Uncertainty quantification and experimental design based on unsupervised machine learning identification of contaminant sources and groundwater types using hydrogeochemical data
V.V. Vesselinov, D. O'Malley, B. Alexandrov
AGU Fall Meeting2017
Summary
This presentation covers uncertainty quantification and experimental design based on unsupervised machine learning identification of contaminant sources and groundwater types using hydrogeochemical data. It discusses the use of nonnegative matrix factorization to identify hidden patterns in hydrogeochemical data, which can be used to classify groundwater types and identify contaminant sources. The presentation also covers how these insights can be used for uncertainty quantification and experimental design in groundwater studies.