Integration of proximal soil sensors into commercial row-crop planter components have allowed for a dense quantification of within-field soil spatial variability. These technologies have potential to guide real-time management decisions, such as on-the-go variable seeding rate or depth. However, little is known about the performance of these systems. Therefore, research was conducted in central Missouri, USA to determine the relationship between planter sensor metrics, and corn (Zea mays L.)  early stand density (population) and emergence uniformity. The study was conducted in 2020 and 2021 at two separate production agricultural fields, each around 4 ha. Planter sensor data were collected during the seeding operation, followed by unmanned aerial vehicle (UAV) imagery taken 21 days after planting. Planter sensor data consisted of several metrics, including furrow moisture, organic matter, and row-unit downforce. Imagery from the UAV was used to estimate population and the average day of emergence for each 1 m of row at both sites. Several machine learning techniques were implemented to evaluate the spatial relationships between planter-sensor data and early stand density and emergence uniformity. Results from the study did not show strong correlations between planter-sensor data and population. However, when utilizing the random forest algorithm, planter metrics were able to explain around 60% of the variation in corn emergence uniformity at the 2020 site. Further, the model showed that sensor-based organic matter and soil cation exchange capacity were the most important factors relating to early corn emergence uniformity. These preliminary results suggest that planter sensor technology has the potential to guide corn planting depth decisions.