The Institute for Sustainability, Energy, and Environment (iSEE) is accepting proposals to support interdisciplinary research, visioning, and planning activities on ambitious topics related to sustainability, energy, and environment. The iSEE seed funds are available to promote meaningful research collaborations among faculty and scientists across campus and to raise the national visibility of U. of I. and the research team in the topic area. The specific goal of the funding is to expedite the coalescence of interdisciplinary research teams that touch on any of the thematic areas of interest to iSEE and to develop multiple strong, large-scale (>$1M) proposals that can be submitted for external funding through iSEE in 2026-27.
Three types of proposals are invited:
Seed Research projects are limited to a maximum of $30,000 for one year. Funding may support research assistantships for graduate students, postdoc time, data purchase, travel, and/or other necessary expenses that support growth of the initiative. Faculty summer salary and equipment are excluded from this funding.
Campus as a Living Laboratory (CALL) projects are limited to a maximum of $30,000 for one year. CALL projects link faculty researchers to sites or initiatives on campus that are relevant to objectives in the Illinois Climate Action Plan (iCAP). CALL researchers are also expected to leverage the seed funding to develop interdisciplinary external funding proposals through iSEE.
Visioning and Planning Activities are limited to a maximum of $50,000 (total) spread over two years. Funding may support workshops and planning meetings hosted by the project team, in addition to activities similar to Seed Research and CALL projects. Year two funding is contingent upon meaningful progress in year one.
All proposals must meaningfully involve researchers from at least two different disciplines and two different campus units. Proposals should address research questions in one or more iSEE thematic areas of climate solutions, energy transitions, secure & sustainable agriculture, sustainable infrastructure, and water & land stewardship. Along with these themes are the cross-cutting topics of circular bioeconomy and policy.
Successful applicants for the seed funding and CALL projects will be expected to submit external funding proposals related to this seed funding through iSEE in 2026-27. Applicants for Visioning and Planning Activities proposal should explain how their activities will promote multi-disciplinary, multi-institutional collaborations that need a long lead time to develop a team to submit a proposal for a large, team-based Center-type grant.
Successful external funding proposals submitted through iSEE will not affect indirect cost recovery to the home department of the PIs. iSEE will provide personnel support for event planning, proposal development, and, in the case of successful external proposals, post-award management. Recipients will also work with iSEE to communicate the findings of their activities, research, publications, and other outcomes.
Guidelines for preparing the proposal
Proposals are invited from faculty and scientists who are currently eligible to serve as PIs on proposals for external funding (e.g., tenured/tenure-track faculty, research professors, research scientists). Postdocs are not eligible to apply. Updated versions of previously submitted proposals may be resubmitted if feedback from the iSEE review has been addressed. The proposal will be submitted through an online portal with the following sections:
Project title
Principal and co-investigator information (names, affiliations, and email addresses)
Abstract [up to 150 words]
Motivation and Opportunity [up to 500 words]
Describe the scholarly merit, innovation, and substantive interdisciplinarity of the proposed research.
Team Science Approach [up to 400 words]
Describe the need for interdisciplinary collaboration and the role and contribution of each team member to tackle the problem at hand.
Plan for Seed Funding [up to 600 words]
Describe specific plans for the use of seed funding and the potential impact on national visibility and growth of the initiative. Describe the potential to develop a large-scale (>$1M), externally funded research program, including a comprehensive plan with specific funding opportunities (anticipated in 2026-2027), which the applicants will pursue.
Summarize any previous efforts to secure external funding for this research.
Other campus seed funding sources [up to 200 words]
If you are receiving seed funding from any other unit on campus in the 2025-26 or 2026-27 year for this project or closely related research, please describe how that seed funded research differs from this proposal.
Additionally, a single compiled PDF with the following documents for the principal investigator (PI) and co-investigators (co-Is) is required: (i) a CV (up to three pages) that includes five most relevant recent publications and five other publications; (ii) a summary of all internal and external current and pending research funding; and (iii) an itemized budget (with no F&A or fringe benefits included). SciENcv is the recommended format for CV and current and pending.
