Skip to main content
ARS Home » Midwest Area » Columbia, Missouri » Cropping Systems and Water Quality Research » Research » Publications at this Location » Publication #394451

Research Project: Sustainable Intensification of Cropping Systems on Spatially Variable Landscapes and Soils

Location: Cropping Systems and Water Quality Research

Title: Predicting corn emergence uniformity with on-the-go furrow sensing technology

item CONWAY, LANCE - University Of Missouri
item VONG, CHIN NEE - University Of Missouri
item Kitchen, Newell
item Sudduth, Kenneth - Ken
item ANDERSON, STEPHEN - University Of Missouri

Submitted to: International Conference on Precision Agriculture Abstracts & Proceedings
Publication Type: Proceedings
Publication Acceptance Date: 6/1/2022
Publication Date: 6/26/2022
Citation: Conway, L.S., Vong, C., Kitchen, N.R., Sudduth, K.A., Anderson, S.H. 2022. Predicting corn emergence uniformity with on-the-go furrow sensing technology. Proceedings of the 15th International Conference on Precision Agriculture, June 26-29, 2022, Minneapolis, Minnesota. Available:

Interpretive Summary: Automatic control of critical functions on agricultural planting equipment is now possible through output from soil-engaging sensors. However, evaluation is needed to determine how output from these sensors can be used to maximum advantage. Therefore, research was performed to determine if for corn planted at various planting depths, soil sensor data, and terrain features could be used to estimate within-field variations of plant density and emergence rate. The study was conducted in 2020 on a highly variable soil field in Missouri, USA. A planter equipped with recent monitoring and control technology was used to plant at four different depths and provide a suite of soil sensor measurements obtained from the planting operation. The results found corn stand densities were not greatly impacted by planting depths or by the variable soil landscape. However, advanced modeling procedure was able to detect differences in emergence rate at all planting depths from the array of variables used in prediction. Soil sensor metrics representing inherent soil variability, such as organic matter and texture, were most useful in the emergence rate prediction models, and were superior to others known to impact corn emergence (e.g., soil moisture). This information will help producers make more informed decisions when managing emerging equipment technologies to manage spatial soil variability.

Technical Abstract: Real-time sensor output during row-crop planting operations has the potential to improve control of multiple row-unit functions on-the-go. However, research is lacking on how best to maximize the utility of these new sensor systems across varying landscapes. Therefore, an investigation was conducted to determine if planter and other proximal soil sensor data, in combination with topographic features, could predict within-field variation in corn (Zea mays L.) emergence rate (ER) across multiple planting depth treatments. Research was conducted in Missouri, USA on a highly variable claypan soil field in 2020. Corn was planted with a four-row planter equipped with hydraulic downforce and planter-mounted soil sensors on each row unit. Four field-length strips of seed planting depth (3.8, 5.1, 6.4, and 7.6 cm) replicated three times were treatments to induce emergence variation. Machine learning approaches were applied to determine the predictive capability of planter sensors, soil apparent electrical conductivity (ECa), and topographic features (slope, flow direction, and topographic wetness index) in estimating corn ER. Field-scale results from the planting depth treatments showed that planting depth had a marginal influence on corn stands, with stand densities decreasing slightly at 6.4 and 7.6 cm. Additionally, a suite of predictors could effectively estimate ER across the study site, with similar accuracies observed across planting depths. Planter sensor variables representing estimates of inherent soil variability (i.e., OM and texture) were most useful in the ER prediction model, and were superior to estimates of furrow moisture and seed-to-soil contact. These results illustrate the ability to predict ER at a field scale, and can be used as a framework for further research and development of planter sensor systems targeting uniform corn emergence.