New AI-assisted Climate Study Reveals What Urban Heat Really Feels Like
Category: Climate Solutions
Urban Heating, Cooling to Play Major Role in Energy Demand, Climate Change
Existing global energy projections underestimate the impact of climate change on urban heating and cooling systems by roughly 50% by 2099 if greenhouse gas emissions remain high, researchers report. This disparity could profoundly affect critical sustainable energy planning for the future.
Existing studies predominantly concentrate on chemical feedback loops, which are large-scale processes involving complex interactions between energy use, greenhouse gas emissions and the atmosphere. However, a research group at Illinois focuses on the often-overlooked physical interactions between urban infrastructure and the atmosphere that can contribute to local microclimates and, ultimately, global climate.
A new study led by Lei Zhao, Assistant Professor of Civil and Environmental Engineering, emphasizes that smaller-scale city-level waste heat from residential and commercial property heating and cooling efforts can lead to big impacts on local climates and energy use. The study findings are published in the journal Nature Climate Change.
Zhao’s research was seed-funded by iSEE to help climate scientists model the dynamics between climate change and urbanization — and inform policymkers and planners of potential climate solutions.
Climate Change and Urbanization: Team Employs New Modeling Framework
With climate change driving temperature increases, water scarcity, and limited access to energy in urban areas, it has become more important than ever to understand the relationships between urban areas and their resources.
Lei Zhao, Assistant Professor of Civil and Environmental Engineering at the University of Illinois, works with a team of engineers and climate scientists to model the dynamics between climate change and urbanization. Their research, which has received seed funding from iSEE, helps inform policymakers and urban planners of potential climate solutions.
The software currently used by scientists to predict climate conditions and model land, ocean, and atmospheric dynamics, called the Earth Systems Modeling framework, may be underrepresenting urban environments. Zhao describes it as a “legacy issue,” in which the happenings in an urban environment are too small to cause any discernible changes in large-scale dynamics that traditional models were designed to capture. Additionally, because of the great heterogeneity of urban environments, specific details are often overlooked.
“Chicago is different from New York City. New York City is different from San Francisco. The textures and forms of those cities are not the same,” Zhao said.
There’s a common misconception about the availability of urban climate data. Urban weather stations are not placed in areas that are truly representative of the city’s environment.
“People might think urban environments are very data-rich, but in terms of climatology or meteorology, they’re not,” Zhao said. “When you walk into the city center, you’ll seldom see a weather station there. It’s typically in the airport or in some park, which doesn’t represent urban environments.”
Placing observational sites in truly urban areas causes logistical issues. In the city center, citizens prefer shopping malls and other recreational buildings over weather stations. So the lack of documentation from city centers causes a gap in research between the urban landscape and observational and modeling processes.
To address this, engineers and climate scientists are researching how to use process-based climate modeling and machine learning/artificial intelligence approaches to produce a simulation of climate dynamics that is representative of real urban landscapes. The new hybrid modeling framework leverages the few models that capture urban dynamics and integrates their fully coupled simulations with a physics-informed machine-learning approach.
Together, they provide global multi-model projections of local urban climates under different climate change scenarios, with an assessment of the associated robustness and uncertainties. With this framework, when public health or climate interventionists want to initiate change, they can use a model that is precise to the city of interest.
It’s an unfortunate reality in urban engineering that sustainability sometimes conflicts with resilience. Zhao warns that researchers must aim to strike a balance between strategies that make efficient use of energy and strategies that make cities more resilient to hazards and extremes.
Thankfully, many urban infrastructure experts have spearheaded efforts to prevent cities from being major sources of greenhouse gases while still prioritizing high-quality infrastructure. Zhao notes that targeting urban areas in particular may be the most effective way toward a sustainable future: “75% of final energy use is from cities. They’re hotspots of emission, even though they’re only 2-3% of the land. If we don’t act on cities, we won’t have a sustainable future.”
This urban hybrid modeling project is highly interdisciplinary, featuring a team of experts from different fields. Collaboration between atmospheric scientists and civil engineers helps bring the urban systems model to a broader scale. The two teams have weekly discussions about their research, some of which have led to other urban-related sustainability and climate pursuits.
