Unsupervised Machine Learning,Science-informed Machine Learning,Matrix Factorization,Tensor Factorization
NMFk is a novel unsupervised Machine Learning method based on Matrix Decomposition coupled with sparsity and nonnegativity constraints.
NMFk is developed in Julia.
NTFk is a novel unsupervised Machine Learning method based on Tensor Decomposition coupled with sparsity and nonnegativity constraints.
NTFk is developed in Julia.
Machine Learning applications, publications, presentations and videos
NTFk is applied to reveal hidden features associated with advection, dispersion, diffusion and boundary effects in reactive-diffusion simulations.
NTFk is applied to extract spatial and temporal climate patterns associated with heat waves over Europe.
NMFk/NTFk are applied to analyze field geochemical data collected at the LANL chromium site to characterize contaminant plume sources and transport processes.
NMFk is applied to characterize processes during the LANSCE (Los Alamos Neutron Accelerator) operation.
NTFk is applied to differentiate phase separation of co-polymers.
NTFk is applied to represent seismic processes associated with geothermal activities.