SAES-422 Multistate Research Activity Accomplishments Report
Sections
Status: Approved
Basic Information
- Project No. and Title: NC1210 : Frontiers in On-Farm Experimentation
- Period Covered: 01/01/2024 to 01/01/2025
- Date of Report: 03/06/2025
- Annual Meeting Dates: 01/09/2025 to 01/10/2025
Participants
Abban-Baidoo, Emmanuel Auburn University Adotey, Nutifafa University of Tennessee Ashworth, Amanda USDA-ARS Augarten, Abby University of Wisconsin-Madison Baath, Gurjinder Texas A&M Boerngen, Maria Illinois State University Brorsen, Wade Oklahoma State University Bugingo, Collins Oregon State Bullock, David University of Illinois Chandel, Abhilash Virginia Tech Clark, Jason South Dakota State University Delport, Marion BFAP Dey, Sourajit Kansas State University Dhillon, Jagmandeep Mississippi State University Dos Santos, Caio Iowa State Du, Qianqian University of Illinois Edge, Brittani University of Illinois Felehgari, Shilan Montana State Gabbard, Daniel (Scott) Purdue Griesbaum, Brett Montana State Griffin, Terry Kansas State University Islam, Md. Sayemul Montana State Jones, Carli University of Illinois Kumar, Hemendra University of Maryland Lanza, Phillip Cornell Leise, Adam University of Nebraska-Lincoln Li, Johnny University of Idaho Li, Xaiofei Mississippi State University Liu, Guodong University of Florida Miao, Yuxin University of Minnesota Mieno, Taro University of Nebraska-Lincoln Miguez, Fernando Iowa State Mousavi, Mona University of Nebraska-Lincoln Negrini, Renzo University of Minnesota Nugent, Paul Montana State Pinto, Ricardo Montana State Pires, Carlos North Dakota State University Proulx, Rob North Dakota State University Ransom, Curtis USDA-ARS Schwarck, Lauren Iowa State Setiyono, Tri Louisiana State University Shajahan, Sunoj University of Illinois Sheppard, John Montana State Stechschulte, Logan University of Illinois Sundquist, Aaron Mitchell Tech Tao, Haiying University of Connecticut Van Der Westhuizen, Divan BFAP Wahl, Scott University of Illinois Won, Sunjae Auburn University Yost, Matt Utah State University Zheng, Yiling University of Connecticut Zhou, Congliang Louisiana State University Owens, Phillip USDA-ARS Sun, Rex North Dakota State University
See attached meeting minutes.
Accomplishments
Short-term Outcomes:
As part of NC-1210, in 2016 DIFM scholars submitted and received $4 million from USDA-NRCS, with the purpose of working with famers to run several hundred on-farm precision experiments and creating a "cyber-infrastructure" that enables users to create OFPE designs, to import, process, and analyze OFPE data, and to write reports on the agronomic and economic implications of the data analysis. DIFM and NC-1210 have accomplished these goals. This system is freely available to the public at https://difm.farm. The sytem is now being used by dozens of farmers, crop consultantsj, extension personnel and agronomic researchers to run OFPEs and evaluate the economic implications for crop production management. From some of the trials, data-driven insights are leading to dramatic increases in profits. Other trials have provided mixed results. We expect the insights and social benefits derived for the OFPE data we are working with farmers to generate will only grow as the development and use of the difm.farm cyber-infrastructure progress and goals have been accomplished.
Outputs:
A major insight from the data the DIFM project has generated is that producers’ corn and soybean seed planting densities are often higher than economically optimal. On some farms, particularly those in the drier parts of the Corn & Soy Belt, the planting rates recommended by seed companies and university extension guidelines seem often to be higher than is economically optimal. Another insight is that farmers’ nitrogen fertilizer application rates, in contrast to wide speculation, are not in general higher than the economically optimal rates. This means that there is no “win-win” opportunity available in which farmers increase profits by cutting their fertilization rates and thereby reduce drop nutrient losses into the nations’ water systems. The implication is that the environmental costs of fertilizer application aren’t just going to go away. Government policies that change farmers’ production management incentives are necessary. The DIFM project is just beginning to work with trials to examine the economic effects of various kinds of eco-friendly crop production practices.
