Black carbon, an aerosol that is emitted into the atmosphere from combustion sources, impacts human health and plays an important role in the climate system. Existing physics-based modeling methods to represent black carbon phenomena have inherent uncertainties associated with the assumptions that must be made about aerosol properties. Machine learning techniques have recently been employed to improve black carbon prediction and ultimately replace traditional models. Andrew May of The Ohio State University and Hanyang Li of San Diego State University were funded by The Climate Program Office’s Atmospheric Chemistry, Carbon Cycle and Climate (AC4) Program to expand the application of machine learning to the prediction of black carbon in a variety of atmospheric environments. The results of their machine learning models, published in Aerosol Science and Technology, do not require assumptions on aerosol composition and capture temporal variations very well. More work is needed to improve machine learning models in certain scenarios involving airborne dust. The incorporation of machine learning in research and modeling to advance mitigation strategies for anthropogenic change is a main goal in the NOAA Artificial Intelligence Strategy. This research is part of an AC4 initiative to understand the changing atmospheric composition, emissions and state conditions, in order to properly characterize and project changes in air quality.