Date of Award
8-4-2023
Degree Type
Thesis
Degree Name
Master of Science (MS)
Department
Earth Sciences
Advisor(s)
Tao Wen
Second Advisor
Zunli Lu
Keywords
Alkalinization;Climate Change;Freshwater;Human;Machine Learning;Salinization
Abstract
In previous studies, ongoing salinization and alkalinization in U.S. rivers have been attributed to inputs of road salt and effects of human accelerated weathering. Salinization poses a severe threat to human and ecosystem health, while human-derived alkalinization implies increasing uncertainty in the dynamics of terrestrial sequestration of atmospheric carbon dioxide. A mechanistic understanding of whether and how human activities accelerate weathering and contribute to the geochemical changes in U.S. rivers is lacking. To address this uncertainty, we compiled dissolved sodium (salinity proxy) and alkalinity concentrations along with 32 watershed properties ranging from hydrology, climate, geomorphology, geology, soil chemistry, land use, and land cover for 226 river monitoring sites across the coterminous U.S. Using these data, we built two machine learning models to predict monthly-aggregated sodium and alkalinity fluxes at these riverine sites, respectively. The sodium-prediction model detected human activities (represented by population density and impervious surface area) as major contributors to the salinity of U.S. rivers. In contrast, the alkalinity-prediction model identified natural processes as predominantly contributing to variation in riverine alkalinity flux, including runoff, carbonate sediment or siliciclastic sediment, soil pH, and soil moisture. Unlike prior studies, our analysis suggests that the alkalinization in U.S. rivers is largely governed by climatic and hydrogeological conditions. Trained machine learning models were also used to predict sodium and alkalinity fluxes in the next 60 years under various projected socioeconomic pathways assuming three highly important predictor variables including population density, temperature, and precipitation vary with socioeconomic pathway. The projected increase in future temperature likely leads to less road salt use in winter, resulting in a decrease in sodium flux in the northern U.S. However, sodium flux in the southern U.S. is projected to increase due to a rapid rise in population density. As for future alkalinity flux, the increase in temperature will likely inhibit the weathering of carbonate sediments when the temperature is > 10 °C, leading to a decrease in future alkalinity flux in regions where carbonate dominates the lithological component. In regions dominated by siliciclastic and unconsolidated sediments, and those with higher levels of soil organic carbon, rising temperature will accelerate the weathering of siliciclastic and unconsolidated sediments and the decomposition of soil organic carbon. This study provides insights for future environmental and water management policies.
Recommended Citation
E, Beibei, "A Machine Learning Approach For Assessing Human And Natural Impacts On The Current And Future Salinization And Alkalinization Of U.S. Freshwater" (2023). Theses - ALL. 762.
https://surface.syr.edu/thesis/762