Activities:
NC1210 and DIFM have been working closely with farmers, crop advisors, extension personnel using the cyber-infrastructure to conduct on-farm research. We expect for the system to be used to run at least 150 OFPEs in the 2025 growing season. This collaboration involves daily communication among NC1210 personnel and difm.farm users.
Held weekly "trouble-shooting" sessions to help users with the system. We are continuing to develop the background computer code and user-interface that are key to the difm.farm system.
In January 2025, NC1210 and DIFM held a conference titled "Opportunities for Extension for On-farm Precision Experimentation," in which we provided training in use of the difm.farm cyber-infrastructure to over fifty extension agents, specialists, and university faculty, many of whom are beginning to work with farmers in their states to run OFPEs in 2025.
In Janary 2025, held the DIFM/NC1210 meeting, attended by approximately 70 scholars conducting OFPE research. They made dozens of presentations to report the results of OFPE research.
Milestones:
Finished the creation a fully working cyber-infrastructure, freely and publicly accessible through difm.farm. The system was used to run nearly 100 OFPEs in 2024, and we expect it to be used to run over 150 OFPEs, on fields in over twenty U.S. states, four Canadian provinces, South Africa and Brazil in 2025.
Impacts
- NC1210 Impact Statement NC1210’s work resulted in farmers and their advisors running of approximately one hundred OFPEs in 2024. Those field trials were run in approximately twenty U.S. states, four Canadian provinces, and South Africa. The data generated by the field trials were gathered, processed, organized, managed and analyzed using the difm.farm, and each grower received detailed reports on the management implications of their trials. Many farms will make management changes based on their data, and some will generate significant increase in profits as a result. NC1210’s work created the difm.farm cyber-infrastructure, and trained over fifty U.S. Extension personnel in its use. As of March 2025, this training has resulted in Extension personnel beginning to work with dozens of U.S. farmers and crop consultants to conduct on-farm research in 2025.j NC1210’s work in 2024 and earlier has resulted in a “snowballing” effect in on-farm precision experimentation. Interest is rapidly increasing all over the world. Indicators include the dozens of new farms, crop advising companies and extension personnel who have recently agreed to run OFPEs in 2025.
Publications
Manuscripst published or forthcoming:
Negrini, R., Miao, Y., Mizuta, K., Stueve, K., Kaiser, D., & Coulter, J. (2024). Spatial and temporal variability in optimal sulfur rates for corn in Minnesota: implications for Precision sulfur management.
Negrini, R., Miao, Y., and Stueve, K. (2024). Identifying key factors influencing corn responses to sulfur fertilizer application under on-farm conditions using machine learning.
dos Santos, Caio and Miguez, Fernando E., Pacu: Precision Agriculture Computational Utilities. Available at SSRN: https://ssrn.com/abstract=4946676 or http://dx.doi.org/10.2139/ssrn.4946676
Working paper on using satellite images for estimating planting and harvest date. Tentative. Authors: Caio dos Santos, Laila Puntel, David Bullock, others, Fernando Miguez
Poursina, D., and B.W. Brorsen. 2024. “Site-Specific Nitrogen Recommendation: Fast, Accurate, and Feasible Bayesian Kriging.” Computational Statistics. In Press
Poursina, D., and B.W. Brorsen. 2024. “Fully Bayesian Economically Optimal Design for Spatially Varying Coefficient Linear Stochastic Plateau Model.” Stochastic Environmental Research and Risk Assessment. 38:1089-1098.
Poursina, D., B.W. Brorsen, and D.M. Lambert. 2024. “Optimal Treatment Placement for On-Farm Experiments: Pseudo-Bayesian Optimal Designs with a Linear Response Plateau Model.” Precision Agriculture. In Press
Park, E., B.W. Brorsen, and X. Li. 2024. “Using Data from Uniform Rate Applications for Site-Specific Nitrogen Recommendations.” Journal of Agricultural and Applied Economics. 56: 138-154.
Zhang, Y., and B.W. Brorsen. 2024. “Optimizing Nitrogen Rates in Corn Production: A Multi-Degree Spline Approach.” Selected paper. Agricultural and Applied Economics Association annual meeting.
T Mieno, J Hwang, DS Bullock. Learning about Optimal Corn Seed Rate Management Via On-farm Experimentation: Are Farmers Over-planting?
M Mousavi, T Mieno, DS Bullock. A new model selection approach based on local economically optimal input rate.
