A surrogate model approximates a computationally expensive solver. PolynomialChaos is a method to construct surrogate models by summing combinations ofcarefully chosen polynomials. The polynomials are chosen to respect theprobability distributions of the uncertain input variables (parameters); thisallows for both uncertainty quantification and global sensitivity analysis. In this paper we apply these techniques to a commercial solver for theestimation of peak gas rate and cumulative gas extraction from a coal seam gaswell. The polynomial expansion is shown to honour the underlying geophysicswith low error when compared to a much more complex and computationally slowercommercial solver. We make use of advanced numerical integration techniques toachieve this accuracy using relatively small amounts of training data.
展开▼
