Unsupervised Machine Learning,Supervised Machine Learning,Physics-Informed Machine Learning,Science-Informed Machine Learning,Matrix Factorization,Tensor Factorization,Tensor Networks
SmartTensors is a general high-performance Unsupervised, Supervised and Physics-Informed Machine Learning and Artificial Intelligence (ML/AI).
SmartTensors includes a series of alternative ML/AI methods / algorithms (NMFk, NTFk, NTTk, SVR, etc.) coupled with constraints (sparsity, nonnegativity, physics, etc.).
SmartTensors is developed in Julia.
NMFk is a novel unsupervised ML method based on Matrix Decomposition.
NTFk is a novel unsupervised ML method based on Tensor Decomposition.
SmartTensors extracts COVID-19 pandemic waves.
SmartTensors discovers spatiotemporal dynamics in California climate data impacting wildfire and re-burn occurrence.
SmartTensors reveals hidden features associated with advection, dispersion, diffusion, and boundary effects in reactive-mixing simulations.
SmartTensors extracts spatiotemporal climate patterns associated with heat waves over Europe.
SmartTensors extracts spatiotemporal climate patterns associated with precipitation over USA.
SmartTensors characterizes plume sources and contaminant transport at the LANL (Los Alamos National Laboratory) chromium site.
SmartTensors characterizes and predicts processes impacting the LANSCE (Los Alamos Neutron Accelerator) operations.
SmartTensors differentiates phase separation of co-polymers.
SmartTensors extracts seismic processes associated with geothermal extraction at the Geysers geothermal field, California.
SmartTensors deconstructs relations bwtween the Oklahoma seismic events caused and the oil/gas production activities.
SmartTensors discovers hidden geothermal resources and signatures in Southwest New Mexico.
SmartTensors predicts oil/gas production within the Eagle Ford unconventional reservoir, Texas.
SmartTenosrs is open source and available on GitHub
SmartTensors resources include: