Predicting the output from a complex computer code when fast approximations are available
Predicting the output from a complex computer code when fast approximations are available
复制标题
DOI：
10.1093/biomet/87.1.1
复制
发表时间：
2000-03-01
期刊：
影响因子：
2.7
通讯作者：
O'Hagan, A
中科院分区：
文献类型：
--
作者：
Kennedy, MC;O'Hagan, A
我们考虑预测和不确定性分析复杂的计算机代码，可以运行在不同的复杂程度。特别是，我们希望通过将最复杂的代码版本的昂贵运行与从一个或多个更简单的近似中相对便宜的运行相结合来提高效率。描述了一种贝叶斯方法，其中关于代码的先验信念用高斯过程表示。给出了一个使用两个版本的油藏模拟器的实例。
We consider prediction and uncertainty analysis for complex computer codes which can be run at different levels of sophistication. In particular, we wish to improve efficiency by combining expensive runs of the most complex versions of the code with relatively cheap runs from one or more simpler approximations. A Bayesian approach is described in which prior beliefs about the codes are represented in terms of Gaussian processes. An example is presented using two versions of an oil reservoir simulator.