“Our team has grown,” Zhao said. “For example, this project has led to a larger grant to explore how the wind and concentration of heat in the cities affects mosquitoes, and then how that affects dengue disease.”
When it comes to current research successes, Zhao highlights his students and postdocs and their work on urban humid heat stress (Joyce Yang), urban climate-energy interactions (Cathy Li), urban green stormwater infrastructure (Laura Gray), and global urban data and modeling development (Bowen Fang, Yifan Cheng, and Yiwen Zhang).
“Some of our students are working on nature-based solutions,” he said. “One of those solutions, green stormwater infrastructure, was designed for water infiltration and reduced flooding, but it has other co-benefits. Those benefits are what we are trying to evaluate.”
A long-term goal of this research is to advance global urban science, and consequently, global sustainability.
“I hope to build an advanced understanding of global science that is both fundamental and solution-oriented,” Zhao said.
The research team hopes that these findings will help inform decision-making policies and enable climate-sensitive urban design and engineering. Although cities are currently notorious for being energy-costly, pathogenic hotspots, accurate urban modeling can help transform them into resilient, sustainable, and livable spaces for generations to come.
— Article by iSEE Communications Intern Anjali Yedavalli
USDA Selects U of I Team to Study Spring Dust Storms over Rural Midwest
It made headlines nationwide. An abrupt dust storm blinded drivers on Interstate 55 south of Springfield, Ill., on May 1, causing a massive pileup, ultimately killing eight people and injuring 37. A team of researchers from the University of Illinois, Cornell University, and Texas A&M University will try to determine the factors that caused the tragic event with the hope to prevent future similar episodes thanks to a U.S. Department of Agriculture (USDA) grant.
“We put this team together to understand the mechanisms of this kind of dust storm through the lens of at least three factors,” said Sheng Wang, the principal investigator (PI) on the project. “How much did climate (drought, soil dryness), farming activities (tillage, cover crop planting), and the extreme weather event (wind gusts, direction, etc.) each contribute to the disaster?”
Wang notes that while the May 1 I-55 storm received the most attention, it was one of a multitude of such events to hit the Midwest within the last year.
“Agricultural dust storms very rarely happen in the central Midwest,” Wang said. “Not since the Dust Bowl of the 1930s have we seen them here with this kind of regularity.”
Wang, a research assistant professor and research scientist affiliated with the Institute for Sustainability, Energy, and Environment (iSEE) and the Department of Natural Resources and Environmental Sciences (NRES), leads the airborne sensing research team for the two-year old Agroecosystems Sustainability Center (ASC).
ASC, under the leadership of Founder and Director Kaiyu Guan, was established to use advanced modeling and monitoring of agroecosystems to improve sustainability in the light of climate change.
“We have the foundation to elaborate work on these problems,” Wang said. “For example, we can use remote system data as well as artificial intelligence to detect conservation practices like the use of cover crops. We have published a number of papers on this subject.”
The USDA has funds available to support “rapid response” projects. In this case, researchers had one month after the incident to apply for the funding and a year to produce results. The study begins in earnest on Oct. 1, 2023 and concludes Sept. 30, 2024.
Team members will first use remote system data collected from satellite images and ASC’s highly accurate AI modeling to characterize conservation practice in Illinois. They will use information along with NOAA climate data to plug into weather research and forecasting with chemistry (WRF-Chem) models. From there they can develop different scenarios. For example, what if farmers had used 10 percent or 50 percent of their land for cover crops.
“We can develop a mitigation strategy to advise stakeholders on potential preventative measures like cover crops and no-till practices,” Wang said.
The third component will be a social and policy analysis. The researchers do not want to merely rely on empirical data to drive the solution. They intend to survey local farmers, policymakers, and traffic agencies to understand their thoughts about the dust storms and conservation agriculture practices.
“At ASC we advocate for these practices,” Wang said. “We can use modeling of these incidents as part of our research at UIUC to help develop agriculture policy and social science.”
The team was carefully put together with the goal of using multiple approaches to understand the mechanism of this kind of dust storm. Guan and Bin Peng, an incoming assistant professor of crop sciences, will focus on sustainability. Jonathan Coppess, the Director of the Gardner Agricultural Policy Program, and Mackenzie Johnson, an assistant professor in NRES, will focus on agricultural policy. All of which are a vital part of the ASC team. Qi Li, an assistant professor of civil and environmental engineering at Cornell University and Yangyang Xu, an assistant professor of atmospheric sciences at Texas A&M University, will largely focus on modeling.
