ASC Director chosen to give the American Society of Agronomy Plenary Distinguished Lectureship on AI Innovations for a Changing Climate

(Photo by Fred Zwicky / University of Illinois Urbana-Champaign)

Kaiyu Guan, the Founding Director of the Agroecosystem Sustainability Center (ASC) and a professor of Natural Resources and Environmental Sciences at the University of Illinois, has been selected as the American Society of Agronomy (ASA) Plenary E.T. and Vam York Distinguished Lectureship at the ASA annual meeting. The international annual meeting is the largest gathering of soil, crop, and agronomic scientists in the world.

It will be presented at the annual meeting of the ASA, the Crop Science Society of America, and the Soil Science Society of America on Nov. 10-13, 2024, in San Antonio, Texas. This conference is the most important gathering for agricultural scientists in the US and globe, for exchanging and sharing ideas, solutions, and innovation from across the field of agricultural sciences.

Guan will deliver an address titled SYMFONI: The “System-of-Systems” Solution to Quantify Soil Carbon and GHG Outcomes for the U.S. Croplands. Guan is the project leader of SYMFONI, an ARPA-E SMARTFARM project, which advanced the first-of-its-kind system-level quantification of greenhouse emissions for agroecosystems from field to continental scales. His group has developed accurate and scalable quantification of soil carbon and greenhouse gas emissions for corn, soybeans, spring and winter wheat, cotton, rice, pastureland, and miscanthus fields.

Guan founded and directs ASC, which has a mission to revolutionize agricultural systems through research, collaboration, and engagement, bridging science and practice for agricultural productivity and ecosystem sustainability. He is also the Chief Scientist for the NASA Acres Program. His research group uses computational models, satellite data, field work, and artificial intelligence to address how climate and human practices affect crop productivity, water resource availability, and ecosystem functioning. Guan’s group aims to increase our society’s resilience and adaptability to maintain sustainability of ecosystem services, food security and water resources.

Photo courtesy of RIPE

When Carl Bernacchi was completing his Ph.D. at the University of Illinois some 20 years ago, Illinois was globally referred to as a “photosynthesis powerhouse.” Today, thanks to Bernacchi and other world-class researchers on Illinois-centric research teams, like the Agroecosystem Sustainability Center (ASC), that agriculture profile has expanded.

“Over the last 10 years, Illinois is starting to accelerate its global profile with regards to ecosystem-scale processes, from mechanism to remote sensing to satellites,” Bernacchi said.

He and contemporary colleague fellow ASC scientist Lisa Ainsworth have been instrumental in building that reputation as internationally recognized research plant physiologists at the USDA Agricultural Research Service (ARS) while also leading research teams in the Departments of Crop Sciences and Plant Biology.

Bernacchi cites strategic hires such as (ASC Director and Blue Waters professor) Kaiyu Guan, Wendy Yang, and D.K. Lee (both ASC scientists) and the collaborative community at Illinois as reasons that reputation has grown exponentially in the last decade.

“I have always seen myself as wearing two different hats that are relatively equal,” Bernacchi said. “One is as a government researcher focusing on government sciences, but also a fully integrated member of an academic environment, where the pillars of strength are collaboration and the full flow of ideas from the spectrum of undergraduate students to administrative staff.”

Bernacchi, who earned bachelor’s and master’s degrees from Bradley University, began his career as a research scientist at the Illinois State Water Survey, an entity that was moved from a governmental organization to a university center and renamed the Prairie Research Institute. 

In 2009, Bernacchi moved to the USDA Photosynthesis Research Unit, a position aligned with his passion of studying how crop interactions with the environment, from the enzyme to the ecosystem scale, affects climate change.

“I am trying to understand how the underlying mechanisms come together to translate into a responsive ecosystem at the canopy or global scale,” Bernacchi explained. “I define myself as an environmental plant physiologist, and that gives me the freedom to maneuver within a very wide space. Over the years, as a result, I have developed a diverse research group.”

Several decades earlier, a group of University of Illinois faculty, understanding the value of collaboration, decided to create the USDA unit and integrate it into campus as a sort of Venn Diagram intersecting university and government priorities. Bernacchi points out that similar USDA centers near colleges and universities don’t often integrate as well as this one does.

“We see ourselves as equal parts USDA and university,” Bernacchi noted. “I think it would be shortsighted to not integrate fully into the community of this campus. As a government scientist, I have the ability to respond quickly to challenges. The academic environment enables me to build collaborations in multiple disciplines to become a member of a much larger community that’s trying to tackle scientific questions well beyond the limits of what our specific units are.”

