Articles | Volume 25, issue 6
https://doi.org/10.5194/hess-25-3397-2021
https://doi.org/10.5194/hess-25-3397-2021
Research article
 | 
17 Jun 2021
Research article |  | 17 Jun 2021

Machine learning deciphers CO2 sequestration and subsurface flowpaths from stream chemistry

Andrew R. Shaughnessy, Xin Gu, Tao Wen, and Susan L. Brantley

Cited articles

Alexandrov, B. S. and Vesselinov, V. V.: Blind source separation for groundwater pressure analysis based on nonnegative matrix factorization, Water Resour. Res., 50, 7332–7347, 2014. 
Bailey, S. W., Mayer, B., and Mitchell, M. J.: Evidence for influence of mineral weathering on stream water sulphate in Vermont and New Hampshire (USA), Hydrol. Process., 18, 1639–1653, 2004. 
Bernhardt, E., Likens, G. E., and Rosi, E.: Continuous precipitation and stream chemistry data, Hubbard Brook Ecosystem Study, 1963–present, Environmental Data Initiative, Hubbard Brook Data Catalog, https://doi.org/10.6073/pasta/4022d829f3a1fa4057b63b5db8b1a172, 2019. 
Berry, M. W., Browne, M., Langville, A. N., Pauca, V. P., and Plemmons, R. J.: Algorithms and applications for approximate nonnegative matrix factorization, Comput. Stat. Data An., 52, 155–173, 2007. 
Brantley, S. L., Holleran, M. E., Jin, L., and Bazilevskaya, E.: Probing deep weathering in the Shale Hills Critical Zone Observatory, Pennsylvania (USA): the hypothesis of nested chemical reaction fronts in the subsurface, Earth Surf. Proc. Land., 38, 1280–1298, 2013a. 
Download
Short summary
It is often difficult to determine the sources of solutes in streams and how much each source contributes. We developed a new method of unmixing stream chemistry via machine learning. We found that sulfate in three watersheds is related to groundwater flowpaths. Our results emphasize that acid rain reduces a watershed's capacity to remove CO2 from the atmosphere, a key geological control on climate. Our method will help scientists unmix stream chemistry in watersheds where sources are unknown.
Share