With evolutionary AI, scientists find hidden keys for better land use
Researchers say the AI system can lead to better decision-making around a wide range of complex policy choices
University of Texas at Austin
image:
Aerial photo of original, cleared, and planted land
view moreCredit: Sam Beebe: https://www.flickr.com/photos/28585409@N04/3275040520
Using global land use and carbon storage data from the past 175 years, researchers at The University of Texas at Austin and Cognizant AI Labs have trained an artificial intelligence system to develop optimal environmental policy solutions that can advance global sustainability initiatives of the United Nations. The AI tool effectively balances various complex trade-offs to recommend ways of maximizing carbon storage, minimizing economic disruptions and helping improve the environment and people’s everyday lives, according to a paper published today in the journal Environmental Data Science.
The project is among the first applications of the UN-backed Project Resilience, a team of scientists and experts working to tackle global decision-augmentation problems—including ambitious sustainable development goals this decade—through part of a broader effort called AI for Good. University of Texas at Austin computer scientist Risto Miikkulainen, who helped launch Project Resilience, believes the new AI approach, initially focused on land use, can address an even larger set of challenges, from infectious diseases to food insecurity, with artificial intelligence potentially discovering better solutions than humans.
“There’s always an outcome you want to optimize for, but there’s always a cost,” he said. Amid all of the trade-offs, AI can home in on unexpected pathways to desirable outcomes at various costs, helping leaders selectively pick battles and yield better results.
The secret sauce of the researchers’ system is evolutionary AI. Inspired by the process of natural selection in biological systems, this computational approach starts with a few dozen policy scenarios and predicts how each scenario will impact various economic and environmental costs. Then, like a digital version of survival of the fittest, policy combinations that don’t balance the trade-offs well are killed off, while the best ones are allowed to reproduce, giving rise to hybrid offspring. Random mutations also are sprinkled in to help the system explore novel combinations faster. The process then repeats, winnowing poor performers and keeping the best, across hundreds or thousands of scenarios. Like biological evolution, the “generations” of scenarios become ever-more optimized for a set of priorities.
The team used two tools—a recently released set of global land use data going back centuries and a model that correlates land use with carbon fluxes. First, they used this data to train a prediction model to correlate location, land use and carbon over time. Second, they developed a prescription model to help decision makers find optimal land-use strategies to reduce climate change.
The AI system’s recommendations sometimes surprised the team. Although forests are known to be good at storing carbon, the AI prescription model offered a more nuanced approach than converting as much land as possible into forests, regardless of location. For example, it found that replacing crop land with forest is much more effective than replacing range land (which includes deserts and grasslands). Also, generally, the same land use change at one latitude didn’t yield the same benefits as at another latitude. Ultimately, the system recommended that larger changes should be allocated to locations where it mattered more; in essence, it’s more effective to pick your battles.
“You can obviously destroy everything and plant forests, and that would help mitigate climate change,” said Daniel Young, a researcher at Cognizant AI Labs and a Ph.D. student at UT Austin. “But we would have destroyed rare habitats and our food supply and cities. So we need to find a balance and be smart about where we make changes.”
The researchers have turned their model into an interactive tool that decision makers like legislators can use to explore how incentives, such as tax credits for landowners, would be likely to alter land use and reduce carbon.
Land use activities, including agriculture and forestry are estimated to be responsible for nearly a quarter of all human-caused greenhouse gas emissions. Experts believe smart land use changes will be needed to reduce the amount of carbon in the air and thereby slow climate change. According to Miikkulainen and Young, AI offers options that people, businesses and governments otherwise resistant to change may find easier to accept.
An earlier version of the paper was presented at a major machine learning and computational neuroscience conference, NeurIPS, where it won the “Best Pathway to Impact” award at the Climate Change workshop.
The other authors on the paper are Olivier Francon, Elliot Meyerson, Clemens Schwingshackl, Jakob Bieker, Hugo Cunha and Babak Hodjat.
Journal
Environmental Data Science
Method of Research
Computational simulation/modeling
Subject of Research
Not applicable
Article Title
Discovering effective policies for land-use planning with neuroevolution
Article Publication Date
19-May-2025
Publication reveals soil lab use, fertility findings for blackberries, row crops, forages
Recent soil fertility publication tracks results of soil testing samples from across state
University of Arkansas System Division of Agriculture
image:
The annual Wayne E. Sabbe Arkansas Soil Fertility Studies publication guides nutrient management recommendations to improve soil health and crop yield.
view moreCredit: U of A System Division of Agriculture photo
FAYETTEVILLE, Ark. — When you test more than 200,000 soil samples in a year, you not only learn something about how Arkansans grow crops, gardens and lawns, but also the value of recommendations that result from soil test results.
Each year, the Arkansas Agricultural Experiment Station publishes the Wayne E. Sabbe Arkansas Soil Fertility Studies. The latest edition, released in spring, features 12 research reports prepared by scientists with the University of Arkansas System Division of Agriculture and the Dale Bumpers College of Agricultural, Food and Life Sciences at the University of Arkansas.
This edition includes investigations into the effects of fertilization on row crops, blackberries, forage and soil, plant tissue nutrient testing and perceptions of stakeholders when it comes to the state’s public soil testing program.
