Wednesday, April 2, 2008 : 1:40 p.m.
Development of pattern recognition and learning utilities for groundwater recharge and discharge estimation and general model conceptualization
We have developed a Geographic Information System (GIS) software package, called the Pattern Recognition Organizer and Groundwater Recharge and Discharge Estimator for GIS (PRO-GRADE), to help hydrogeologists estimate R&D in a more efficient way than conventional methods. The PRO-GRADE uses numerical methods and image processing algorithms to estimate and visualize shallow R&D patterns and rates in GIS. It includes (but is not limited to) a default R&D estimation code, which only requires data for the water table and bedrock elevations and hydraulic conductivities, instead of labor intensive and time consuming field R&D measurements.
Our group has also developed another independent software package, called Spatial Pattern to Learn (SP2Learn), to cross analyze results from the PRO-GRADE with field information, such as land coverage, soil type, topographic maps and previous R&D estimates. The learning process of SP2Learn cross examines each initially recognized R&D pattern with a weighted segment in the reference spatial dataset, and then calculates a quantifiable reliability index using decision tree. These reliability indices will provide significant information to aid research in groundwater R&D estimation because they provide objectively quantifiable conceptual bases for further probabilistic uncertainty analyses.
Both the PRO-GRADE and SP2Learn have been designed as universal utilities for pattern recognition and learning from point data and zonation delineation. Both packages have been tested against an intensively studied field site in Wisconsin, and currently are being used for several active projects in Illinois and Wisconsin.
Jihua Wang, University of Illinois at Urbana-Champaign Jihua Wang is a PhD candidate in the Department of Civil and Environmental Engineering at University of Illinois at Urbana-Champaign. Her major interest is ground water modeling, water resources planning and management and eco-hydrology.
Chulyun Kim, University of Illinois at Urbana-Champaign Chulyun Kim is a graduate student working on image processing and pattern recognition in the Department of Computer Science.
Yu-Feng Lin, Illinois State Water Survey and University of Illinois at Urbana-Champaign Yu-Feng Lin (Forrest) is an Associate Professional Scientist at the Illinois State Water Survey and the University of Illinois at Urbana-Champaign. He received his M.S. in Civil and Environmental Engineering from the University of Connecticut in 1996, and his Ph.D. in Geological Engineering from the University of Wisconsin – Madison in 2002. Yu-Feng was a Faculty Fellow at the National Center for Supercomputing Applications in 2006. His research interests have involved groundwater modeling, recharge/discharge estimation, pattern recognition, machine learning and nanotechnology application in sensor development. His current research projects involve cooperation with the USGS, the USDA and the USEPA.
Albert Valocchi, University of Illinois at Urbana-Champaign Albert J. Valocchi is a Professor and Associate Head in the Dept. of Civil & Environmental Engineering at Univ. of Illinois. His research interest is Modeling the fate and transport of reactive contaminants in the subsurface environment, numerical methods; aquifer remediation and mathematical modeling applications in environmental and hydrological sciences.
Peter Bajcsy, National Center for Supercomputing Applications and University of Illinois at Urbana-Champaign Peter Bajcsy is a Research Scientist at National Center for Supercomputing Applications and University of Illinois at Urbana-Champaign. His research interests revolve around theoretical modeling and experimental understanding of multi-instrument measurement systems that deal with multi-dimensional multi-variate data, as well as, around automation of common image pre-processing and analysis tasks.