Photo courtesy of RIPE

Bernacchi’s contributions to the scientific community over the past 15-plus years are numerous. For instance, he was instrumental in developing the Spidercam system, the largest phenotyping system on the planet. It allows researchers to make several measurements on hundreds of thousand plants multiple times per day under different conditions and produces several terabytes of data every 24 hours.

He also built a large-scale experiment that enables researchers to alter the temperature of plants grown under field conditions — the first of its kind and certainly the most versatile in large-scale agricultural systems. The experiment can dial in a heat wave or season-long warming and look at how the crops respond in different levels ranging from the enzymes to the canopy.

With these tools, Bernacchi is helping farmers understand how CO2 not only affects the environment, but also yield.

“There is the notion that elevated CO2 decreases plant water use and increases productivity; however once you layer elevated temperature on top of that, the story gets a little more muddled,” Bernacchi explains. “On its own, elevated CO2 appears to be beneficial for yield. However, when you consider you can’t increase CO2 without elevating temperature, and temperature has an adverse effect on yield, you understand that they offset each other.”

His experiments have revealed that plants typically can rebound from heat waves early in a growing cycle, but if they come later in the growing season, yields take a hit.

“This data sets the ground truth for modeling, remote sensing, and a wide range of different measurements that occur on multiple different scales,” Bernacchi said. “So if you want to model something, you need to have the measurements to know whether the model works.”

That is one of the reasons that Bernacchi’s work is so important to the modelers like Guan and Bin Peng, within ASC.

In 2021, Bernacchi became a founding member of ASC. Under the leadership of Guan, the Center has developed the synergy to respond to current and future environmental challenges related to agriculture, both with regard to the scale of measurements and expertise.

For instance, the Center was instrumental in developing the SMARTFARM project, which uses farms in Champaign County as a test bed for the Midwest Bioenergy Crop Landscape (MRC) Lab to monitor emissions in those fields and make them publicly available. The data could someday be used to develop financial rewards for farmers across the country who practice sustainable farm management.

“One of the biggest limitations that ecosystem science faces is that so much more data is generated from remote sensing and modeling than is being measured directly,” Bernacchi said. “SMARTFARM brings together experts in different scales of measurement, whether it is spatial scales or temporal scales, and compares the results with the models. It is one of the ways that Illinois is now a world leader in crop ecosystem atmosphere interactions. We delve into everything from the mechanisms in the soil that Wendy Yang is doing to the agronomy that DK is doing to ecosystem and canopy scale fluxes that I am doing to the remote sensing and the modeling that Kaiyu and others are doing.”

Three years after its founding, ASC is ready to take flight, with projects like SMARTFARM as its launching pad.

“What SMARTFARM has helped us do is build the machine,” he said. “Now that the machine is running and is well oiled, it doesn’t take much to keep that machine going forward. There are so many ways to leverage this machine, and in 10 years it isn’t hard to imagine a 10-fold increase in ARPA investment in what we are doing here. That kind of investment doesn’t even account for all of the other users of this data that are beyond the boundaries of ASC or beyond the University of Illinois or even the United States.”

One of the tenets of the work is that most of the results are publicly available through Ameriflux, a network of PI-managed sites funded by the U.S. Department of Energy. It measures ecosystem CO2, water, and energy fluxes in North, Central and South America. One of the major anticipated outcomes of Ameriflux is to standardize data collection methods and data analysis. Those methods have so far gathered data in different ways and used different algorithms to tell the statistical story.

Bernacchi pointed out that even as a researcher using USDA ARS funds, he doesn’t have an obligation to participate in Ameriflux or share his team’s results, but he and others within ASC have the greater good in mind. While most Ameriflux contributors have one or two eddy covariance towers (which measure the concentration of gasses and turbulence in the air), Bernacchi’s team has about a dozen such towers that have produced 60-70 site years of data. Those towers take about 10 measurements per second, every second of the day.

“When you start to look at multiple towers in multiple fields with different management practices or different crops, you can start to characterize how changing the landscape alters how the ecosystems transfer carbon, water, energy, and greenhouse gasses with the atmosphere.”

ASC has taken this idea and run with it. Last year, for instance, ASC brought together scientists to strategize about developing a uniform tool to measure nitrous oxide (N2O) — a gas not getting as much attention as CO2 but a major player in agriculture’s role in climate change. The result is a tool called N2Onet, a standardized tool to measure these gasses.

While ASC has facilitated common projects and synergy, each participant has carved his/her own niche. For Bernacchi, that has been measuring temperature differentiation. Historically, if you wanted to know how enzymes change with regards to temperature, it would be done in a test tube. Early in his career, Bernacchi helped change that narrow approach.

Having an interest in photosynthesis and how it responds to parameters, he used genetically modified plants to fine-tune measurements and understand how enzymes respond to changes in temperature in the leaf itself. This gives scientists in vivo abilities instead of just in vitro and helps them understand how most canopy ecosystems respond to temperature. His measurements combined with remote sensing and modeling are helping tell the complete story.

“For someone who does the kind of work that Kaiyu does, having immediate access to ecosystem-scale flux data is useful (instead of having to wait until quality assurance and quality control data is processed nearly a year later),” Bernacchi indicated. “On the other hand, there is always something that is going to create a gap in data. Modeling helps fill in that gap. Combined, you can start to look at what is going on with annual cycles.”

Bernacchi’s work continues to have a major influence on the future. He believes that with temperatures rising in states like Arizona, Florida, and California — which produce over 90 percent of fresh fruits — the Midwest needs to carve out a small portion of its farms to grow food that humans eat, such as tomatoes and kale, in addition to corn and soybeans. To that end, his lab is ramping up efforts in the field of agrivoltaics, which combines agriculture with solar panels.

Whatever future discoveries Bernacchi’s lab will make in the next 20 years, he will benefit from his relationship with his colleagues at ASC.

“From my perspective, having a formalized center where people come together to achieve a common goal, each carrying a very specific charge, has huge benefits,” he said. “It formalizes and streamlines opportunities for collaboration. Under Kaiyu’s leadership, ASC has created a framework of collaboration. We have always collaborated, but now we are doing collaboration with a capital ‘C.’”

Dignitaries at the ARPA-E Symposium included Mikaela Algren, Lead Engineer in Systems Analysis and Quantitative Sustainability with Booz Allen Hamilton; John Reid, Executive Director of the Center for Digital Agriculture, Professor of Computer Science and Agricultural Biological Engineering; Wendy Yang, ASC Associate Director and Professor of Plant Biology; Steven Singer, Program Director at ARPA-E; Kaiyu Guan, ASC Director and Professor of Natural Resources and Environmental Sciences; Calden Stimpson, Project Coordinator for ARPA-E; and Andrew Leakey, Director of CABBI and Michael Aiken Chair Professor of Plant Biology (Photo credit: Mike Koon)

The University of Illinois and the Agroecosystem Sustainability Center at Illinois are in the forefront of studying agriculture’s effect on the environment. To that end, ASC hosted “A Symposium on Agricultural Decarbonization” on Wednesday, September 18 on the Illinois campus. 

The event coincided with a 1.5-day visit by Steven Singer, the Program Director at ARPA-E (The Advanced Research Projects Agency-Energy). Singer gave an overview on the program’s vision, which intersects with many of the initiatives spearheaded by ASC. Among those is the SMARTFARM program, which measures N2O and other greenhouse gas (GHG) emissions. ASC and the Institute for Sustainability, Energy, and Environment was selected as one of the SMARTFARM sites last year.

Steven Singer (left) and Andrew Leakey (right) shared insights as invited speakers at the inaugural Decarbonization Symposium (photos by Mike Koon)

“I really enjoyed coming to Illinois and hearing about the transformative research occurring in agriculture,” said Singer. “The University of Illinois Urbana-Champaign is a leader in thinking about growing bioenergy crops sustainably, a critical aspect of developing a US bioeconomy.”

ASC Director Kaiyu Guan served as the MC for the event and spoke on “Frontier of agricultural carbon accounting technology.” He pointed to how he and his colleagues have developed a “system of systems” approach and how modeling, cross-scale sensors, and artificial intelligence are instrumental in generating accurate and scalable quantification of GHG and soil carbon change from the field to the national scales.

ASC Associate Director Wendy Yang presented insights on her research on N2O GHG emission and later moderated a panel featuring many of the speakers. John Reid, newly minted Executive Director of the Center for Digital Agriculture at Illinois, presented remarks on “Circular Bioeconomy.” Andrew Leakey, Director of Center for Advanced Bioenergy and Bioproducts Innovation (CABBI) and Chair Professor of Plant Biology and Crop Sciences, explained how the campus’ biggest research centerCABBI is leading the way in that space. 

“We are thrilled to have Dr. Singer of ARPA-E visit Illinois, and we are thankful for all the support from ARPA-E,” said Guan. “Decarbonizing agricultural production to ensure both high productivity and environmental sustainability is an urgent and essential task that requires huge devotion and efforts. We at Illinois aim to lead this effort and welcome all the collaborations worldwide to join us. We expect this agricultural decarbonization symposium will recur in the coming years and aim to make this as a major event to showcase Illinois’s achievements in this space.”

An eddy covariance system situated in a maize field is one of the tools used as part of this project. It is used to measure ecosystem fluxes of carbon dioxide, water vapor, energy, methane, and nitrous oxide.