The deadline for proposal submissions is 5 p.m. Wednesday, April 8, 2026, uploaded to the OVCRI Special Programs site. Applicants will be informed about final funding decisions by mid-May, with a start date for funding beginning or after August 15, 2026.
Questions about this RFP may be addressed to Jeremy Guest, iSEE Associate Director for Research at jsguest@illinois.edu.
URBANA, Ill. — A new AI-based system can generate high-resolution soybean yield maps across Brazil using only limited local data, improving yield estimates for this key agricultural region and potentially providing strategic benefits to global soybean markets.
Soybeans at the South Farms. Credit: Brian Stauffer/University of Illinois Urbana-Champaign
The newly published work by researchers at the University of Illinois Urbana-Champaign demonstrates an innovative approach that enables high-performance national yield estimates for Brazilian soybeans, even in areas where directly reported local yield data are very limited.
By leveraging knowledge learned from earlier U.S.-based work through so-called “AI transfer learning,” the research team was able to make detailed yield predictions at the municipal level using Brazil’s state-level soybean yield data. It’s one of the first successful nationwide applications of cross-scale AI yield predictions for Brazilian agriculture.
Although Brazil is currently the world’s largest soybean producer and a major global food exporter, high-resolution yield data for Brazilian soybeans remain largely unavailable. These data are essential for precision agriculture, risk management, and sustainability planning, and the data scarcity has hampered scientific understanding of this important agricultural region. Previous crop yield modeling — which relies on coarse state-level data to model finer predictions at the municipal or field level — has demonstrated limited performance nationally.
The Illinois research team developed a new framework to predict national soybean yields at a finer level by integrating satellite observations, climate data, and state-level yield statistics, leveraging AI transfer learning techniques with the knowledge learned from their U.S. based models.
Remarkably, the model for Brazilian soybean achieved strong predictive performance without using any municipal-level yield data. The explained variance (R²), a key measure of effectiveness, doubled in the new model compared to conventional cross-scale studies. When municipal data were included, performance improved further (R² of 0.57), comparable to the best existing approaches that rely on much more abundant data.
The power of transfer learning
A key innovation of the study is the use of AI transfer learning, which allows scientists to reuse existing models rather than starting from scratch in each region. This makes it possible to generate detailed agricultural information in areas where collecting large amounts of local data would be costly, slow, or impractical.
Spatial maps of the yield data show the harvested-area-weighted average soybean yield across all valid years for each municipality (left); and the standard deviation across all valid years in each municipality. Credit: Paper in the International Journal of Applied Earth Observations and Geoinformation.
For this work, knowledge from an advanced model that was trained to predict soybean yield in the U.S. was adapted to Brazilian growing conditions. By fine-tuning the U.S. model using only state-level data or sparse municipal-level data from Brazil, the researchers were able to account for differences in climate, crop phenology, and management practices between the two countries.
First author Jiaying Zhang explained, “This approach boosted the effectiveness of cross-scale yield prediction from 50 percent to 78 percent of the theoretical upper limit, which we defined as the best performance achieved by models trained with highly detailed local yield data. The results demonstrate that AI-driven transfer learning can overcome both data scarcity and scalability challenges in agricultural modeling.”
Implications for yield predictions worldwide
The findings arrive at a pivotal moment for global soybean markets.
In 2018, Brazil surpassed the United States to become the world’s largest soybean producer for the first time. The ability to monitor and forecast production in detail is essential for understanding global soybean supply as well as the environmental impacts of large-scale agriculture in Brazil. Enhanced predictability of soybean yield will enable more accurate assessments of supply-demand relationships, land-use change, and soil health impacts at scale for more informed decision-making.
“The ability to monitor and anticipate crop production regionally and globally with high fidelity is strategically important for market analysis, trade forecasting, and risk assessment for U.S. soybean producers,” said the project lead and senior author Kaiyu Guan, Levenick Endowed Professor and Director of the Agroecosystem Sustainability Center at Illinois.
The study provides a pathway for applying advanced yield modeling in regions of the world with limited data, supporting food security planning, climate risk management, and evidence-based agricultural policy. By leveraging models trained in data-rich regions and adapting them to areas where data are scarce, the approach opens new opportunities for cost-effective, global-scale agricultural intelligence.
