Machine learning deciphers CO<sub>2</sub> sequestration and subsurface flowpaths from stream chemistry
<p>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 r...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2021-06-01
|
| Series: | Hydrology and Earth System Sciences |
| Online Access: | https://hess.copernicus.org/articles/25/3397/2021/hess-25-3397-2021.pdf |
| Summary: | <p>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
CO<span class="inline-formula"><sub>2</sub></span> in the atmosphere. For example, CO<span class="inline-formula"><sub>2</sub></span>-driven weathering of
silicate minerals removes carbon from the atmosphere over <span class="inline-formula">∼</span>10<span class="inline-formula"><sup>6</sup></span>-year timescales. Weathering of another common mineral, pyrite, releases sulfuric
acid that in turn causes dissolution of carbonates. In that process,
however, CO<span class="inline-formula"><sub>2</sub></span> is released instead of sequestered from the atmosphere. Thus, understanding long-term global CO<span class="inline-formula"><sub>2</sub></span> sequestration by weathering
requires quantification of CO<span class="inline-formula"><sub>2</sub></span>- versus H<span class="inline-formula"><sub>2</sub></span>SO<span class="inline-formula"><sub>4</sub></span>-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 CO<span class="inline-formula"><sub>2</sub></span>, but the extent of CO<span class="inline-formula"><sub>2</sub></span> drawdown is diminished in areas heavily affected
by acid rain. Prior to applying the new algorithm, CO<span class="inline-formula"><sub>2</sub></span> 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.</p> |
|---|---|
| ISSN: | 1027-5606 1607-7938 |