Through funds from the Inflation Reduction Act (IRA), the Agroecosystem Sustainability Center (ASC) will ramp up efforts to investigate the impact of conservation practices on nitrous oxide and other greenhouse gas (GHG) emissions. The Act, signed into law in 2022, includes a historic investment for implementation of practices that support climate mitigation through the U.S. Department of Agriculture (USDA) Natural Resources Conservation Service (NRCS), in addition to funding to advance estimates of mitigation outcomes.

The Global Change and Photosynthesis Research Unit of the USDA Agricultural Research Service (ARS) is a key collaborator on the work to advance mitigation outcome estimates. The funding will support the ongoing work of ARS plant physiologist and also an adjunct professor at UIUC, Carl Bernacchi and fellow ASC scientists Wendy Yang, Kaiyu Guan, and DoKyoung Lee to advance the understanding of conservation practices on GHG fluxes. Data will be used by modelers to improve mitigation outcome estimates, including estimates for USDA conservation programs and the US national inventory of GHG emissions and sinks.

 “The Inflation Reduction Act provides funding for NRCS to address unmet demand for our conservation programs, and also funding to improve our mitigation outcome estimates and advance national reporting,” said Gayle Barry, the IRA National Coordinator for the USDA Natural Resources Conservation Service. “The work of ARS and partners like the University of Illinois are advancing critical research on the impact of conservation practices on GHG emissions, and we are excited to work together.”

The USDA funding for this project is through fiscal year 2031 and builds on the type of work University of Illinois faculty, the ASC, and Illinois’ Institute for Sustainability, Energy, and Environment is doing through the SMARTFARM Project, supported by the Advanced Research Projects Agency-Energy (ARPA-E). Through the ARS, Bernacchi plans to sign research agreements with ASC scientists or hire researchers within the local ARS to work jointly with those scientists.

“Because of the team that we’ve put together with SMARTFARM, we are ideally situated to expand upon what we have been doing in order to meet the objectives of the section of the IRA funding this work,” Bernacchi said. “Because of the extent of our understanding of greenhouse gas emissions from agriculture as well as modeling, the remote sensing, the infield measurements, and the biogeochemical process modeling and measurements we do, USDA recognized that we are well suited to create an intensive measurement site here.”

The SMARTFARM program at ARPA-E is directed by Dr. Steven Singer. “The Illinois intensive measurement site is a great example of partnership between ARPA-E and USDA.” Singer said. “The multi-year funding from the USDA NRCS as part of the IRA will allow the ASC group to expand the observations from the initial datasets generated in the ARPA-E SMARTFARM program. These data will provide a comprehensive inventory of greenhouse gas emissions from working farms, influencing models and informing policy.”

Opportunities for expanding collaboration with the Illinois research in nitrous oxide emissions were explored in January, when ASC convened a group of international leaders in soil nitrous oxide research, including some from the USDA and ARPA-E, in Chicago — which ultimately led to the announcement of the N2Onet to track emissions from agricultural systems.

“Allowing the USDA to see the vision that the University of Illinois faculty has in characterizing and quantifying the fluxes of N2O in agricultural settings really helped us move to the forefront of this funding opportunity,” Yang noted. “We will use our years of experience in this area to generate an unprecedented long-term record of multi-scale data needed to take the leap forward in our understanding of how to mitigate soil nitrous oxide emissions  ”

As one of two intensive measurement sites in the Midwest (the other in Ames, Iowa), ARS Urbana will be a test bed of making baseline measurements at multiple different scales and then integrating those scales to understand the drivers and the consequences of management practices in current agricultural systems. Ultimately, the team will investigate how various changes in management or land uses can offset some of those greenhouse gas emissions. The funding will enable the collaborators to hire more researchers to further characterize what is happening with soil biogeochemistry, to understand the mechanisms behind greenhouse gas emissions from the soil, to purchase equipment to double or triple activities and provide data necessary for improving model estimates of the impact of practices on mitigation outcomes.

Another stream of USDA funding will support a similar project by faculty in the Department of Natural Resources and Environment Sciences to instrument greenhouse gasses measurements from the Illinois Public Media Tower near Monticello. That project will use regional inverse modeling to study how different urban and agricultural settings are contributing to greenhouse gas emissions, coupling precise measurements of those emissions with weather and climate circulation models.

Bernacchi believes that having resources and the infrastructure to develop data collection, data analysis, and data storage pipelines will leverage future funding opportunities.

“We’re a big gear in an important and impressive machine,” he concludes. “Our intensive measurement site is a strong blend of university and federal scientists. The granularity of what we are going to be measuring at the field scale in terms of really high temporal and spatial resolution all the way to the ecosystem and regional scale will bring us national attention in this effort.”