Q Du, T Mieno, DS Bullock. Measuring the Estimation Bias of Yield Response to N Using Combined On-Farm Experiment Data.
Tanaka, T. S., Heuvelink, G. B., Mieno, T., & Bullock, D. S. (2024). Can machine learning models provide accurate fertilizer recommendations?. Precision Agriculture, 1-18.
Mieno, T., Li, X., & Bullock, D. S. (2024). Bias in economic evaluation of variable rate application based on geographically weighted regression models with misspecified functional form. Journal of the Agricultural and Applied Economics Association, 3(1), 135-151.
Qianqian Du, Taro Mieno, and David S. Bullock. Measuring the Estimation Bias of Yield Response to N Using Combined On-Farm Experiment Data. Under revision (JAAEA).
Farmers’ perceptions of and interest in conducting on-farm precision experimentation, in preparation, anticipated submission December 2024. Authors Tibbs, Bullock, Heller, Boerngen
Evaluating the Profitability of Corn Seeding1 Decisions: Insights from On-Farm Precision Experiments Data (Jaeseok Hwang , David S Bullock, Taro Mieno).
Giorgio Morales and John W. Sheppard, "Univariate Skeleton Prediction in Multivariate Systems Using Transformers," Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), Vilnius, Lithuania, September 2024.
Giorgio Morales and John W. Sheppard, "Counterfactual Analysis of Neural Networks Used to Create Fertilizer Management Zones," Proceedings of the International Joint Conference on Neural Networks, Yokohama, Japan, July 2024.
Giorgio Morales and John W. Sheppard, "Adaptive Sampling to Reduce Epistemic Uncertainty Using Prediction Interval-Generation Neural Networks," submitted to the 39th Annual AAAI Conference on Artificial Intelligence, Philadelpha, PA, 2025.
Edge, Brittani; Taro Mieno, and David S. Bullock. Impact of Machinery Misalignment on Economic Results through Jensen’s Inequality in On-Farm Precision Experiments. Status: Needs updating and revisions. Estimated publication: within 2025 if time permits more time to work on this after January conference.
Duff, H., D. Debinski and B.D. Maxwell. 2024. Ecological Refugia Enhance Biodiversity, Ecosystem Services, and Crop Production in Agroecosystems. Agriculture, Ecosystems and Environment. 359: 108751 https://doi.org/10.1016/j.agee.2023.108751
Duff, H., D. Debinski and B.D. Maxwell. 2024. Landscape context affects patch habitat contributions to biodiversity in agroecosystems. Ecosphere. https://doi.org/10.1002/ecs2.4879
Maxwell, B. D., & Duff, H. (2024). Increasing the scope and scale of agroecology in the Northern Great Plains [Commentary]. Journal of Agriculture, Food Systems, and Community Development. Advance online publication. https://doi.org/10.5304/jafscd.2024.133.0XX
Loewen, S. and B.D. Maxwell. 2024. Optimizing cover crop seeding rates and following cash crops to maximize net return in organic grain farming. Field Crop Research. Accepted 9/13/2024
Loewen, S. and B.D. Maxwell. 2024. Site Specific Weed Management on Organic Grain Farms using Variable Rate Seeding and Data Driven Simulation. Weed Research Accepted 10/28/2024
Flávia Luize Pereira de Souza, Maurício Acconcia Dias, Tri Deri Setiyono, Sérgio Campos, Haiying Tao, Luciano Shozo Shiratsuchi. Identification of soybean planting gaps using machine learning. Journal Smart Agricultural Technology. Submitted.
Flávia Luize Pereira de Souza, Luciano Shozo Shiratsuchi, Haiying Tao, Maurício Acconcia Dias, Marcelo Rodrigues Barbosa Júnior, Tri Deri Setiyono, Sérgio Campos. Counting soybean plants by UAV RGB Imagery: an effective approach during phenological changes. Agrosystems, Geosciences & Environment. Submitted.
Flávia Luize Pereira de Souza, Luciano Shozo Shiratsuchi, Haiying Tao, Maurício Acconcia Dias, Marcelo Rodrigues Barbosa Júnior, Tri Deri Setiyono, Sérgio Campos. Soybean plant count based on multisensor images. Precision Agriculture. Under Review.
