Surface Water



Data Mining is being applied to an array of problems related to the interactions between natural and man-made systems. These interactions are becoming increasingly important as growing populations and development place heavier burdens on our environment. An area of particular success has been in Data Mining for surface water systems - streams, lakes, rivers, and estuaries.

 

Sample ADMi Surface Water Projects.  The results of these projects are published and  links provided:

 

Beaufort River Water Quality

Need:      The regulatory permitting of 3 wastewater treatment plants on the Beaufort River, South Carolina.  The Beaufort River is a complex estruarine river system on the list of impaired waters for low dissolved oxygen (DO) concentrations.  The Clean Water Act stipulates that a Total Maximum Daily Load (TMDL) be determined.

 

Results:   ADMi developed the Beaufort water quality models, ADMi developed a Microsoft EXCELTM based Decision Support System (DSS), results were applied, and permits were issued over a time period of 2.5 years.  Similar projects in Myrtle Beach and Charleston, SC using traditional mechanistic models have taken 7+ and 10+ years respectively.  ADMi’s methods deliver models with demonstrably better prediction accuracy and in packaging  that is readily used by  individuals of varying technical ability.  

 

Savannah Harbor Deepening

Need:      The Savannah Harbor, one of the busiest ports on the East Coast of the USA, is located downstream from the Savannah National Wildlife Refuge (SNWR), an important freshwater marsh. The needs of the Savannah DSS were to assess the impact of the deepening and various mitigation scenarios, model water levels and salinities in the marsh from riverine inputs (M2M), and integrate a 3D hyrdrodynamic model and a plant succession model with the M2M.

 

Results:  ADMi developed the Savannah  models and built a Microsoft EXCELTM based DSS in 3 phases over 4 years.  The DSS is currently being used.

 

Pee Dee River Salinity Intrusion

Need:      Six reservoirs in North Carolina discharge into the Pee Dee River, which flows through South Carolina to the coastal communities near Myrtle Beach. During the drought between 1998 and 2002, salinity intrusions inundated a coastal municipal freshwater intake near Myrtle Beach, South Carolina. The North Carolina reservoirs are currently being re-licensed by the Federal Energy Regulatory Commission (FERC) for a 50-year operating permit. The water has important commercial value for generating electric power and for waterfront property development. A coalition composed of Alcoa Power, Progress Energy, the Pee Dee River Coalition, and the South Carolina Department of Natural Resources sought to model the system’s hydrodynamics and determine the minimum flows needed to protect coastal intakes.

 

Results:   ADMi developed the Pee Dee  models and built a Microsoft EXCELTM based DSS and the results were accepted by the stakeholders over a time period of 1.5 years.  The DSS is currently being used in the relicensing process.

 


 Related White Papers and Publications
 

Data Mining Surface Water Systems - a white paper from ADMi

 

Features of Advanced Decision Support Systems for Environmental Studies, Management, and Regulation , Edwin A. Roehl, Jr.,  Paul Conrads, Ruby C. Daamen

http://sc.water.usgs.gov/publications/pdfs/HIC2006_DSS.pdf

 

Transforming Large Databases into Critical Knowledge Using Data Mining – Three Case Studies in South Carolina and Georgia, Paul Conrads, Edwin A. Roehl, Jr.

http://sc.water.usgs.gov/publications/pdfs/WEFTEC06_3CaseStudies.pdf

 

Development of an Empirical Model of a Complex, Tidally Affected River Using Artificial Neural Networks,  Paul Conrads, Edwin A. Roehl, Jr., William B. Martello

http://sc.water.usgs.gov/publications/abstracts/TMDL0301a1-Abstract.html

 

Integration of Data Mining Techniques with Mechanistic Models to Determine the Impacts of Non-Point Source Loading on Dissolved Oxygen in Tidal Waters, Paul Conrads, Edwin A. Roehl, Jr.

http://www.sc-ec.org/PDFs/2005SCEC/18-4%20Using%20Data%20Mining%20Techniques.pdf

 

Estimating water temperatures in small streams in western Oregon using neural network models, Risley, John C.; Roehl, Edwin A., Jr.; Conrads, Paul A.

http://pubs.er.usgs.gov/usgspubs/wri/wri024218

 

An Artificial Neural Network-Based Decision Support System to Evaluate Hydropower Releases on Salinity Intrusion, Conrads, Paul A.; Roehl, Edwin A., Jr

http://sc.water.usgs.gov/publications/pdfs/HIC2006_PeeDee.pdf

Estimating Water Depths Using Artificial Neural Networks, Conrads, Paul A.; Roehl, Edwin A., Jr.

http://sc.water.usgs.gov/publications/pdfs/HIC2006_EDEN.pdf

 

Integrating 3D Hydrodynamic Transport and Ecological Plant Models of the Savannah River Estuary Using Artificial Neural Network Models, Ruby C. Daamen; Edwin A. Roehl, Jr.; Paul A. Conrads; Wiley M. Kitchens

http://sc.water.usgs.gov/publications/pdfs/HIC2006_M2M.pdf

Using Artificial Neural Network Models To IntegrateE Hydrologic And Ecological Studies of the Snail Kite in the Everglades, USA, Conrads, Paul A.; Roehl, Edwin A., Jr.; Ruby C. Daamen; Wiley M. Kitchens

http://sc.water.usgs.gov/publications/pdfs/HIC2006_SnailKite.pdf

 

ADMI, LLC 3620 Pelham Rd. PMB 351, Greenville, SC 29615 (843) 513-2130


   

 

 
 

 

   

  ©2007 ADMi

   
  Web Site by TrueZeal.com .net