Kaiyu Guan is one of 18 finalists for the 2024 Blavatnik National Award for Young Scientists (courtesy Blavatnik Family Foundation)

Kaiyu Guan, the founding director of the Agroecosystem Sustainability Center and Chief Scientist at NASA Acres, has been named one of 18 finalists for the 2024 Blavatnik National Award for Young Scientists. Established in 2007, the award, jointly presented by the Blavatnik Family Foundation and the New York Academy of Sciences, honors exceptional young scientists (age 42 or younger) across the life sciences, physical sciences, engineering, and chemistry, providing critical support to innovative research that addresses global challenges.

Guan was one of 331 nominations from 172 institutions in 43 states. He represents the Agriculture and Animal Science category and is being recognized for “developing revolutionary technology to enhance our understanding of agricultural production systems and innovating transformative solutions to achieve co-sustainability of agricultural productivity.” He will be formally honored at a gala ceremony on October 1 at the American Museum of Natural History in New York.

“Thanks to the Blavatnik Family Foundation for this honor for the second time. The award goes to our whole team for the journey of innovating solutions to ensure agricultural sustainability in the US Midwest and beyond,” said Guan. 

Guan, a Blue Waters Professor of Natural Resources and Environmental Sciences at the University of Illinois Urbana-Champaign, founded and directs ASC, which has a mission to revolutionize agricultural systems through research, collaboration, and engagement, bridging science and practice for agricultural productivity and ecosystem sustainability. He uses computational models, satellite data, fieldwork, artificial intelligence, and supercomputers to enable agriculture to adapt to and mitigate climate change. The approaches spearheaded by Guan enable real-time monitoring of crop growth, water demands, nutrient needs, crop yield forecasts, and environmental impacts of every crop field in the US Midwest and beyond. His agricultural prediction platform is used by the government and farming communities to advance climate-smart agriculture policies and has enabled farmers to shift towards sustainable practices. 

The Blavatnik Award is the latest in a series of honors bestowed upon Guan, which include the 2023 Macelwane Medal from American Geophysical Union and the 2022 FoodShot Global Groundbreaker Prize and being named a 2023 University Scholar by the University of Illinois System.

Andrew Margenot has been measuring phosphorus leaching into creeks and riverbeds in the U.S. Midwest (photo courtesy of Mark Herman)

As the world tries to mitigate agriculture’s effect on the environment, much of the story can be found in the soils, which stores and cycles nutrient elements of carbon, nitrogen, and phosphorus. Biogeochemistssuch as Andrew Margenot, Associate Director of the Agroecosystem Sustainability Center, are set to find answers, but for Margenot and other biogeochemistry experts who specialize in studying phosphorus cycling, the challenge is first being able to accurately measure where phosphorus has accumulated in the <100 years since humans began to increase the amount of the nutrient element in the biosphere.

Researchers span a creek bank for evidence of phosphorus. (Photo courtesy of Mark Herman)

Margenot, an Associate Professor of Soil Science in the Department of Crop Sciences at the University of Illinois Urbana-Champaign, and other phosphorus experts from around the world published a position or synthesis piece (as opposed to a research study) in Global Change Biology, to lay a roadmap to understand phosphorus cycling in the Anthropocene: the new geological era ushered in by human activities.

Other investigators with the project include Leo Condron, a Professor of Biochemistry at Lincoln University in New Zealand; Genevieve Metson, an Associate Professor in the Department of Geography and Environment at the University of West Ontario; Philip Haygarth, a Professor at the Lancaster University Environment Centre in the United Kingdom; and Jordan Wade, Soil Health Assessment Lead at the Syngenta Group, headquartered in Basel, Switzerland; along with Ph.D. student Prince Agyeman from the Czech Republic and research scientist  Shengnan Zhou and postdoctoral researcher  Suwei Xu from the Margenot research group at Illinois.

“The goal is to look at all possible ways to try to measure legacy phosphorus. This is a comprehensive one-stop shopper overview of where it makes sense to measure and where it makes sense to not worry about. In the process, we identify the priorities and non-priorities and provide a unified vision of what we should do going forward.”

The position paper focus on phosphorus in the “terrestrial aquatic continuum,” the interplay of water and soil that interact at varying scales of space and time“A big part of our paper was emphasizing uncertainty,” Margenot said. “This can be uncomfortable for policymakers because they have a need to make policy yesterday for tomorrow’s problems..”

It may take a century for legacy phosphorus already loaded into stream channels and build up o in the soil to fully disseminate to the waterways, so identifying how much and where this residual P is located is an important need 

“When it comes to legacy phosphorus that will impact water for the next 100 years or more, we don’t even know the basics of where to start. However, there has to be a way to navigate the uncertainty: we don’t want to be too brash, but we also cannot wait 50 years to determine what to do either.”