“We have received very positive feedback from the USDA,” Wang said. “ There are many dust storm studies on the dry land region in the western part of the United States, but there is very limited study in the Midwest. This is a great integration of research with an extension component. It takes advantage of the strength of ASC and has great interest to the public. With such an elite team, I am quite confident we can generate some very exciting results.”
— Article by ASC Communications Lead Mike Koon
ASC Director Receives Macelwane Medal; Named AGU Fellow
Kaiyu Guan, Founding Director of the Agroecosystem Sustainability Center (ASC) and a Blue Waters Associate Professor of Natural Resources and Environmental Sciences, has received the prestigious James B. Macelwane Medal from the American Geophysical Union (AGU).
The award is given annually to three to five early career scientists in recognition of their significant contributions to Earth and space science. Honorees automatic distinction as AGU Fellows. The Macelwane Medal is named in honor of the former AGU president James B. Macelwane, who was renowned for his contributions to geophysics.
Guan joins other scientists, leaders, educators, journalists, and communicators from around the world who have made outstanding achievements and contributions by pushing forward the frontiers of science. According to the AGU, “Each recipient embodies the AGU’s community’s shared vision of a thriving, sustainable, and equitable future powered by discovery, innovation, and action.”
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 leads a research group focusing on the computational modeling and sensing of agricultural ecosystems under climate change. His work combines advanced domain knowledge with satellite data, supercomputing, process-based modeling, and machine learning.
In doing so, he addresses key questions on how climate and human management control productivity and ecosystem services for agricultural systems. He and his team have made significant breakthroughs towards quantifying the impact of environmental stresses and human activities on agricultural productivity and sustainability.
Guan earned a Ph.D. from Princeton University in 2013 and was a postdoctoral scholar at Stanford University. The AGU previously honored Guan with its Early Career Award in Global Environmental Change.
“I am very honored to receive the James B. Macelwane Medal and to be included alongside such distinguished previous recipients,” Guan said. “This is a shared honor to our whole team, including our students, researchers, collaborators, and mentors. I am truly grateful for all their great contributions. We are striving to build solutions to make our agricultural system both more productive and more sustainable. It is a very hard problem and requires a big team effort. I thank AGU for giving us this recognition in this uphill journey, and we know the hard work needs to continue and accelerate.”
AGU will formally recognize this year’s recipients at AGU23, which will convene more than 25,000 attendees from over 100 countries in San Francisco and online everywhere on Dec. 11-15.
About the American Geophysical Union: The American Geophysical Union (AGU) supports a global community of more than half a million professionals and advocates in the Earth and space sciences. Through broad and inclusive partnerships, AGU aims to advance discovery and solution science that accelerate knowledge and create solutions that are ethical, unbiased and respectful of communities and their values.
About the Agroecosystem Sustainability Center: ASC was established in 2021 to be a global leader in harmonizing sustainable food production with thriving ecosystems. The Center, made up of a cross-disciplinary set of faculty and researchers at the University of Illinois at Urbana-Champaign, strives to revolutionize agricultural systems through research, collaboration, and engagement, bridging science and practice for agricultural productivity and ecosystem sustainability.
AGU press contact: Samson Reiny, (202) 998-8654, news@agu.org
ASC press contact: Mike Koon, (217) 898-3519, mkoon@illinois.edu
Climate Win-Win: Enhanced Weathering
Applying ground-up silicate rock to Midwestern farm fields can capture significant amounts of carbon dioxide and prevent it from accumulating in the atmosphere, according to a new study that successfully quantified those climate benefits for the first time.
Working with Eion Corp., researchers at the University of Illinois Urbana-Champaign and the Leverhulme Centre for Climate Change Mitigation (LC3M) developed a new method to calculate the CO2-reduction potential of basalt rock amendments applied to cropland soil, a process known as enhanced weathering.
