Open Access. Powered by Scholars. Published by Universities.®
Electrical and Computer Engineering
Missouri University of Science and Technology
Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works
Articles 1 - 2 of 2
Full-Text Articles in Engineering
Modeling Land Subsidence Using Insar And Airborne Electromagnetic Data, Ryan G. Smith, R. Knight
Modeling Land Subsidence Using Insar And Airborne Electromagnetic Data, Ryan G. Smith, R. Knight
Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works
Land subsidence as a result of groundwater overpumping in the San Joaquin Valley, California, is associated with the loss of groundwater storage and aquifer contamination. Although the physical processes governing land subsidence are well understood, building predictive models of subsidence is challenging because so much subsurface information is required to do so accurately. For the first time, we integrate airborne electromagnetic data, representing the subsurface, with subsidence data, mapped by interferometric synthetic aperture radar (InSAR), to model deformation. By combining both data sets, we are able to solve for hydrologic and geophysical properties of the subsurface to effectively model the …
Clustering Data Of Mixed Categorical And Numerical Type With Unsupervised Feature Learning, Dao Lam, Mingzhen Wei, Donald C. Wunsch
Clustering Data Of Mixed Categorical And Numerical Type With Unsupervised Feature Learning, Dao Lam, Mingzhen Wei, Donald C. Wunsch
Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works
Mixed-type categorical and numerical data are a challenge in many applications. This general area of mixed-type data is among the frontier areas, where computational intelligence approaches are often brittle compared with the capabilities of living creatures. In this paper, unsupervised feature learning (UFL) is applied to the mixed-type data to achieve a sparse representation, which makes it easier for clustering algorithms to separate the data. Unlike other UFL methods that work with homogeneous data, such as image and video data, the presented UFL works with the mixed-type data using fuzzy adaptive resonance theory (ART). UFL with fuzzy ART (UFLA) obtains …