In making recommendations for future phosphorus use, researchers can measure how much was added to the soil and how much was exported by biomass removal (e.g., harvest) or loss (e.g., leaching or erosion). Calculating the balance (what went in, minus what came out of a ‘system’ like a field, watershed or country) enables estimation of the quantify of residual P – a positive mass balance. 

The position paper also provide several  case studies of legacy P using the two oldest continuous agriculture test plots in the World, the Rothamsted Experiment in Harpenden, England founded in 1843, and the University of Illinois Morrow Plots founded in 1876. Among the discoveries was that the accumulated phosphorus is generally located in the top 12 inches of the soil, and is often in a different form than when it was added to the soil. This last part was a key finding of the paper. 

“We typically add phosphorus in inorganic form as phosphate, which is readily soluble in in water and thus may be at a high risk for loss,” explains Margenot. “What we found is that even though we have a lot of phosphorus going on as phosphate, the amount that builds up doesn’t persist in soil in the soluble phosphate form. It transforms into forms associated with organic matter, iron, and calcium. So we can’t assume that the amount of phosphorus that was applied and not used (i.e., residual phosphorus), is there for the taking by the crop or potential loss to water.”

In addition to comprehensively evaluating  the problem, the consortium made several recommendations.

1)    Researchers need to be better at validating estimates. “Oftentimes we don’t measure the small input or the output amounts of phosphorus. Over time those gaps in the measurements amplify uncertainty,” Margenot says.

2)    Scientists often don’t have sufficient information to form decent estimates.The group suggests an initiative where the private sector (e.g., soil testing labs) could work with researchers to make use of existing datasets. 

3)    There needs to be a uniform method of measuring the data. “In a lot of cases, basic measurements basically haven’t been taken,” Margenot says.  “We need to couple complementary methods that are individually not great, but in combination are quite strong. While it can be overwhelming to figure out where the P has built up over the last 70 years, I think the important thing is to identify where it matters for different reasons of agronomic utilization and water quality impairment.”

4)    There needs to be an effort to discover the hot spots of legacy P so that resources could be prioritized to decrease the negative impacts of water quality. Margenot’s group is already doing that in Illinois. “We don’t need to map the entire state,” Margenot says. “We know where there is a priority watershed because the USGS is measuring this.”

The challenge according to the paper is to convince researchers and funders to allocate resources to provide data that will make a difference. “To get that last 5 percent of the data will cost you half of what it takes for other 95% of the data,” Margenot notes.  

The challenge for policymakers, according to Margenot, will be to explain that because the measurements of legacy P are estimates at this point, they should see the data as a living document. “The policies have to be plastic,” he says.

“The global phosphorus has been more perturbed by human activities than nitrogen,” Margenot notes. “We’ve about doubled the amount of nitrogen in circulation in the biosphere, but we have quadrupled it for phosphorus.”

The collaboration applied Knowledge-Guided Machine Learning (KGML), which uses satellite remote sensing, computational models and state-of-the-art AI techniques to help faster and more accurately predict GMG emissions, a process that promises to be scalable in the coming years. (Courtesy of University of Minnesota Department of Bioproducts and Biosystems Engineering)

For the first time, a team of scientists has demonstrated it is possible to provide accurate, high-resolution predictions of carbon cycles using Artificial Intelligence (AI) and supercomputers to measure the amount of Greenhouse Gas (GHG) emissions from every individual farm at the national scale. This breakthrough is a critical first step in developing a credible measurement, monitoring, reporting, and verification of agricultural emissions. It can be used to incentivize the implementation of climate smart practices and help mitigate the impacts of climate change, which supports the White House’s national strategy highlighting the need to quantify GHG emission across sectors with a goal of net-zero emissions by 2050. The team’s research findings were recently published in Nature Communications, based on a visionary framework the team published in Earth-Science Reviews.  

Funded by the Foundation for Food & Agriculture Research, FoodShot Global, U.S. Department of Energy and U.S. National Science Foundation, the study was co-led by University of Illinois Urbana-Champaign’s Agroecosystem Sustainability Center Founding Director and Blue Waters Professor Kaiyu Guan and University of Minnesota’s Professor Zhenong Jin. The team with collaborators developed the AI and supercomputer solution to quantify the related changes in GHG emissions from adopting climate mitigation practices like cover cropping and precision nitrogen fertilizer management. 