The study is titled “Transfer learning for improved crop yield predictions in a cross-scale pathway: a case study for Brazilian national soybean” (DOI: 10.1016/j.jag.2025.104981).
The work was supported by the National Science Foundation and the U.S. Department of Agriculture.
Pesticide use is integral to modern-day farming, but it has carried unintended consequences. Research shows pesticides have caused steep declines in the populations of bees and other pollinators vital to agriculture, as well as possible links to cancer and other diseases.
Scott McArt. Credit: Cornell University
The 2026 iSEE Critical Conversation, “Balancing the Intended and Unintended Effects of Managing Pests,” is scheduled for March 5-6 at the Illini Center in Chicago. The two-day event will bring together scientists, farmers, beekeepers, and industry and nonprofit leaders to encourage dialogue and find solutions to this complex challenge.
The public portion of the event is a March 5 keynote address by Scott McArt, Associate Professor of Pollinator Health at Cornell University.
McArt started his career as a chemical ecologist, studying the chemistry that influences interactions among different organisms – in his case, the natural toxins in plants that make them inedible to predators. About 15 years ago, he shifted his work to explore the impact of unnatural toxins – pesticides – on organisms and how that contributes to biodiversity loss. While other toxicologists had documented their harmful effects, McArt wanted to know exactly which pesticides bees and other pollinators are being exposed to, and at what levels, to better understand the risks and pinpoint solutions. Through his appointment with Cornell Cooperative Extension, McArt also works directly with beekeepers, farmers, and regulatory agencies to improve pollinator conservation and health.
In this Q&A, McArt explains the challenges posed by pesticides and the work he and others have done to address them. This interview has been edited for length and clarity.
This year’s iSEE Critical Conversation will focus on the effects of pesticide use. Why is this a timely topic right now?
I would say the reason we are talking about this is that we’re in a global biodiversity crisis. There are species that are being impacted by the things that we do. And agriculture happens to be one of those major things, and pesticides happen to be one of the stresses in agriculture that is contributing to biodiversity loss.
How do you benefit people but also benefit the environment? There is a constant tension between those two things as the global population gets to the point where we’re having significant impacts on the land and the various animals that live on that land.
Pesticides are used to improve yields by controlling pests that are harmful to crops. Are their benefits overstated?
With current agricultural practices, how we set up modern farming, we are absolutely reliant on pesticides. If we didn’t have pesticides, we would experience yield losses, there’s no question about that. But maybe we’re not doing agriculture in a way that is actually sustainable. Maybe we’re doing agriculture in a way that is overly reliant on pesticides.
I will be talking about some examples where, in certain contexts, we can show very conclusively that we are overusing some pesticides. The risks outweigh the benefits. In other application contexts, we can’t show that. The benefits are really clear, and there might be risks, but then the issue becomes: If we are going to get rid of something, we’re going to lose a major benefit, even though we might be harming wildlife in the process. That becomes less of a biological question and more of a social question or even an economic question. That’s why I think this interdisciplinary workshop is really necessary for this particular topic.
What are the unintended effects of pesticide use on pollinators and other wildlife? What are the biggest risks they pose? Are some of those difficult to measure?
Our lab does a lot of risk assessment for pollinators. There’s no perfect way of doing risk assessment, but what we can say is that there are problems with pesticides. They are directly linked to declines of many species in our country, including pollinators – that’s not just bees, but butterflies, moths, and other species of pollinators. And it’s not just pollinators – it’s a lot of other things, especially insects, but frogs and other species as well. We know pesticides have a long-term negative impact on many of these species, and they are a contributor to biodiversity loss. So clearly we are using pesticides in a way that, if the goal of the risk assessment and pesticide registration process is to minimize those nontarget effects, well, we’re failing.
Can you give an example of the specific impact, especially on bees?
McArt examines a bee colony with undergraduates in a summer research program in 2019. Credit: Delanie Sickler
Last year, honeybee colony losses in the United States were at 56%. That is the highest honeybee colony loss rate in recorded history. This year, some of the early reports we’re getting from commercial beekeepers are just as troubling. So will it be 56% again? I don’t know, but that is unsustainable. Beekeepers are going out of business because they can’t sustain that level of losses year after year.
