Scalable AI
FOR BIG SCIENTIFIC CHALLENGES
SmartTensors transforms scientific challenges into opportunities with its science-informed AI framework. Extensively tested over 10+ years, SmartTensors has delivered groundbreaking insights in hydrology, environmental science, and climate analysis.
By leveraging advanced cloud computing and high-performance technologies, SmartTensors solves AI problems at scale. From Non-negative Matrix and Tensor Factorization methods to seamless handling of vast datasets, SmartTensors ensures precision and efficiency for large-scale scientific challenges.
Need more? Our team offers support and consulting to help you achieve your goals.
TRUSTED BY EXPERTS
Recognized by Industry
Trusted by experts and recognized globally, SmartTensors won two R&D 100 awards in 2021 for its groundbreaking contributions to AI and scientific problem-solving. With over a decade of development, rigorous testing, and applications in hydrology, environmental science, and climate analysis, SmartTensors is a proven leader in science-informed AI.
OPEN, ACCESSIBLE AND
Ready to Use
SmartTensors is open-source and available on GitHub, developed in Julia for performance and flexibility. With detailed tutorials and examples, you can get up and running in no time. Advanced visualization and mapping tools make it simple to process and interpret results. Need more? Our team offers support and consulting to help you achieve your goals.
Explore EnviCloud
Explore related demos
Try interactive public demos that bring these ideas to life.
- Public demo
Temporal Feature Extraction
Separate time-series data into interpretable hidden signals with NMFk.
Open demo (opens in a new tab) - Public demo
Spatial Feature Extraction
Discover spatial patterns, clusters, and hidden features in 2D and 3D data.
Open demo (opens in a new tab) - Public demo
Tensor Information
Compare data resolutions by retained information, structure, and computational cost.
Open demo (opens in a new tab) - Public demo
Information Theory Explorer
See how patterns and useful detail emerge in one- and two-dimensional data.
Open demo (opens in a new tab)
Related publications
- Discovering hidden geothermal signatures using non-negative matrix factorization with customized k-means clustering (2022) — V.V. Vesselinov et al. — Geothermics
- SmartTensors: Unsupervised and physics-informed machine learning framework for the geoscience applications (2022) — B. Ahmmed, V.V. Vesselinov, M.K. Mudunuru — Second International Meeting for Applied Geoscience & Energy
- Discovering Signatures of Hidden Geothermal Resources based on Unsupervised Learning (2020) — V.V. Vesselinov et al. — Stanford Geothermal Workshop
- Nonnegative tensor decomposition with custom clustering for microphase separation of block copolymers (2019) — B.S. Alexandrov et al. — Statistical Analysis and Data Mining
- Unsupervised Machine Learning Based on Non-Negative Tensor Factorization for Analyzing Reactive-Mixing (2019) — V.V. Vesselinov et al. — Journal of Computational Physics
- Unsupervised Machine Learning for Analysis of Coexisting Lipid Phases and Domain Growth in Biological Membranes (2019) — C.A. Lopez et al. — J. Chem. Theory Comput.
- Identification of the release sources in advection-diffusion system by machine learning combined with Green function inverse method (2018) — V.G. Stanev et al. — Applied Mathematical Modelling
- Nonnegative Matrix Factorization for identification of unknown number of sources emitting delayed signals (2018) — F.L. Iliev et al. — PLoS ONE
- Nonnegative Tensor Factorization for Contaminant Source Identification (2018) — V.V. Vesselinov, B.S. Alexandrov, D. O'Malley — Journal of Contaminant Hydrology
- Nonnegative/binary matrix factorization with a D-Wave quantum annealer (2018) — D. O'Malley et al. — PlosOne
- Unsupervised Machine Learning Based on Non-negative Tensor Factorization for Analysis of Filed Data and Simulation Outputs (2018) — V.V. Vesselinov et al. — Computational Methods in Water Resources (CMWR), Saint-Malo, France
- Unsupervised Phase Mapping of X-ray Diffraction Data by Nonnegative Matrix Factorization Integrated with Custom Clustering (2018) — V. Stanev et al. — Nature Computational Materials
- Contaminant source identification using semi-supervised machine learning (2017) — V.V. Vesselinov, D. O'Malley, B.S. Alexandrov — Journal of Contaminant Hydrology