Traditional row-crop agriculture releases sizable amounts of soil-derived carbon to the atmosphere as CO2, a greenhouse gas that is a primary driver of climate change. With enhanced weathering, silicate rock is applied to farmland to capture that carbon before it reaches the atmosphere. As the rock weathers, calcium and magnesium are released and react with dissolved CO2 to produce bicarbonate, essentially locking up the gas and redirecting it harmlessly into groundwater.
Quantifying its carbon-capture potential, however, has been a challenge — until now. The Illinois team was able to calculate both the weathering rate and carbon dioxide reduction potential of the basalt rock amendments applied to maize and miscanthus fields. Those factors are critical for efforts to optimize carbon sequestration and for farmers hoping to earn carbon credits.
“In addition to reducing emissions, we desperately need effective ways to draw down atmospheric carbon dioxide. Our results suggest that basalt application to farms could be a win-win for farmers and for the planet, improving yields and drawing down CO2,” said study co-author Evan DeLucia, Director Emeritus at the Institute for Sustainability, Energy, and Environment (iSEE), G. William Arends Professor Emeritus of Plant Biology, and Co-Investigator at the Center for Advanced Bioenergy and Bioproducts Innovation (CABBI) at Illinois.
The breakthrough — the result of a five-year study at the Illinois Energy Farm — was published in Global Change Biology Bioenergy. The study was led by DeLucia and Ilsa Kantola, Research Scientist at iSEE and the Carl R. Woese Institute for Genomic Biology (IGB).
The work is part of iSEE’s partnership with the Leverhulme Centre at the University of Sheffield in the United Kingdom, which is investigating enhanced weathering for carbon dioxide removal in field sites around the world: Malaysia, Australia, the U.K., and the United States.
In this case, researchers repeatedly applied finely-ground basalt on twin fields at the Energy Farm for four years — one field with a maize/soybean crop rotation and the other with Miscanthus x giganteus, a perennial grass that is emerging as a productive bioenergy crop to replace fossil fuels.
Grinding the basalt accelerates a natural weathering process that involves two chemical reactions. First, atmospheric CO2 dissolves in rainwater to create carbonic acid. Then, the acid reacts with the rock dust in the soil to form bicarbonate, a soluble compound that leaches with soil water; that redirects the CO2 from the atmosphere to the water cycle, where it can pass harmlessly into waterways and potentially help fight ocean acidification. Basalt contains both calcium and magnesium as well as phosphorus and minor nutrients that are released during weathering and benefit soil fertility.
The Illinois team calculated the CO2 reduction and weathering rate of the basalt by measuring the change in rare earth elements in the soil with the addition of basalt and comparing it to the calcium and magnesium in the system. The rare earth elements are “sticky,” building up in the soil in tiny amounts as more basalt is applied, and calcium and magnesium are released by weathering, with some taken up by the crops. The difference in rare earth elements indicates how much basalt, and therefore how much calcium and magnesium, has been applied; and the difference between the expected amount of calcium and magnesium and the actual amount in the soil tells researchers how much has been consumed by reactions in the soil.
The calculations showed that enhanced weathering reduced net carbon loss to the atmosphere by 42% in maize plots. Paired with conservation tillage or cover crops, the basalt application could turn maize into a net carbon sink. In miscanthus plots, which already stored more CO2 than they emitted before the addition of basalt, enhanced weathering more than doubled carbon storage. The finding adds to the potential climate benefits of this renewable bioenergy crop, one of three targeted by CABBI in its U.S. Department of Energy-funded work.
Carbon dioxide removal methods are a critical part of climate mitigation strategies, and as social and political efforts to reduce carbon emissions to the atmosphere are delayed, pressure is growing to implement these strategies soon.
Farmers, landowners, and others seeking carbon credits all want to know how much basalt rock to apply and how long the effect will last, both of which depend on the composition of the rock and the environmental conditions where it is applied.
“As we look for new ways to offset carbon emissions, we need to be able to quantify those carbon savings to better compare our options,” Kantola said.
Co-authors on the paper included Professor Carl Bernacchi of the Department of Plant Biology at Illinois, CABBI, and the USDA Agricultural Research Service; Illinois researchers Elena Blanc-Betes of iSEE and CABBI and Mike Masters of ISEE and Plant Biology; Elliot Chang, Alison Marklein, and Adam Wolf of Eion Corp; Caitlin Moore of the University of Western Australia and former CABBI postdoc; Adam von Haden of the University of Wisconsin-Madison and former CABBI postdoc; and Dimitar Epihov and Professor David Beerling of LC3M.
