M
Mariush Kemblowski
Researcher at Utah State University
Publications - 29
Citations - 1557
Mariush Kemblowski is an academic researcher from Utah State University. The author has contributed to research in topics: Support vector machine & Statistical learning theory. The author has an hindex of 18, co-authored 29 publications receiving 1436 citations. Previous affiliations of Mariush Kemblowski include Arizona State University & Royal Dutch Shell.
Papers
More filters
Journal ArticleDOI
Multi-time scale stream flow predictions: The support vector machines approach
TL;DR: New data-driven models based on Statistical Learning Theory that were used to forecast flows at two time scales: seasonal flow volumes and hourly stream flows showed a promising performance in solving site-specific, real-time water resources management problems.
Journal ArticleDOI
Soil Moisture Prediction Using Support Vector Machines
TL;DR: Results from the SVM modeling are compared with predictions obtained from ANN models and show that SVM models performed better for soil moisture forecasting than ANN models.
Journal ArticleDOI
A Practical Approach to the Design, Operation, and Monitoring of In Situ Soil‐Venting Systems
TL;DR: In this paper, the authors present a decision tree approach to identify the limitations of in situ soil venting, and subjects or behavior that are currently difficult to quantify and for which future study is needed.
Journal ArticleDOI
Ionic and isotopic ratios for identification of salinity sources and missing data in the Gaza aquifer
TL;DR: In this paper, a Bayesian belief network (BBN) is used to identify salinization sources in the coastal aquifer of the Gaza Strip, based on a combination of different processes, such as seawater intrusion, upconing of brines from the deeper parts of the aquifer, flow of saline water from the adjacent Eocene aquifer and return flow from irrigation water, and leakage of wastewater.
Journal ArticleDOI
Support vectors–based groundwater head observation networks design
TL;DR: In this paper, a methodology based on Support Vector Machines (SVM) is proposed for designing long-term groundwater head monitoring networks in order to reduce spatial redundancy. But, a spatially redundant well does not change the potentiometric surface estimation error appreciably, if not sampled.