Calibration Using Emulation of Filtered Simulation Results
Calibration Using Emulation of Filtered Simulation Results
复制标题
DOI：
10.1109/wsc52266.2021.9715296
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Özge Sürer;M. Plumlee
中科院分区：
文献类型：
--
作者：
Özge Sürer;M. Plumlee
为了得出具有量化不确定性的精确预测，对模拟模型中的参数进行校准是必要的。一种可扩展的校准方法是在对模拟模型进行实验后构建一个模拟器。然而，当参数空间很大，即在校准前参数具有很大的不确定性时，大部分参数空间可能会产生与观测数据差异极大的不稳定或不切实际的模拟器响应。解决这个问题的一个方法是简单地丢弃或过滤掉那些产生不合理响应的参数，然后仅基于剩余的模拟器响应构建模拟器。在本文中，我们展示了一种模拟过滤后响应且避免不稳定和错误推断的方法的关键机制。这些想法通过一个校准新冠疫情流行病学模拟模型的实际数据示例进行了说明。
Calibration of parameters in simulation models is necessary to develop sharp predictions with quantified uncertainty. A scalable method for calibration involves building an emulator after conducting an experiment on the simulation model. However, when the parameter space is large, meaning the parameters are quite uncertain prior to calibration, much of the parameter space can produce unstable or unrealistic simulator responses that drastically differ from the observed data. One solution to this problem is to simply discard, or filter out, the parameters that gave unreasonable responses and then build an emulator only on the remaining simulator responses. In this article, we demonstrate the key mechanics for an approach that emulates filtered responses but also avoids unstable and incorrect inference. These ideas are illustrated on a real data example of calibrating COVID-19 epidemiological simulation model.