“This solution is a scalable, reliable way to measure and predict on individual farm fields the agricultural carbon fluxes, crop yields and changes in soil carbon stocks and can help the industry speak uniformly about best practices for reducing farmland emissions,” said Guan. “This breakthrough could allow the agricultural and food sectors to quantify their carbon footprints in producing or sourcing raw agricultural products so that they can design strategies to reduce GHG in their supply chain and objectively assess different GHG-reducing strategies.”  

The team built their predictive modeling tool using Knowledge-Guided Machine Learning (KGML), an emerging machine learning research framework proposed by a group of computer scientists . Pioneered by this team, the KGML model for Agriculture (KGML-Ag) uses the power of satellite remote sensing, computational models and state-of-the-art AI techniques to cost-effectively produce accurate results more than 10,000 times faster than traditional process-based models, even with limited data.

“Unlike traditional model-data fusion approaches, we developed KGML-Ag as a new way to bring together the power of sensing data, domain knowledge and artificial intelligence techniques,” said Jin. “AI plays a critical role in realizing our ambitious goals to quantify every field’s carbon emission.”

“Building the KGML is very challenging due to the need of data and knowledge from various domain. ” said Licheng Liu, the lead author of the KGML-Ag work and a research scientist at University of Minnesota. “Fortunately, our team brings together the experts in field measurements, domain sciences, and AI techniques, allowing us to achieve this significant breakthrough.”

To compute the vast amount of information from millions of individual farms, the team is using supercomputing platforms available at the National Center for Supercomputing Applications

Although locally tested in the Midwest, the new approach can be scaled up to national and global levels and help the industry grasp the best practices for reducing emissions. “The strength of our tool is that it is both generic and scalable, and it can be potentially applied to different agricultural systems in any country,” said Bin Peng, co-author of the study and an assistant professor at the University of Illinois Crop Sciences Department

“There are many effective farming practices that reduce GHG emissions, but if everyone measures them differently, we’ll never be able to objectively understand how well these practices work,” added Peng. “This research helps agriculture stakeholders ‘speak the same language’ about farmland greenhouse gas emissions and will foster more scientific rigor in estimating those emissions.”

The study also details how emissions and agricultural practices data can be cross-checked against economic, policy and carbon market data to find best-practice and realistic GHG mitigation solutions locally to globally – especially in economies struggling to farm in an environmentally conscious manner. 

“The real beauty of our work is that it is both very generic and scalable, meaning it can be applied to virtually any agricultural system in any country to obtain reliable emissions data using our targeted procedure and techniques, which is what we are expanding to do right now” Guan concluded. 

A Breakthrough of: 2022 FoodShot Global Award and 2020 FFAR Seeding Solutions Award

Research Findings Published: University of Illinois Urbana-Champaign News, Earth-Science Reviews and Nature Communications.

The collaboration between the Danforth Plant Science Center and the Agroecosystem Sustainability Center promises to produce findings that will improve agriculture sustainability. (Photo courtesy, Danforth Plant Science Center)

ASC Director Kaiyu Guan and fellow ASC scientists Bin Peng and Sheng Weng are teaming with Christopher Topp, member and principal Investigator of the Danforth Plant Science Center and his lab members Marcus Griffiths, and Kong Wong to explore the impact of cover crops on soil health and corn production to improve agriculture sustainability. The research findings will be used to develop tools to help farmers make decisions about when, where and what type of cover crops could be beneficial. A $650,000 award grant from the National Institutes for Food and Agriculture will support the research project.

The research team will conduct multi-year field trials of 12 cover crop species that integrate with corn production, and use root phenomics, cutting-edge sensing technologies, and machine-learning enabled agroecosystem modeling to gain an improved understanding of the variation for root traits that exists among diverse cover crop species and their influence on soil and cash crops.

“The major goal of the project is to fill key gaps in the foundational knowledge base of cover crop plant species that currently hinder their efficacy and farmer adoption,” said Topp. “Roots are the interface of the plant with soil, but there is a limited understanding of cover crop root system traits and their empirical effects on soil health and cash crop productivity.”

Cover cropping has been largely considered a major conservation approach to improve ecosystem services for sustainable agriculture. With current adoption rates low across US farmlands, extensive investments from government and private sectors have strongly encouraged farmers to employ cover crops. These efforts will be bolstered by an increased understanding of cover crop root system traits and their effect on soil and cash crops, especially across the spectrum of cover crop species diversity that will be needed to maximize benefits in many different environments and cropping systems.

“What’s unique about this project is that we will combine the unprecedented capability of the Danforth Center’s root phenotyping with our advanced modeling capability at the University of Illinois, aiming to significantly deepen our understanding of cover crop root diversity and their impacts on plant and soil. Our modeling thus can extrapolate the findings and implications to the broader geography across the Midwest to inform better practices of cover crop,” said Guan

“Creating a better understanding of the impact of cover crops will help farmers be more informed about selecting cover crops that maximizes both yield and ecosystem benefits and thereby supports widespread adoption of cover crop management practices in the US,” Topp added.

