Recent studies point to a significant gap between current scenario practice and its potential contributions. Our research has significantly improved the analytic underpinnings of "scenario-discovery," one key step in an RDM analysis that may help bridge this gap. Scenario discovery uses statistical/data-mining algorithms to find policy-relevant clusters of cases in large, multi-dimensional databases of simulation model results. Conveniently interpreted as scenarios, these clusters help illuminate and quantify the tradeoffs among alternative strategies under deep uncertainty.
This paper systematically describes the scenario discovery concept and its implementation, presents statistical tests to evaluate the resulting scenarios, and demonstrates the approach on an example policy problem involving the efficacy of a proposed U.S. renewable energy standard.
Evaluates alternative algorithms needed to implement a novel task the authors call ''scenario discovery,'' in which users identify concise descriptions of input parameters to a simulation model.
Description of a new analytic method, based on robust decisionmaking, that could be applied to water resource management in California and climate change policy questions.
This study identifies robust, adaptive pollution-control strategies to help ensure economic growth and environmental quality for the 21st century.
