Optimal soil venting design using Bayesian Decision analysis
Remediation of hydrocarbon-contaminated sites can be costly and the design process becomes complex in the presence of parameter uncertainty. Classical decision theory related to remediation design requires the parameter uncertainties to be stipulated in terms of statistical estimates based on site observations. In the absence of detailed data on parameter uncertainty, classical decision theory provides little contribution in designing a risk-based optimal design strategy. Bayesian decision theory, however, allows the use of subjective judgments of the designer together with parameter uncertainty in the decision-making process. In the present work, Bayesian theory is used in developing the theoretical framework for risk-based design analysis for soil gas venting operations. Two utility functions, exponential and quadratic, were used in the analysis, identifying the cost, and risk associated with under- or over-achieving the site stipulated remediation targets. Preposterior analysis provided the information on estimated optimal venting time, optimal effective flow rate and sample size for both utility functions, and the applicability of each function. Hypothetical field-scale simulations using normal and weathered gasoline were performed to demonstrate the applicability of Bayesian decision theory based analysis for practical scale problems.