Are pesticides driving all of those losses? Absolutely not. There are other factors that also play a role. But pesticides are definitely playing a role.
For wild pollinators, based on the most recent science, we know that the use of two types of pesticides in particular, neonicotinoids and pyrethroids, are the strongest predictor of wild bee declines in the United States. This was from a Nature paper last year, which put lots of different factors into a really impressive analysis. Over and over, for the past decade or so now that we’re starting to get large-scale studies like this, we’re seeing that pesticides are, if not the major driver, one of the major drivers of insect declines in the U.S., and globally.
Why is it important for growers to consider these unintended effects? What are the costs to our environment, the agricultural economy, and our food supply?
If you’re an environmentalist, any loss of species is disheartening to you. But not everybody is an environmentalist. Other people might say, OK, if using pesticides is necessary for my livelihood, what’s the problem with losing a species or two? Or, more likely, they may have no idea that pesticides are causing large-scale environmental problems. I think that’s again a social issue that needs to be navigated.
From an economic perspective, we know a lot of insects play major roles not only in the functioning of natural systems, but also in the functioning of farms. So if you’re in pollination agriculture, and you have half the number of bees in your orchard, you have half the amount of pollination occurring; therefore, yield may go down in those crops. If you’re in corn and soybeans, yield might not actually change all that much – maybe in soybeans because they’re pollination-dependent to some extent, but corn pretty much is wind-pollinated.
What about all the soil microorganisms – all of the beetles and the various things that live in the soil? If you wipe them out, nutrient cycling goes away. Soil fertility declines. Alternatively, if we wipe out the predators of the pests, there might actually be a pest outbreak.
The other axis is probably the one that resonates with most people: human health effects. A recent study from Iowa shows cancer rates going up quite a bit in that state, and it seems to be tracking with pesticide use. So is that the driver? We don’t really know. But if more and more pesticides are being used, and you’re getting more cancers, more Alzheimer’s, and other human diseases, it could potentially be playing a role. I would say that’s much less abstract to most people. Some people may like bees, while others may have absolutely no idea what a pollinator is. But every single person understands cancer in their own child or in themselves.
What specific topics will you be addressing in your keynote?
I’m a biologist, and I do a lot of risk assessment. In the past 10 years or so I’ve become sort of a closet sociologist, because no progress can be made on this topic by only considering biology. I also collaborate with economists in almost every single thing that we do now, because when people are making decisions about pesticides, oftentimes economics has to be considered. Navigating that complex biological, social, and economic landscape to try and figure out how we make these agricultural systems sustainable, how we define sustainability and then also come to some agreement to make things sustainable – it’s not easy, as you might expect.
I’ll be giving a few different stories of ways that we have been successful in navigating things. One is with a new law restricting pesticides that’s now been implemented in New York, as a direct result of the work we’ve done – not just me, but a lot of other people who contributed as well.
Another story I’ll talk about is something that’s been much more industry-driven: how a commercial apple company initiated a successful reduced-spray pesticide program. It is not only benefiting pollinators but looks like it’s benefiting the growers as well – something that’s not the heavy hand of government but is driven by private industry, the sellers of the apples that are grown by farmers.
The third story I’ll share is something that is actually driven by the stakeholders themselves: beekeepers who want to understand how pesticides are playing a role in colony losses throughout the United States. Bees are exposed to myriad pesticides in the environment, which isn’t good of course. But beekeepers also use pesticides to control parasites in their colonies. One of the major issues the beekeeping industry is facing right now is that they themselves are overusing one particular pesticide. When they do that, the parasites evolve resistance to the pesticide, and unfortunately, they end up doing more harm than good. So we’ve worked with many beekeepers to stop using that pesticide exclusively, to instead use cultural controls, rotations with other pesticides, and other integrated pest management tactics. The parasites don’t develop resistance as quickly, and the beekeepers are able to control them more effectively.
Can you say more about the effort to pass the 2025 New York law that restricts the use of neonicotinoid-treated seeds and its impact?
