Nitrogen (N) fertilizer recommendations for corn (Zea mays L.) in the US Midwest have been a puzzle for several decades, without agreement among stakeholders for which methodology is the best to balance environmental and economic outcomes. Part of the reason is the lack of long-term data of crop responses to N over multiple fields since trial data is often limited in the number of soils and years it can explore. To overcome this limitation, we designed an analytical platform based on crop simulations run over millions of farming scenarios over extensive geographies. The database was calibrated and validated using data from more than four hundred trials in the region. This dataset can have an important role for research and education in N management, machine leaching, and environmental policy analysis. The calibration and validation procedure provides a framework for future gridded crop model studies. We describe dataset characteristics and provide thorough descriptions of the model setup.

Digital agriculture is emerging as the next green revolution, helping farmers to make data‐informed decisions that increase productivity and optimize resource use. Understanding farmers' perceptions of current barriers and future opportunities for technology adoption is necessary for sustainable agriculture. This study aimed to identify trends and patterns in farmers' perceptions of digital agriculture technology adoption. A survey was distributed across most of the Midwest and adjacent region of the United States, collecting 247 responses. Results showed 93% used digital agricultural technology, with long‐term (>10 years) adoption of auto‐guidance (59%), yield mapping (56%), and variable rate technologies (36%). Perceived financial profitability was a key driver of technology adoption (36%), followed by input optimization (18%) and productivity (16%). The main barrier was high cost relative to perceived benefit (31%), followed by small farm size (16%) and equipment incompatibility (14%). Environmental benefits emerged as a tertiary motivator, and their lower prioritization suggests that farmers focus more on the economic dimension of sustainability when adopting new technologies. Fertilizer efficiency (27%), pest management (18%), and water management (13%) were top challenges to address. Findings suggest that digital agriculture adoption is primarily driven by economic considerations, with cost‐benefit analysis and entry costs as key determinants in US Midwest and adjacent region farming systems.

Meeting the growing demand for maize while reducing nitrogen losses remains a key challenge for sustainable agriculture. Here, we present a market-based nitrogen insurance concept that allows farmers who apply excess fertilizer to reduce nitrogen use without financial risk. Using a large-scale process-based crop model dataset covering 4270 maize fields in Illinois, over 30 years of weather data, and 33 fertilizer rates, we found that the insurance is profitable for farmers applying at least 40 kilograms of nitrogen per hectare above recommended rates, yielding average annual gains of 14 dollars per hectare for farmers and 10 dollars per hectare for insurers. Applied across the eligible Illinois maize area, the insurance annually reduces nitrate leaching by 31% and lowers greenhouse gas emissions by 682,000 metric tonnes of carbon dioxide equivalent. This self-sustaining approach could be extended to other nitrogen-intensive crops and regions, providing a globally relevant pathway to reconcile farm profitability with environmental stewardship.

Corn (Zea mays L.) yield productivity is driven by a multitude of factors, specifically genetics, environment, and management practices, along with their corresponding interactions. Despite continuous monitoring through proximal or remote sensors and advanced predictive models, understanding these complex interactions remains challenging. While predictive models are improving with regard to accurate predictions, they often fail to explain causal relationships, rendering them less interpretable than desired. Process-based or biophysical models such as the Agricultural Production Systems sIMulator (APSIM) incorporate these causalities, but the multitude of interactions are difficult to tease apart and are largely sensitive to external drivers, which often include stochastic variations. To address this limitation, we developed a novel methodology that reveals these hidden causal structures. We simulated corn production under varied conditions, including different planting dates, nitrogen fertilizer amounts, irrigation rules, soil and environmental conditions, and climate change scenarios. We then used the simulation results to rank features having the largest impact on corn yield through Random Forest modeling. The Random Forest model identified nitrogen uptake and annual transpiration as the most influential variables on corn yield, similar to the existing research. However, this analysis alone provided limited insight into how or why these features ranked highest and how the features interact with each other. Building on these results, we deployed a Causal Bayesian model, using a hybrid approach of score-based (hill climb) and constraint-based (injecting domain knowledge) models. The causal analysis provides a deeper understanding by revealing that genetics, environment, and management factors had causal impacts on nitrogen uptake and annual transpiration, which ultimately affected yield. Our methodology allows researchers and practitioners to unpack the “black box” of crop production systems, enabling more targeted and effective model development and management recommendations for optimizing corn production.

Improving nitrogen (N) management for corn (Zea mays L.) remains challenging because field trials rarely cover the full range of soils, climates, and management conditions present across a state. To address this gap for the state of Indiana (US), we generated a large APSIM Next Generation simulation dataset of corn response to N fertilizer. More than two million simulations were run on a 10 km grid for 4,010 fields and 44 years, spanning multiple N rates under corn–soybean rotation. Model inputs combine USDA field boundaries, SSURGO soils, and Daymet weather, and outputs are stored in a SQLite database with spatial, soil, weather, and simulation tables. Genetic and soil parameters were calibrated using 339 Indiana N-rate trials. Validation showed that the model captured regional yield response patterns and economically optimum N rates, and monthly N-leaching totals were consistent with long-term subsurface drainage measurements at the Southeast Purdue Agricultural Center (SEPAC), an experimental station located in the study region. This dataset supports research and teaching on N recommendations, machine learning applications, and environmental assessments of corn systems in the U.S. Corn Belt.