Machine learning deciphers CO 2 sequestration and subsurface flowpaths from stream chemistry

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

Endmember mixing analysis (EMMA) is often used by hydrogeochemists to interpret the sources of stream solutes, but variations in stream concentrations and discharges remain difficult to explain. We discovered that machine learning can be used to highlight patterns in stream chemistry that reveal information about sources of solutes and subsurface groundwater flowpaths. The investigation has implications, in turn, for the balance of COinline-formula2 in the atmosphere. For example, COinline-formula2-driven weathering of silicate minerals removes carbon from the atmosphere over inline-formula∼10inline-formula6-year timescales. Weathering of another common mineral, pyrite, releases sulfuric acid that in turn causes dissolution of carbonates. In that process, however, COinline-formula2 is released instead of sequestered from the atmosphere. Thus, understanding long-term global COinline-formula2 sequestration by weathering requires quantification of COinline-formula2- versus Hinline-formula2SOinline-formula4-driven reactions. Most researchers estimate such weathering fluxes from stream chemistry, but interpreting the reactant minerals and acids dissolved in streams has been fraught with difficulty. We apply a machine-learning technique to EMMA in three watersheds to determine the extent of mineral dissolution by each acid, without pre-defining the endmembers. The results show that the watersheds continuously or intermittently sequester COinline-formula2, but the extent of COinline-formula2 drawdown is diminished in areas heavily affected by acid rain. Prior to applying the new algorithm, COinline-formula2 drawdown was overestimated. The new technique, which elucidates the importance of different subsurface flowpaths and long-timescale changes in the watersheds, should have utility as a new EMMA for investigating water resources worldwide.

Zitieren

Zitierform:

Shaughnessy, Andrew R. / Gu, Xin / Wen, Tao / et al: Machine learning deciphers CO2 sequestration and subsurface flowpaths from stream chemistry. 2021. Copernicus Publications.

Zugriffsstatistik

Gesamt:
Volltextzugriffe:
Metadatenansicht:
12 Monate:
Volltextzugriffe:
Metadatenansicht:

Grafik öffnen

Rechte

Rechteinhaber: Andrew R. Shaughnessy et al.

Nutzung und Vervielfältigung:

Export