Unsupervised Machine Learning Based on Non-negative Tensor Factorization for Analysis of Filed Data and Simulation Outputs
V.V. Vesselinov, Karra Mudunuru. M., O'Malley S., Alexandrov D.
Computational Methods in Water Resources (CMWR), Saint-Malo, France2018DOI 10.13140/RG.2.2.27777.92005
Summary
In general, unsupervised machine learning (ML) methods are powerful tools for data analyses to extract essential features hidden in data. The integration of large datasets, powerful computational capabilities, and affordable data storage has resulted in the widespread use of ML in science, technology, and industry. Here we present applications of ML to characterize (1) reactive transport data observed at groundwater contamination sites, and (2) model simulations representing fast irreversible bimolecular reactions.