriculture, allowing fertilizer, pesticides, herbicides and water to be applied only where needed. This has the potential to reduce pollution while saving water and money. Imagine a hyperspectral camera mounted on a helicopter or drone mapping a field's condition and transmitting that information to a tractor designed to deliver fertilizer or pesticides at variable rates across the fields.


Original Submission

 
This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 2) by PiMuNu on Monday October 21 2019, @04:46PM (1 child)

    by PiMuNu (3823) on Monday October 21 2019, @04:46PM (#909910)

    > It should probably be done on smartphones with machine learning acceleration chips

    Sigh. Is everything an "app" nowadays?

    Specialised equipment, bespoke applications, significant processing power, slowly changing systems all mark "smartphone" as exactly the wrong choice for deployment I would have thought.

    Starting Score:    1  point
    Karma-Bonus Modifier   +1  

    Total Score:   2  
  • (Score: 2) by takyon on Wednesday October 23 2019, @04:42AM

    by takyon (881) <reversethis-{gro ... s} {ta} {noykat}> on Wednesday October 23 2019, @04:42AM (#910668) Journal

    You get better, more compact stuff as a result due to lower development costs. Like a FLIR imager, or in-field medical test. You can purchase a cheap smartphone without contract. Don't let the convenience burn.

    Also, in general, smartphones or AR glasses should gain the ability to determine the composition of objects they are pointing at, without needing an attachment.

    --
    [SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]