McArt testifies to the New York State Assembly about proposed pesticide legislation in September 2021. Credit: Julie Suarez
We have this new law in New York state because, honestly, we did a lot of background work to try and get all these groups together, similar to what you’re doing with iSEE. There’s now a new law in Vermont that mimics the New York law; Massachusetts is considering it, Pennsylvania is considering it, and Colorado is considering it. And I was just out in Minnesota, our first Midwestern state, where we had a full day-long workshop that is very similar to what iSEE is putting together. Minnesota is now considering trying to mimic what we’ve done here in New York. The only way to make that successful is to have these really difficult conversations with a lot of different stakeholders at the table, and people with various expertise. There was a lot of enthusiasm, even from the pesticide companies and seed distributors, after that discussion, because everyone felt heard.
People have very strong opinions on the topic of pesticides. And often you’re not going to change anyone’s mind. But you can facilitate a conversation, and you can make people feel heard. In the places that I’ve gone, oftentimes that’s the first step to going a bit further.
Do you see shifting attitudes toward pesticides among farmers and others in the agricultural community as a result of your work?
I’ve been working with apple growers for about 10 years now. No farmer wants to kill bees, and all the growers that I interact with are very receptive to learning more about pesticides, because they want to have good pollination. But they also want to have good pest control. So it’s a constant balance they have to navigate: good pest control, but not overdoing it and killing all the bees, because then they won’t have apples.
More recently, the topic of neonic seed treatments has been at the forefront. That involves talking to corn and soybean growers. There are almost zero corn and soybean growers who feel like they rely on pollinators, so the dynamic and knowledge base is different from that of apple growers. A lot of people just have absolutely no idea that these seed treatments are harming pollinators. That said, I think we’ve seen a major cultural change in New York. Seven years ago, I think it’s safe to say that most field crop farmers did not appreciate me bringing up this topic. Now, not only do we have a new law banning the seed treatments because of the impact on pollinators, but a lot of farmers are buying into it. Perhaps more importantly, they had no idea there were almost no economic benefits from using seed treatments.
Do your studies show that neonic seed treatments don’t do much good? Are the benefits oversold?
In that particular application context, which happens to be the major use of neonicotinoid insecticides in the entire world, including in Illinois, they have extremely infrequent benefits. We estimate that somewhere between 93 to 94 percent of farmers are losing money from using them.
The reason why seed treatments were thought to be so good is that they let you greatly reduce the amount of pesticide that’s applied on a field. Instead of blanket spraying, you can put just a little bit of pesticide on a seed, and then the seeds are protected. So on a field-by-field basis, it could be considered a good thing. But the problem is overuse. We suspect that somewhere between 90 and 100 percent of corn fields in the United States and the majority of soybeans are planted with neonicotinoid seed treatments.
Neonics are also by far the most toxic insecticides to most insects – about an order of magnitude more toxic than any other insecticide. So even though we’ve been using about the same amount of insecticides over the past 20 years on a pound-by-pound basis in the U.S., by using more and more neonics, we’ve made the environment about 10 times more toxic to insects – which is probably why we’re noticing that direct relationship between neonic use and declines in pollinators.
One reason farmers use neonics is that they consider them inexpensive crop insurance. They might only have pests 5 to 6 percent of the time, but the seed treatments provide protection in that very rare chance of a major pest outbreak. But when every single person does that, it becomes the tragedy of the commons.
How can researchers work with farmers/growers to help them understand the impact of pesticide use and maybe change their management practices?
Number one, listen. Researchers and scientists are very good at talking, but we’re not as good at listening. If you’re a scientist who’s reading this, listen to farmers. You might just learn something.
Also, be a service, be a resource for that person.
And third, just be humble. I see a lot of interactions with farmers where maybe the scientist has listened, maybe they’ve provided some data, but they’re not really humble. They kind of come off as some egghead from an ivory tower. That’s a great way to lose a productive dialogue, to lose trust. If we’re going to work together to solve big issues – and sustainable pesticide use in agriculture is absolutely a big, complex issue – well, it turns out working together requires trust. So be humble and earn that trust. Those are my three keys.
– Article by iSEE Communications Specialist Julie Wurth
