Applying Machine Learning to investigate metal isotope variations at the watershed scale: A case study with lithium isotopes across the Yukon River Basin.

Constraining the multiple climatic, lithological, topographic, and geochemical variables controlling isotope variations in large rivers is often challenging with standard statistical methods. Machine learning (ML) is an efficient method for analyzing multidimensional datasets, resolving correlated processes, and exploring relationships between variables simultaneously. We tested four ML algorithms to elucidate the controls of riverine δ7Li variations across the Yukon River Basin (YRB). We compiled (n = 102) and analyzed new samples (n = 21), producing a dataset of 123 river water samples collected across the basin during the summer including δ7Li and extracted environmental, climatological, and geological characteristics of the drainage area for each sample from open-access geospatial databases. The ML models were trained, tuned, and tested under multiple scenarios to avoid issues such as overfitting. Random Forests (RF) performed best at predicting δ7Li across the basin, with the median model explaining 62 % of the variance. The most important variables controlling δ7Li across the basin are elevation, lithology, and past glacial coverage, which ultimately influence weathering congruence. Riverine δ7Li has a negative dependence on elevation. This reflects congruent weathering in kinetically-limited mountain zones with short residence times. The consistent ranking of lithology, specifically igneous and metamorphic rock cover, as a top feature controlling riverine δ7Li modeled by the RFs is unexpected. Further study is required to validate this finding. Rivers draining areas that were extensively covered during the last glacial maximum tend to have lower δ7Li due to immature weathering profiles resulting in short residence times, less secondary mineral formation and therefore more congruent weathering. We demonstrate that ML provides a fast, simple, visualizable, and interpretable approach for disentangling key controls of isotope variations in river water. We assert that ML should become a routine tool, and present a framework for applying ML to analyze spatial metal isotope data at the catchment scale.

Sources of solutes and carbon cycling in perennially ice-covered Lake Untersee, Antarctica.

Perennially ice-covered lakes that host benthic microbial ecosystems are present in many regions of Antarctica. Lake Untersee is an ultra-oligotrophic lake that is substantially different from any other lakes on the continent as it does not develop a seasonal moat and therefore shares similarities to sub-glacial lakes where they are sealed to the atmosphere. Here, we determine the source of major solutes and carbon to Lake Untersee, evaluate the carbon cycling and assess the metabolic functioning of microbial mats using an isotope geochemistry approach. The findings suggest that the glacial meltwater recharging the closed-basin and well-sealed Lake Untersee largely determines the major solute chemistry of the oxic water column with plagioclase and alumino-silicate weathering contributing < 5% of the Ca2+-Na+ solutes to the lake. The TIC concentration in the lake is very low and is sourced from melting of glacial ice and direct release of occluded CO2 gases into the water column. The comparison of δ13CTIC of the oxic lake waters with the δ13C in the top microbial mat layer show no fractionation due to non-discriminating photosynthetic fixation of HCO3- in the high pH and carbon-starved water. The 14C results indicate that phototrophs are also fixing respired CO2 from heterotrophic metabolism of the underlying microbial mats layers. The findings provide insights into the development of collaboration in carbon partitioning within the microbial mats to support their growth in a carbon-starved ecosystem.