As more planters are equipped with the technology to vary seeding rate, evaluation of the within-field relationships between plant stand density (or population) and yield is needed. One aspect of this evaluation is determining how stand loss and yield are related to soil and landscape factors, and how these relationships vary with different weather conditions. Therefore, this research examined nine site-years of mapped corn yield, harvest population, and soil and landscape data obtained for a central Missouri, USA field. Mechanical population sensors developed to collect data during combine harvesting provided data at the same scale as yield monitor measurements.  Spatial population variability was large in all site-years, and harvest populations were as much as 40% lower than seeding rate. In a preliminary analysis, population and stand loss (i.e., the difference between planting rate and harvest population) were not strongly related to soil (i.e., fertility, organic matter, and apparent soil electrical conductivity, EC_a) or landscape (i.e., slope, elevation) properties. Relationships between corn yield and population were complex and highly variable, and only in some site-years was there a significant and positive relationship between maximum yield and population. In this paper, we investigate the use of several machine learning techniques, including the random forest and artificial neural network algorithms, to better define nonlinear relationships between crop yield and stand loss as a function of soil, weather, and landscape factors. Our overall goal is to use this information as part of the decision process for variable-rate seeding strategies.