Efficient

Exploratory Research on Knowledge Integration for Long-Term Monitoring, Operations, and Stewardship
B. S. Minsker,,* A. Valocchi,* V. Babovic, L. Durham, B. Michael, D. Tcheng, J. Quinn, M. Welge, G. Williams.
Sponsor: National Center for Supercomputing Applications, University of Illinois.
Sponsor: Argonne National Laboratory.

Due to technical limitations and the high cost of hazardous waste site clean up, there has been a shift toward risk-based long-term management of sites, where some contamination is left in place. A recent DOE report identifies the need for managing existing restoration sites for periods of 70 years or longer. As the groundwater remediation field matures and the installation of remediation systems are completed, it is becoming clear that long-term monitoring, operation, and stewardship (LTMOS) of these systems will comprise a significant portion of future expenditures. LTMOS data collection objectives are not well defined and only a small portion of the data currently collected is used to assess the remediation progress. The University of Illinois, Argonne National Laboratory, and DHI Water and Environment are collaborating to demonstrate how integrating all available site data can improve LTMOS decision making and provide cost savings.

The initial approach will involve using an artificial neural network (ANN) to integrate historic and current data from the 317/319 Area phytoremediation site at Argonne National Lab-East (ANL-E) with an existing Modflow flow model to provide a better understanding of site processes and direct future data collection. The complex geology and spotty history of waste disposal practices make the application of transport models impractical. The unstructured nature of ANNs allows these complexities to be included in a flexible framework for decision making.

The site is currently monitored under multiple programs, each with different objectives and timelines. Development of the ANN will provide a method for integrating the diverse data sources available at the site and using that information to determine the importance of each data source in achieving monitoring objectives.