About the Donald Danforth Plant Science Center: Founded in 1998, the Donald Danforth Plant Science Center is a not-for-profit research institute with a mission to improve the human condition through plant science. Research, education, and outreach aim to have an impact at the nexus of food security and the environment and position the St. Louis region as a world center for plant science. The Center’s work is funded through competitive grants from many sources, including the National Science Foundation, National Institutes of Health, U.S. Department of Energy, U.S. Agency for International Development, and The Bill & Melinda Gates Foundation, and through the generosity of individual, corporate, and foundation donors. Follow us on Twitter at @DanforthCenter.

One of the experimental fields shortly before planting in early May. [Remote sensing signals can provide reliable estimates of soil moisture without vegetation cover during non-growing seasons. (photo by Yi Yang)

A multi-institutional study led by University of Illinois and Agroecosystem Sustainability Center (ASC) scientists concluded that, although soil moisture varies significantly both within a single field and from field to field due to varying soil properties and different management practices, soil moisture distribution relative to the field average remains consistent across time within each field. 

Over three years, the team used sensor measurements and a high-density campaign to reveal that the drier areas remain the drier areas and the wetter areas remain the wetter areas. The study also deduced this finding, reliable estimations of high-resolution soil moisture could be made by integrating optical and active microwave remote sensing, and modeling,  instead of relying on infield measurements.

“Our ultimate goal was to improve our understanding of soil moisture variability,” said principal investigator Bin Peng, an ASC scientist and an assistant professor in the Department of Crop Sciences. “We wanted to understand the controlling factors of those variabilities and how those variabilities can be reflected in satellite remote sensing data.”

“The current satellite-based soil moisture products are too coarse to meet the requirements for agricultural applications,” noted Yi Yang, the study’s first author and a doctoral student in computational ecohydrology. “We found that the spatial pattern of soil moisture variability is not changing over the season. In other words,drier areas tend to stay drier and wetter areas tend to stay wetter. We can use this knowledge to estimate the pattern of the spatial variability of soil moisture, and then estimate high-resolution soil moisture products.”

The research team also included Kaiyu Guan, founding director of ASC and a professor in the department of Natural Resources and Environmental Sciences; Ming Pan, a senior hydrologist at Scripps Institute of Oceanography at the University of California-San Diego; Trenton Franz, a professor of hydro geophysics at the University of Nebraska-Lincoln; Michael Cosh, a researcher at the U.S. Department of Agriculture’s (USDA) Hydrology and Remote Sensing Laboratory and Carl Bernacchi, a core ASC scientist at USDA and a professor in the Department of Crop Sciences and Plant Biology. The team conducted field campaigns in three 85-acre fields and set up continuous field stations in 30 other fields from 2021 to ’23. Their results were published on April 26 in the Vadose Zone Journal.

“Most of our efforts were to improve our understanding of soil moisture variability using field experiment data, and we are also striving to test if our improved understanding can really be useful for remote sensing retrieval,” Yang said.

A container in the field housing the data logger connected to soil moisture sensors and communication equipment transmitting data via cellular network. (photo by Yi Yang)

He noted that taking regular field measurements are too expensive, too labor intensive and not scalable.

“We can get the relative dry-wet pattern within a crop field through optical remote sensing,” Peng said. “Therefore, you don’t have to go to the field and replicate the data collection. Our experiment confirmed that because the relative pattern is stable, once you get two or three images from optical satellite sensors to confirm the wetter and drier pattern, you can fill in the temporal gap. This opens a new pathway for high resolution remote sensing retrieval.”

Peng said the study provides a roadmap for studying soil moisture variability in cropland, which until this point had been lacking both measurement and reliable remote sensing capabilities. That pathway combines optical remote sensing data with shortwave infrared spectral bands, active microwave remote sensing, and modeling. High-resolution soil moisture data will be valuable to the farmer for more precision irrigation. It could also be used to understand greenhouse gas emissions or carbon intensity of agricultural production, which are closely related to soil oxygen and water conditions as they directly affect biochemical reactions and microbial activities. 

“We should build upon the knowledge discovered here to develop a high-resolution soil moisture product,” Guan said. “We laid out our roadmap for mapping high resolution soil moisture over cropland using multi-source satellite remote sensing and modeling data. The first stream of information gives within field soil moisture variability, and then the second stream gives the absolute soil moisture temporal changes. We can then integrate them with modeling to map every field across the Midwest or even across the globe.”