Application of neural networks to waste site screening
- Science Applications International Corp., San Diego, CA (United States)
Waste site screening requires knowledge of the actual concentrations of hazardous materials and rates of flow around and below the site with time. The present approach to site screening consists primarily of drilling, boreholes near contaminated site and chemically analyzing the extracted physical samples and processing the data. In addition, hydraulic and geochemical soil properties are obtained so that numerical simulation models can be used to interpret and extrapolate the field data. The objective of this work is to investigate the feasibility of using neural network techniques to reduce the cost of waste site screening. A successful technique may lead to an ability to reduce the number of boreholes and the number of samples analyzed from each borehole to properly screen the waste site. The analytic tool development described here is inexpensive because it makes use of neural network techniques that can interpolate rapidly and which can learn how to analyze data rather than having to be explicitly programmed. In the following sections, data collection and data analyses will be described, followed by a section on different neural network techniques used. The results will be presented and compared with mathematical model. Finally, the last section will summarize the research work performed and make several recommendations for future work.
- Research Organization:
- EG and G Idaho, Inc., Idaho Falls, ID (United States). National Low-Level Waste Management Program
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- OSTI ID:
- 343726
- Report Number(s):
- CONF-921137-PROC.; ON: DE98050439; TRN: IM9921%%190
- Resource Relation:
- Conference: 14. annual DOE low-level radioactive waste management conference, Phoenix, AZ (United States), 18-20 Nov 1992; Other Information: PBD: Mar 1993; Related Information: Is Part Of Fourteenth annual U.S. Department of Energy low-level radioactive waste management conference: Proceedings; PB: 651 p.
- Country of Publication:
- United States
- Language:
- English
Similar Records
Deep Convolutional Neural Networks as a Rapid Screening Tool for Complex Additively Manufactured Structures
Final Technical Report - Applications of Machine Learning Techniques to Geothermal Play Fairway Analysis in the Great Basin Region, Nevada