Quantifying methane emissions from Laurentian Great Lakes estuaries using in situ measurements, remote sensing, and machine learning

Abstract Freshwater estuaries are natural contributors to the carbon cycle, including production and emission of methane (CH 4 ), a potent greenhouse gas (GHG); however, estimates of their contribution to global GHG emissions is uncertain. Recent research has identified the potential for quantifying limnetic methane using optical remote sensing coupled with machine learning. In this study, CH 4 fluxes were measured from three drowned river mouth (DRM) estuaries along the eastern shore of Lake Michigan using low‐cost, autonomous floating samplers in the littoral zone and discrete samples in the pelagic zone from May to October 2024. Sentinel‐3 Ocean and Land Color Instrument, Gridded Meteorological Data, and Moderate Resolution Imaging Spectrometer were used to calculate environmental variable proxies, which were used to estimate CH 4 fluxes with machine learning. Model performance ( R 2 = 0.50) indicated ability to capture trends in CH 4 flux and extend predictions to other DRM estuaries. These results provide an accessible framework for reducing the current uncertainty in lakes' CH 4 emissions estimates.