- ToQ.jl: A high-level programming language for D-Wave machines based on Julia (2016) — D. O'Malley, V.V. Vesselinov — IEEE High Performance Extreme Computing
- Blind source separation for groundwater level analysis based on non-negative matrix factorization (2014) — B. Alexandrov, V.V. Vesselinov — Water Resources Research
Related presentations
- When Earth Meets AI (2025) — V.V. Vesselinov, T. Kliphuis — RealmIQ El Sailon
- Laying the groundwork for a greener future: ML for characterizing and managing geologic reservoirs (2024) — V.V. Vesselinov, H. Jasperson, T. Kliphuis
- Practical Glass-Box Machine Learning for Seasonal Water Supply Forecasting, with Applications to the Owyhee and Yellowstone Rivers: Regression Using Climate Indices Derived from SNOTEL Data Using Nonnegative Matrix Factorization with k-Means Clustering (2022) — W. Fleming, V.V. Vesselinov, A. Goodbody — AGU Fall Meeting
- GeoThermalCloud: Cloud Fusion of Big Data and Multi-Physics Models using Machine Learning for Discovery, Exploration and Development of Hidden Geothermal Resources (2021) — V.V. Vesselinov, et al. — Department of Energy, Geothermal Office
- GeoThermalCloud: Fusion of Big Data and Multi-Physics Models (2021) — V.V. Vesselinov, et al. — JuliaCon, Boston, MA
- Hidden geothermal signatures of the southwest New Mexico (2021) — V.V. Vesselinov, et al. — World Geothermal Congress, Reykjavik, Iceland
- SmartTensors: Unsupervised Machine Learning (2021) — V.V. Vesselinov, et al. — JuliaCon, Boston, MA
- Unsupervised and Physics-Informed Machine learning in Geosciences (2021) — V.V. Vesselinov, et al. — Baylor University, Texas
- Discovering Hidden Geothermal Signatures using Unsupervised Machine Learning (2020) — V.V. Vesselinov, et al. — Stanford Geothermal Workshop
- Unsupervised and Physics-Informed Machine Learning Analyses for Characterization of Energy Production from Unconventional Reservoirs (2020) — V.V. Vesselinov — Machine Learning in Oil & Gas Conference
- Unsupervised and Physics-Informed Machine Learning of Big and Noisy Data (2020) — V.V. Vesselinov — Bureau of Economic Geology, University of Austin, Texas
- Novel Unsupervised Machine Learning Methods for Data Analytics and Model Diagnostics (2019) — V.V. Vesselinov — Machine Learning in Solid Earth Geoscience, Santa Fe
- Unsupervised and Physics-Informed Machine Learning of Big Data (2019) — V.V. Vesselinov — Workshop: Applications of Big Data and High-Performance Computing in Earth Sciences, AGU Fall Meeting, San Francisco, CA (invited)
- Unsupervised Machine Learning Methods for Feature Extraction (2019) — V.V. Vesselinov — New Mexico Big Data & Analytics Summit
- Unsupervised Machine Learning: Nonnegative Matrix Tensor Decompositions (2019) — V.V. Vesselinov — MIT, Boston, MA
- Novel Machine Learning Methods for Extraction of Features Characterizing Complex Datasets and Models (2018) — V.V. Vesselinov — Recent Advances in Machine Learning and Computational Methods for Geoscience, Institute for Mathematics and its Applications, University of Minnesota
- Novel Machine Learning Methods for Extraction of Features Characterizing Datasets and Models (2018) — V.V. Vesselinov — AGU Fall meeting
- Novel Robust Machine Learning Methods for Identification and Extraction of Unknown Features in Complex Real-world Data Sets (2018) — V.V. Vesselinov, D. O'Malley, B. Alexandrov — Society for Industrial and Applied Mathematics (SIAM) Uncertainty Quantification, Garden Grove, CA (invited)
- Unsupervised Machine Learning Based on Non-negative Tensor Factorization for Analysis of Field Data and Simulation Outputs (2018) — V.V. Vesselinov et al. — Computational Methods in Water Resources (CMWR), Saint-Malo, France
- Unsupervised Machine Learning based on Nonnegative Matrix/Tensor Factorization (2018) — V.V. Vesselinov et al. — World Congress on Computational Mechanics (WCCM) (invited)
- Unsupervised Machine Learning Based on Tensor Factorization (2018) — V.V. Vesselinov, D. O'Malley, B. Alexandrov — International Society for Porous Media (INTERPORE)
- Nonnegative/binary matrix factorization with a D-Wave quantum annealer (2017) — D. O'Malley et al. — DOE LANL Presentation
- Uncertainty quantification and experimental design based on unsupervised machine learning identification of contaminant sources and groundwater types using hydrogeochemical data (2017) — V.V. Vesselinov, D. O'Malley, B. Alexandrov — AGU Fall Meeting
- Model-free Source Identification (2014) — V.V. Vesselinov, B. Alexandrov — AGU Fall Meeting