— Article by iSEE Communications Specialist Julie Wurth
New Insights on Soil Carbon Budgets
A study led by researchers at the Agroecosystem Sustainability Center (ASC) at the University of Illinois Urbana-Champaign provides new insights for quantifying cropland carbon budgets and soil carbon credits, two important metrics for mitigating climate change.
The results, outlined in a paper published in the soil science journal Geoderma, could simplify the process for calculating soil carbon credits, which reward farmers for conserving soil carbon through crop rotation, no-tillage, cover crops, and other conservation practices that improve soil health. The project was funded by the U.S. Department of Energy’s Advanced Research Projects Agency-Energy (ARPA-E).
Agricultural activity causes a significant amount of soil organic carbon (SOC) to be released into the atmosphere as carbon dioxide, a greenhouse gas that contributes to climate change. Several conservation practices have been suggested to help sequester that carbon in the soil, but their potential to enhance the total SOC in a soil profile, known as SOC stock, needs to be assessed locally. Such assessments are key to the emerging agricultural carbon credit market.
Accurately calculating cropland carbon budgets and soil carbon credits is critical to assessing the climate change mitigation potential of agriculture as well as conservation practices. Those calculations are sensitive to local soil and climatic conditions, especially the initial SOC stock used to initialize the calculation models. However, various uncertainties exist in SOC stock datasets, and it’s unclear how that can affect cropland carbon budget and soil carbon credit calculations, according to lead author Wang Zhou, Research Scientist at the ASC and the Department of Natural Resources and Environmental Sciences (NRES) at Illinois.
In this study, researchers used an advanced and well-validated agroecosystem model, known as ecosys, to assess the impact of SOC stock uncertainty on cropland carbon budget and soil carbon credit calculation in corn-soybean rotation systems in the U.S. Midwest.
They found that high-accuracy SOC concentration measurements are needed to quantify a cropland carbon budget, but the current publicly available soil dataset is sufficient to accurately calculate carbon credits with low uncertainty.
“This is a very important study that reveals counter-intuitive findings. Initial soil carbon data is very important for all the downstream carbon budget calculation. However, carbon credit measures the relative soil carbon difference between a new practice and a business-as-usual scenario. We find that the uncertainty of initial soil carbon data has limited impacts on the final calculated soil carbon credit,” said ASC Founding Director Kaiyu Guan, Blue Waters Professor in NRES and the National Center for Supercomputing Applications (NCSA) at Illinois and lead of the DOE-funded SMARTFARM project at iSEE, which featured several co-authors on this paper.
The results indicate that expensive in-field soil sampling may not be required when focusing only on quantifying soil carbon credits from farm conservation practices — a major benefit for the agricultural carbon credit market.
“Uncertainty in SOC concentration measurements has a large impact on cropland carbon budget calculation, indicating novel approaches such as hyperspectral remote sensing are needed to estimate topsoil SOC concentration at large scale to reduce the uncertainty from interpolation. However, uncertainty in SOC concentration only has a slight impact on soil carbon credit calculation, suggesting solely focusing on quantifying soil carbon credit from additional management practices may not require extensive in-field soil sampling — an advantage considering its high cost,” Zhou said.
“The approach in this study can be applied to other models and used to assess important uncertainties of the carbon sequestration potential of various conservative land management practices,” said Bin Peng, the other primary author of the study and Senior Research Scientist at ASC and NRES.
The ASC was jointly established by the Institute for Sustainability, Energy and Environment (iSEE), the College of Agricultural, Consumer and Environmental Sciences (ACES), and the Office of the Vice Chancellor for Research and Innovation at Illinois.
Co-authors on the study included ASC Associate Director Andrew Margenot, Assistant Professor of Crop Sciences; DoKyoung Lee, Professor of Crop Sciences and ASC founding faculty member; Even DeLucia, Professor Emeritus of Plant Biology and ASC founding faculty member; Sheng Wang of ASC and NRES Research Assistant Professor; Ziqi Qin of ASC and graduate student in NRES; NRES Professor Michelle Wander; Jinyun Tang, Staff Scientist of the Earth and Environmental Sciences Area, Lawrence Berkeley National Laboratory; Zhenong Jin, Assistant Professor in the Department of Bioproducts and Biosystems Engineering, University of Minnesota; and Robert Grant, Professor in the Department of Renewable Resources, University of Alberta, Edmonton, Canada.
— iSEE Communications Specialist Julie Wurth
Bio-Based Chemicals Project: Homegrown Electronics for All
The world’s appetite for electronics is growing, but what happens when we are done with our old phones and tablets? Most electronics are not degradable, and their disposal contributes to a variety of environmental problems.
To help address this electronic waste problem, a University of Illinois research team led by D.K. Lee and Lisa Ainsworth is working to investigate the production and extraction efficiency of plant-based compounds that can be used to 3-D print biodegradable electronics. This research program, called the Bio-Based Chemicals Project, is part of a multi-institutional effort titled “Manufacturing ADvanced Electronics through Printing Using Bio-based and Locally Identified Chemicals (MADE-PUBLIC).” Funded by the National Science Foundation, MADE-PUBLIC is an interdisciplinary collaboration that brings together experts from the University of Chicago, the University of Illinois Urbana-Champaign, Argonne National Laboratory, Northwestern University, Iowa State University, and University of Illinois Chicago.
The MADE-PUBLIC team hopes to demonstrate a manufacturing paradigm that converts plant biomass into inks that can be used to print green electronic devices. Additionally, they aim to democratize the manufacturing of these electronic devices by enabling individuals to print their own devices.
“We’re using the lignin and cellulose content of plants to produce graphene and cellulose nanocrystals respectively,” said Kayla Vittore, a graduate student in Crop Sciences at Illinois and a member of the Bio-Based Chemicals Project’s operating team. “And those components can be used to make bio-based inks for a 3-D printing process that can produce biodegradable electronics.”
The Bio-Based Chemicals Project team is studying how a plant’s species and growth conditions influence its lignin and cellulose composition. This process will allow the team to determine the best conditions to produce bio-based inks.
To this end, Vittore is raising various plants, such as Miscanthus x giganteus, switchgrass, and fiber-industrial hemp, under different nutrient availability treatments. Once grown, the plants are harvested and analyzed. The research team is evaluating the plants’ cellular morphology, specifically the lignin and cellulose layers, to see if different nutrient treatments influence these structures. The ratios of lignin and cellulose are a determinant of both yield production and extraction efficiency, so these evaluations will inform the team’s strategies for optimizing the amount of bio-based ink that can be produced.
Among the biodegradable electronics that can be printed are precision agriculture sensors developed by the MADE-PUBLIC team. These electronics can be used to monitor the growth conditions of plants.
“We aim to create a closed production circle, where you can use plant products to make sensors that can monitor the air and water conditions important for plant growth,” said Lee, Co-PI of the Bio-Based Chemicals Project and Professor of Crop Sciences. “The sensors will allow users to optimize the plants’ production of lignin and cellulose, which can be used to produce more sensors and other biodegradable electronics. The goal of this project is to create renewable and accessible technology.”
The sensors, which are being developed with both small-scale home growers and large-scale factories in mind, can tell users information like “nitrogen is limiting growth” or “phosphorus is limiting growth.” Based on that information, users can apply fertilizers accordingly, which optimizes the system by increasing the amount of cellulose and lignin the plants produce.
The general public will have access to many different sensor designs to print. One exciting application of these sensors is for urban gardening. If someone is looking to address food deserts in cities, they would be able to print sensors to help them monitor the contents of the soil in their gardens.
In addition to helping growers and reducing electronic waste, MADE-PUBLIC also helps address the supply chain issues common in electronics manufacturing.
“If people are growing their own plants to produce the lignin and cellulose to print their own electronics, that’s a much shorter supply chain than the big systems we rely on right now,” Vittore said.
Shorter supply chains mean reductions in greenhouse gas emissions, as there’s less travel involved. Additionally, as we’ve seen during the COVID-19 pandemic, longer supply chains are more apt to collapse when disrupted.
