Improving Nitrogen Efficiency in Corn Production Systems with Data and Modeling

Design workshop: Based on the design workshop, latitude and longitude, previous cash crops, previous season N management history received the higher number of votes as input factors and yield, crop N uptake, nitrate leaching, and weather and growing degree days received the higher number of votes. While in factor mapping, soil properties, weather information, economics (cost of labor, equipment, N fertilizer), management practices (date of planting, tillage), and genetics were the broad spectrum were of features which influence their management decisions.

Frontend and Backend integration: Figure 3 to 5, showcases the OPTICORN user-interface, highlighting the information required for running the tool and understanding the interpretation of the tool responses. The tool provides user the flexibility to select their cultivar type and previous cash crops through radio buttons, latitude and longitude either by entering it manually or selecting from the map by zoom in/out features, previous N management, current N management, and seed rate through text boxes; date inputs for entering application dates, and checkboxes for selecting outputs. To ease the usability and interpretability of the outputs, separate panes are provided for mapping/plotting different types of output graphs. Text boxes and text areas are used for providing contact information and suggestions, respectively.

Walkthrough for tool: Given the set of inputs which the user provided in the Figure 6, the tool ran and provided the detailed outputs presented in Figure 7 and 8. It is to be noted that the tool was ran on date July 30, 2025, so as to decide how much N fertilizer would be worth to apply.

Figure 7 illustrates the temporal dynamics of key agronomic and environmental indicators throughout the growing season, enabling users to visualize the consequences of their N management decisions for the current year based on the best, worst, and average weather conditions for that location over the past 20 years. The seasonal progression reveals distinct patterns for corn yield (Figure 7a), where initially the curve shows minimal differences, but as the growth stages progress, differences between yield scenarios become apparent. It should be noted that differences between projection values decrease as the tool progresses within the season, while early in the season the differences are greater because the corn has not yet experienced future conditions and therefore has greater uncertainty. Nitrous oxide emissions and nitrate leaching (Figures 7b and 7d) demonstrate a gradual increase throughout the season, with emissions and leaching accelerating during periods of high soil moisture and temperature. Crop Nuptake (Figure 7c) exhibits sharp peaks during vegetative growth stages, showcasing when plant nitrogen demand is highest, followed by declining uptake as the crop approaches physiological maturity. This comprehensive visualization allows users to conduct what-if scenarios and understand the temporal trade-offs between productivity and environmental stewardship under location-specific weather conditions.

Figures 8a-8c demonstrate that increasing nitrogen application rates progressively increases corn yield, nitrate leaching, and nitrous oxide emissions across all weather scenarios. However, the yield response curve (Figure 8a) exhibits classic diminishing returns, with nitrogen applications beyond 125 lbs/ac (for best condition) providing minimal yield improvements while continuing to increase environmental costs. This response pattern highlights the critical importance of identifying the economic optimum nitrogen rate rather than simply maximizing yield. The three-dimensional analysis (Figure 8d) reveals the complex trade-offs between competing management objectives under varying weather conditions. When users prioritize maximum yield optimization, the results inevitably involve higher nitrate leaching and nitrous oxide gas emissions, a pattern that reflects conventional production-focused agricultural approaches. The balanced optimization approach consistently occupies the intermediate position across all three weather scenarios, achieving near-maximum yields while maintaining moderate environmental impacts. This strategy represents the most practical solution for most farming operations, as it balances economic viability with environmental stewardship, which is an essential component of long-term agricultural sustainability. Conversely, environmentally sound optimization minimizes both nitrate leaching and nitrous oxide emissions but have lower yield potential. The optimization framework enables farmers to make informed nitrogen management decisions based on their specific objectives, market conditions, and environmental priorities. By quantifying these trade-offs, the system provides science-based recommendations that align N applications with user-defined goals while highlighting the environmental and economic implications of each management strategy.

Validation

User validation: Based on figure 9, it could be seen that the average rating of the tool was 4.17, when a set of 5 users tested the tool, showcasing the easiness in using the tool. The distribution of responses shows that 74% of ratings were 4 or 5, demonstrating consistent positive user experience across different evaluation criteria. The list of the questions would be available upon request as this work is still in the progress of publication.

While in the case of field testing, we are still in the process of testing the tool performance from Dr. Quinn’s experimental plots.

References:

• Thorburn, P. J., Biggs, J. S., Puntel, L. A., Sawyer, J. E., Everingham, Y. L., & Archontoulis, S. V. (2024). The nitrogen fertilizer conundrum: why is yield a poor determinant of crops’ nitrogen fertilizer requirements?. Agronomy for Sustainable Development, 44(2), 18.
• Baum, M. E., Sawyer, J. E., Nafziger, E. D., Huber, I., Thorburn, P. J., Castellano, M. J., & Archontoulis, S. V. (2023). Evaluating and improving APSIM's capacity in simulating long-term corn yield response to nitrogen in continuous-and rotated-corn systems. Agricultural Systems, 207, 103629.
• Gibbons, S. (2019), Dot Voting: A simple decision-making and prioritizing technique in UX, url: https://www.nngroup.com/articles/dot-voting/. Date accessed July 30, 2025
• Winn, C. A., Archontoulis, S., & Edwards, J. (2023). Calibration of a crop growth model in APSIM for 15 publicly available corn hybrids in North America. Crop Science, 63(2), 511-534.
• Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. A. M. T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation, 6(2), 182-197.
• Frank, R., & Krueger, S. (2025). Gallery walk as research method in information science. Information Research an international electronic journal, 30(iConf), 171-179.