Flávia Luize Pereira de Souza, Haiying Tao, David Bullock, Brittani Edge. Spatial variability of optimum chloride application rate in a soft white winter wheat field. Agronomy Journal. Under Prep.
Presentations & Interviews:
Bullock, D.S. "Why Agricultural Big Data Needs On-farm Precision Experimentation (and Vice-versa).”
International Conference for On-farm Precision Experimentation. South Padre Island, TX. 1/8/24.
Bullock, D.S. "Using the (free!) Data-Intensive Farm Management Project’s Tools to Design and Analyze Your On-farm Trials". Kansas Agricultural Technologies Conference. Manhattan, KS. 1/26/24.
Bullock, D.S. "Working with the Data-Intensive Farm Management Project to Conduct On-Farm Precision Experiments". Virtual Symposium: Harvesting Insights with Data-Driven On-Farm Precision Experimentation. 2/13/24.
Bullock, D.S. “Working with DIFM and Trilogy on On-farm Precision Experimentation.” Trilogy Corporation. Fargo, North Dakota. 3/19/2024.
Bullock, D.S., R.E. Dunker, and S. Wahl. "Improving the Economic and Ecological Sustainability of US Crop Production through On-farm Precision Experimentation." NRCS SNTSC Technology Advisory Board Meeting. Virtual. 3/26/24.
Bullock, D.S. "On-Farm Precision Experimentation: Methods and Results. Univesity of Illinois Dept of Agricultural and Consumer Economics FACS Workshop. Urbana, Illinois. 4/3/24.
Bullock, D.S. “What DIFM Can Offer Microsoft and Project FarmVibes.” Virtual. Meeting with Ranveeer Chandra, Managing Director and Chief Technology Officer of Agri-Food at Microsoft. 4/13/24.
Bulllock, D.S. "On-Farm Precision Experimentationand the Data-Intensive Farm Management Program: Methods and Results" (*Invited speaker). IoT4Ag Group. Purdue University, W. Lafayette, IN. 4/5/24.
‘
Bullock, D.S. "New Opportunities for U of I Extension: On-Farm Precision Experimentation with DIFM, Farmers and CCA.” Meeting of the Illinois Extension Commercial Agriculture Team. Virtual. 4/12/24.
Bullock, D.S, "An Opportunity for Illinois Farmers: On-farm Research with the Data-Intensive Farm Management Project." Interview for WILL radio with Todd Gleason. University of Illinois Extension. 4/26/24.
Bullock, D.S., and J. Jung. "Using On-farm Precision Experimentation to Incentivize Cost-effective Climate-friendly Crop Research, Policy, and Production." Presentation to Tim Pilwkowski, NRCS National Nutrient Management Discipline Lead. Virtual. 5/23/24.
Bullock, D.S. "Conducting On-farm Precision Experimentation with U of I Extension and the Data-Intensive Farm Management Project." University of Illinois Extension Ewing Field Day. Illinois Extension Ewing Demonstration Center. 7/25/24.
Bullock, D.S. "The Data-Intensive Farm Management Project: On-Farm Nitrogen Rate Experiments." The Nitrogen Use Efficiency Workshop. Urbana, Illinois. 8/5/24.
Bullock, D.S. "Vayda-DIFM Discussion: On-farm Precision Experimentation and Regenerative Agriculture." Virtual. 8/27/24.
Bullock, D.S. "Opportunities for Data-intensive Farm Management in Africa"
United Nations Science Summit: "4IR Opportunities for Agriculture in Africa." Virtual (*invited speaker*). 9/25/24.
Bullock, D.S. "The Data-Intensive Farm Management Project and Opportunities for On-farm Precision Experimentation." Interview with Matthew Grassi, Technology & Machinery Editor of Farm Journal. Telephone. 9/26/24.
Bullock, D.S. "The Data-Intensive Farm Management Project and Opportunities for On-farm Precision Experimentation." Auburn University Dept of Crop, Soil and Environmental Sciences. Auburn, Alabama. 10/18/24.
Bullock, D.S. "YARA-DIFM Discussion: Opportunities for On-farm Precision Experimentation."
Representatives for YARA North America. Virtual. 10/28/24.
