April 24, 2018 — 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, Blue Waters professor at the National Center for Supercomputing Applications (NCSA), assistant professor in the Department of Natural Resources and Environmental Sciences at the University of Illinois, and the principal investigator of the new study.
The advancement, published in Remote Sensing of Environment, is a breakthrough because, previously, national corn and soybean acreages were only made available by the USDA to the public four to six months after harvest. The lag meant policy and economic 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.
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 market future projections, and more.
A set of satellites known as Landsat have been continuously circling the Earth for 40 years, collecting images using sensors that represent different parts of the electromagnetic spectrum. Guan says most previous attempts to differentiate corn and soybean from these images were based on the visible and near-infrared part of the spectrum signal analysis, but his team decided to include something different.
Two supercomputers at NCSA, ROGER and Blue Waters, were used to generate the time-series Landsat data stack. Blue Waters, with its large memory and rich computing resources, was used to build the classification model through intensive machine training and testing. These powerful computing resources at NCSA allowed Guan and his team to determine how the deep learning approach can be used for crop-type classification, and how early into the growing season this method can be applied for optimal accuracy of crop-type classification.
It turns out corn and soybean have different canopy water statuses, which cannot be captured by visible and near-infrared bands but only shortwave-infrared band. To validate the technique, the team used short-wave infrared (SWIR) data and other spectral data from three Landsat satellites over a 15-year period, and consistently picked up this leaf water status signal.
“The SWIR band is more sensitive to water content inside the leaf. That signal can’t be captured by traditional RGB (visible) light or near-infrared bands, so the SWIR is extremely useful to differentiate corn and soybean,” Guan concludes.
The researchers used a type of machine-learning, known as a deep neural network, to analyze the data.
“Deep learning approaches have just started to be applied for agricultural applications, and we foresee a huge potential of such technologies for future innovations in this area,” says Jian Peng, a NCSA Faculty Fellowand assistant professor in the Department of Computer Science at University of Illinois, and a co-author and co-principal investigator of the new study.
The team focused their analysis within Champaign County, Illinois, as a proof-of-concept. Even though it was a relatively small area, analyzing 15 years of satellite data at a 30-meter resolution still required a supercomputer to process tens of terabytes of data.
“It’s a huge amount of satellite data. We needed the Blue Waters and ROGER supercomputers at the NCSA to handle the process and extract useful information,” Guan says. “Technology wise, being able to handle such a huge amount of data and apply an advanced machine-learning algorithm was a big challenge before, but now we have supercomputers and the skills to handle the dataset.”
The team is now working on expanding the study area to the entire Corn Belt, and investigating further applications of the data, including yield and other quality estimates.
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. The work was supported by NCSA, NASA, and the National Science Foundation.
The National Center for Supercomputing Applications (NCSA) at the University of Illinois at Urbana-Champaign provides supercomputing and advanced digital resources for the nation’s science enterprise. At NCSA, University of Illinois faculty, staff, students, and collaborators from around the globe use advanced digital resources to address research grand challenges for the benefit of science and society. NCSA has been advancing one third of the Fortune 50® for more than 30 years by bringing industry, researchers, and students together to solve grand challenges at rapid speed and scale.
About the Blue Waters Project
The Blue Waters petascale supercomputer is one of the most powerful supercomputers in the world, and is the fastest sustained supercomputer on a university campus. Blue Waters uses hundreds of thousands of computational cores to achieve peak performance of more than 13 quadrillion calculations per second. Blue Waters has more memory and faster data storage than any other open system in the world. Scientists and engineers across the country use the computing and data power of Blue Waters to tackle a wide range of challenges. Recent advances that were not possible without these resources include computationally designing the first set of antibody prototypes to detect the Ebola virus, simulating the HIV capsid, visualizing the formation of the first galaxies and exploding stars, and understanding how the layout of a city can impact supercell thunderstorms.