Agricultural lands can be a sink for carbon and play an important role in offsetting carbon emissions. Current methods of measuring carbon sequestration—through repeated temporal soil samples—are costly and laborious. A promising alternative is using visible, near-infrared (VNIR) diffuse reflectance spectroscopy. However, VNIR data are complex, which requires several data processing steps and often yields inconsistent results, especially when using in situ VNIR measurements. Using a convolutional neural network (CNN) could bypass these steps and incorporate measurements from multiple sensors to predict three-dimensional carbon stocks. Using data previously collected (n = 1,500; from 2016 to 2020), a CNN modeling framework will be developed to predict soil carbon by incorporating information from profile VNIR, apparent electrical conductivity (ECa), penetration resistance measurements, and spatial covariates (e.g., mobile-sensor ECa and topography). Improvements over traditional modeling methods will be reported. This presentation will include an evaluation of the optimal spatial density of sensor measurements needed to use the CNN model to estimate soil carbon across contrasting field management conditions (e.g., hay crop vs. historically tilled corn-soybean vs. no-till corn-soybean fields) using data collected in 2021). Ultimately, 3D maps of soil carbon will be developed using the multiyear dataset and the selected CNN modeling approach.