Negrini, R., Miao, Y. (Corresponding Author), Mizuta, K., Stueve, K., Kaiser, D., & Coulter, J. (2024). Within-field Spatial Variability in Optimal Sulfur Rates for Corn in Minnesota: Implications for Precision Sulfur Management. ISPA;
Kechchour, A., Miao, Y. (Corresponding Author), Folle, S., & Mizuta, K. (2024). On-farm Evaluation of the Potential Benefits of Variable Rate Seeding for Corn in Minnesota. 16th International Conference on Precision Agriculture, Manhattan, KS. (July 21-24, 2024);
Negrini, R., Miao, Y., (Advisor) "Optimizing Sulfur Management in Corn through On-Farm Experimentation and Machine Learning in Minnesota: A Study on Within-Field Variability and Limiting Factors," 2024 ASABE North Central Regional Section Meeting, Brookings, South Dakota. (April 12, 2024).
Miguez, Fernando E. Integrating Nonlinear Models and Remotely Sensed Data to Estimate Crop Cardinal Dates. https://www.ispag.org/proceedings/?action=abstract&id=10092
Patterson, C., B.W. Brorsen, D. Poursina, T. Mieno, B.K. Edge, and E.D. Nafziger. 2024. “Using Informative Bayesian Priors and On-Farm Experimentation to Predict Optimal Site-Specific Nitrogen Rates.” Presentation. International Society of Precision Agriculture, Manhattan, KS.
"A new model selection approach based on local economically optimal input rate" by Mona Mousavi at the annual AAEA conference. https://www.aaea.org/UserFiles/file/aaea_202407_agenda_pdf_daily.pdf
John Sheppard, Counterfactual Analysis of Neural Networks Used to Create Fertilizer Management Zones, International Joint Conference on Neural Networks, Yokohama, Japan, 9/9/24.
Giorgio Morales, "Decomposable Symbolic Regression Using Transformers and Neural Network-Assisted Genetic Algorithms," PhD Forum, European Conference on Machine Learning, Vilnius, Lithuania
Giorgio Morales, "Discovery Challenge: Seismic Monitoring and Analysis Challenge," First-Place Award, European Conference on Machine Learning, Vilnius, Lithuania.
Giorgio Morales, "Univariate Skeleton Prediction in Multivariate Systems Using Transformers," Paper Presentation, European Conference on Machine Learning, Vilnius, Lithuania
Giorgio Morales, AI and Agriculture, INBRE Workshop on Artificial Intelligence, Butte, MT, 10/21/24
John Sheppard, "AI and Society: Why It Matters," Gallatin Valley Friends of the Sciences, Bozeman, MT, 10/16/24
Edge, Brittani. Presentation at AgSmart 2024 at Old's College to present the DIFM tools and discuss what we have learned implementing OFPE's for seven years.
SOUZA, F. L. P.; SHIRATSUCHI, L. S; TAO, H.; DIAS, M. A.; JÚNIOR, M. R. B.; SETIYONO, T.; CAMPOS, S. Computer vision by UAVs for estimate soybean population across different physiological growth stages and sowing speeds. 16th International Conference on Precision Agriculture. Manhattan, Kansas, United States, 2024.
SOUZA, F. L. P.; SHIRATSUCHI, L. S; TAO, H.; DIAS, M. A.; JÚNIOR, M. R. B.; SETIYONO, T.; CAMPOS, S. Optimizing soybean management with UAV RGB and multispectral imagery: A Neural Network method and image processing. 16th International Conference on Precision Agriculture. Manhattan, Kansas, United States, 2024.
SOUZA, F. L. P.; NEGRINI, R.; TAO, H. Optimizing Chloride (Cl) Application for Enhanced Agricultural Yield. 16th International Conference on Precision Agriculture. Manhattan, Kansas, United States, 2024.
SOUZA, F. L. P.; DIAS, M. A.; SETIYONO, T.; CAMPOS, S.; TAO, H.; SHIRATSUCHI, L. S. How can machine learning assist in identifying issues in soybean planting? Conference for On-farm Precision Experimentation 2024. Hilton Garden Inn South Padre Island Beachfront; City: South Padre Island, Texas; Sponsor: Data-Intensive Farm Management Project (DIFM).
SOUZA, F.L.P. Automatic counting of soybean plants with computer vision and Artificial Intelligence and data from Remotely Piloted Aircraft – RPA. Brazil. UNESP. PhD thesis. 2024. https://hdl.handle.net/11449/255297