Using machine learning to improve black-carbon predictions

Soot from Arizona’s Willow Fire mingles with clouds. Credit: NOAA

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.

Read more at the link below.