MADE-PUBLIC is made possible by the combined efforts of experts from a wide variety of fields and institutions. While researchers at Illinois — who became partners with the help of iSEE’s proposal development office — are working to increase the production and extraction efficiency of lignin and cellulose, MADE-PUBLIC collaborators from different institutions are working on other vital parts of the production cycle, such as producing the 3-D printable ink, designing the sensors, and 3-D printing the sensors and other electronics.
“It’s been fun working with people from different disciplines,” Vittore said. “We’re always learning new things from each other, which is a good opportunity to grow our communication skills. And leaning on each other’s different specialties allows us to do much more than we could as an independent lab.”
Said Lee: “I was very surprised. For many projects like this, the principal investigators will connect across institutions, but the grad students not so much. But the MADE-PUBLIC grad students have been very collaborative and good at communicating across institutes and disciplines.”
It’s easy to be cynical about electronic waste, but with so many passionate researchers putting their heads together to solve this problem, there is hope.
“We’re trying to give people and companies the tools so that when they have the resources to do so, they can make sustainable choices,” Vittore said. “Many 3-D printers use unsustainable materials, like plastics, but if there are alternatives available, people can choose a more renewable source. Making sustainability accessible goes a long way.”
For more information about MADE-PUBLIC, check out the multi-institutional project website >>>
— Article by iSEE Communications Specialist April Wendling
U of I SMARTFARM Researchers Use Novel AI to Model GHG Emissions
University of Illinois researchers were part of a multi-institutional team that has significantly improved the performance of numerical predictions for agricultural nitrous oxide emissions using novel modeling that combines artificial intelligence and process-based knowledge.
According to a release from the University of Minnesota — home of the corresponding author and Digital Agriculture Group lead Zhenong Jin — the team developed a first-of-its-kind knowledge-guided machine learning model for agroecosystem, called KGML-ag, which is 1,000 times faster than current solutions and also significantly improves the modeling accuracy of greenhouse gas emissions from agriculture.
The research was recently published in Geoscientific Model Development. Researchers involved were from Minnesota, Illinois, Lawrence Berkeley National Laboratory, and the University of Pittsburgh. According to the Minnesota news release, KGML-ag was constructed by a special procedure that incorporates the knowledge learned from an advanced agroecosystem computational model, called ecosys, to design and train a machine learning model. In small, real-world observations, the KGML-ag turns out to be much more accurate than either ecosys or pure machine learning models.
“This is revolutionary work that brings together the best of observational data, process-based models, and machine learning by integrating them together,” said Kaiyu Guan, a coauthor of the study, Founding Director of the Agroecosystem Sustainability Center (ASC) and Blue Waters Associate Professor of Natural Resources & Environmental Sciences (NRES) at Illinois. Guan is the Project Director of the U.S. Department of Energy’s Advanced Research Projects Agency-Energy (ARPA-E) Systems for Monitoring and Analytics for Renewable Transportation Fuels from Agricultural Resources and Management (SMARTFARM) project that funded the study.
“We are really excited to continue this collaboration with the University of Minnesota team led by Zhenong Jin to explore and realize the full potentials of KGML,” Guan said.
Jin, Assistant Professor of Agroecosystem Modeling at Minnesota, and Vipin Kumar, Professor and Head of Computer Science and Engineering at Minnesota, are co-authors who work on the SMARTFARM project led by Guan. ASC and SMARTFARM team member Bin Peng and ASC team member Wang Zhou, both from NRES at Illinois, also were among the article’s 16 authors. Guan and Peng are affiliated with the National Center for Supercomputing Applications at Illinois. ASC is a collaboration between the Institute for Sustainability, Energy, and Environment, the College of Agricultural, Consumer, and Environmental Sciences, and the Office of the Vice Chancellor for Research & Innovation.
“There is a lot of excitement around the potential for agriculture to contribute to carbon drawdown, but unless we have accurate and cost-effective measurement tools to assess what is happening both above- and below-ground, we won’t see the market incentives we know are necessary to facilitate a transition to net-negative agriculture,” said David Babson, an ARPA-E Program Director. “I’m looking forward to the teams further expanding this research.”
Read more specifics about KGML-ag in the full University of Minnesota article >>>
Read the journal article in Geoscientific Model Development >>>