Each year, the feature article summarizes the chemical properties of soil samples to the Arkansas Soil Testing Program. In 2023, Arkansas clients submitted a record of 201,896 soil samples — representing approximately 1.5 million acres of land — to the experiment station’s Marianna Soil Test Lab. The article found that row crop use accounted for 74 percent of sampled acreage, hay and pasture uses accounted for 15 percent, and home lawns and gardens accounted for 2.3 percent. Mississippi County submitted the most samples, with 26,953; Clay was next at 23,141 and Poinsett County was third with 22,669 samples.
A study led by Aurelie Poncet, assistant professor with the crop, soil, and environmental sciences department, found that 81 percent of those who submitted samples to the soil test lab used lime and fertilizer recommendations from the Division of Agriculture to improve soil fertility.
“We have a very comprehensive record each year about the status of soil fertility across the state of Arkansas,” said Nathan Slaton, who edited the publication and serves as associate vice president for agriculture and assistant director of the experiment station.
Slaton noted how the publication’s reports are of interest to a variety of stakeholders, from horticulturists to rice producers, reflecting the widely applicable nature of the work.
The online publication sees hundreds of downloads from across the United States — and the world — Slaton said. Ultimately, the publication helps university researchers validate or develop new fertilizer and soil nutrient management recommendations.
“It’s important that as production systems change and new genetics are released into the hands of farmers … that soil fertility data that evaluates the reliability of soil test information is checked over time,” Slaton said.
The 2024 Arkansas Soil Fertility Studies include:
- Arkansas soil-test summary for samples collected in 2023
- Sulfate runoff dynamics from edge-of-field losses at selected Arkansas Discovery Farms
- Potassium fertilization effects on cotton yield and tissue-K concentration in Arkansas
- Assessment of potassium loss by runoff in different cotton production systems
- Bermudagrass forage yield and soil test response to phosphorus and potassium fertilization
- Verifying nitrogen rate recommendations for blackberry grown in Arkansas
- Effectiveness of in-season potassium fertilization on irrigated corn production
- NUMBERS: Nutrient management database for effective rate selection
- Assessing producers’ engagement with the services provided by the Marianna Soil Test Laboratory
- Updated profit-maximizing potash fertilizer recommendations for corn
- Cotton response to nitrogen on silt loam soils: Year two results
- Cover crop and phosphorus and potassium application rate effects on soil-test values and cotton yield
Soil testing is conducted at the Marianna Soil Test Lab.
Credit
U of A System Division of Agriculture photo
Leading free soil testing
All Arkansans can submit soil for free testing thanks to the Arkansas Fertilizer Tonnage Fee Program. Fertilizer tonnage fees are used to support routine soil testing services, soil fertility research, and the regulation and enforcement of fertilizer-related laws that benefit both farmers and the broader public.
Residents can submit soil samples to an Arkansas Cooperative Extension Service county office, which will then forward them to the Marianna lab. These extension offices are located in each of Arkansas’ 75 counties. The extension service is the outreach arm of the Division of Agriculture.
The lab’s routine analysis sheds light on soil pH and nutrient availability for selected nutrients, providing recommendations to achieve optimal soil fertility based on crop. The testing is used by individuals from golf course superintendents and farmers to home gardeners and landscapers.
Poncet’s study assessed producers’ use and satisfaction when it comes to the Marianna lab. Researchers collected 98 responses that were considered representative of Arkansas producers’ practices.
Responses revealed that most of the state’s producers collect soil samples to inform their management practices and use the free soil testing services provided by Marianna lab. Overall, most Arkansas producers are satisfied with the lab and its services.
The Marianna lab, which is the second-largest public soil testing program in the United States, accounts for 80 to 85 percent of the analysis for all of the samples collected in Arkansas, according to Slaton.
To learn more about the Division of Agriculture research, visit the Arkansas Agricultural Experiment Station website. Follow us on X at @ArkAgResearch, subscribe to the Food, Farms and Forests podcast and sign up for our monthly newsletter, the Arkansas Agricultural Research Report. To learn more about the Division of Agriculture, visit uada.edu. Follow us on X at @AgInArk. To learn about extension programs in Arkansas, contact your local Cooperative Extension Service agent or visit uaex.uada.edu.
About the Division of Agriculture
The University of Arkansas System Division of Agriculture’s mission is to strengthen agriculture, communities, and families by connecting trusted research to the adoption of best practices. Through the Agricultural Experiment Station and the Cooperative Extension Service, the Division of Agriculture conducts research and extension work within the nation’s historic land grant education system.
The Division of Agriculture is one of 20 entities within the University of Arkansas System. It has offices in all 75 counties in Arkansas and faculty on three system campuses.
Pursuant to 7 CFR § 15.3, the University of Arkansas System Division of Agriculture offers all its Extension and Research programs and services (including employment) without regard to race, color, sex, national origin, religion, age, disability, marital or veteran status, genetic information, sexual preference, pregnancy or any other legally protected status, and is an equal opportunity institution.
Article Title
Wayne E. Sabbe Arkansas Soil Fertility Studies 2024
No comments:
Post a Comment