Network dissection of neural networks used in optimal groundwater remediation

Conference · Tue Dec 01 04:00:00 EST 1992

OSTI ID:6181697

Rogers, L L; Johnson, V M; Dowla, F U

We have been using an innovative computational approach for optimal groundwater management which involves use of artificial neural networks (ANNs) and the genetic algorithm (GA). In this approach, the ANN is trained to predict a particular aspect of the outcome of the flow and transport simulation. Then the.GA directs a search, based on the mechanics of genetics and natural selection, through possible management solutions, in this case patterns or realizations of pumping. These pumping realizations are presented to the trained ANN which predicts the outcome of the pumping realizations. The primary advantages of the ANN approach are parallel processing for the flow and transport simulations and the ability to recycle'' or reuse the base of knowledge formed by these flow and transport simulations.

• Research Organization: Lawrence Livermore National Lab., CA (United States)
• Sponsoring Organization: DOE; USDOE, Washington, DC (United States)
• DOE Contract Number: W-7405-ENG-48
• OSTI ID: 6181697
• Report Number(s): UCRL-JC-112428; CONF-930585--4; ON: DE93013849
• Country of Publication: United States
• Language: English

Related Subjects

54 ENVIRONMENTAL SCIENCES
540220 -- Environment
Terrestrial-- Chemicals Monitoring & Transport-- (1990-)
540250* -- Environment
Terrestrial-- Site Resource & Use Studies-- (1990-)
99 GENERAL AND MISCELLANEOUS
990200 -- Mathematics & Computers
ALGORITHMS
FLUID FLOW
GROUND WATER
HYDROGEN COMPOUNDS
LAWRENCE LIVERMORE LABORATORY
MATHEMATICAL LOGIC
MATHEMATICAL MODELS
NATIONAL ORGANIZATIONS
OXYGEN COMPOUNDS
REMEDIAL ACTION
US AEC
US DOE
US ERDA
US ORGANIZATIONS
WATER