当前位置: X-MOL 学术J. Comput. Phys. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Mutual information for explainable deep learning of multiscale systems
Journal of Computational Physics ( IF 3.8 ) Pub Date : 2021-07-09 , DOI: 10.1016/j.jcp.2021.110551
Søren Taverniers , Eric J. Hall , Markos A. Katsoulakis , Daniel M. Tartakovsky

Timely completion of design cycles for complex systems ranging from consumer electronics to hypersonic vehicles relies on rapid simulation-based prototyping. The latter typically involves high-dimensional spaces of possibly correlated control variables (CVs) and quantities of interest (QoIs) with non-Gaussian and possibly multimodal distributions. We develop a model-agnostic, moment-independent global sensitivity analysis (GSA) that relies on differential mutual information to rank the effects of CVs on QoIs. The data requirements of this information-theoretic approach to GSA are met by replacing computationally intensive components of the physics-based model with a deep neural network surrogate. Subsequently, the GSA is used to explain the surrogate predictions, and the surrogate-driven GSA is deployed as an uncertainty quantification emulator to close design loops. Viewed as an uncertainty quantification method for interrogating the surrogate, this framework is compatible with a wide variety of black-box models. We demonstrate that the surrogate-driven mutual information GSA provides useful and distinguishable rankings via a validation step for applications of interest in energy storage. Consequently, our information-theoretic GSA provides an “outer loop” for accelerated product design by identifying the most and least sensitive input directions and performing subsequent optimization over appropriately reduced parameter subspaces.



中文翻译:

多尺度系统可解释深度学习的互信息

及时完成从消费电子产品到高超音速飞行器等复杂系统的设计周期依赖于基于快速仿真的原型设计。后者通常涉及可能相关的控制变量 (CV) 和感兴趣量 (QoI) 的高维空间,具有非高斯分布和可能的多峰分布。我们开发了一种与模型无关、与矩无关的全局敏感性分析 (GSA),它依赖于差分互信息来对 CV 对 QoI 的影响进行排序。通过用深度神经网络替代品替换基于物理模型的计算密集型组件,可以满足这种 GSA 信息理论方法的数据要求。随后,GSA 用于解释代理预测,代理驱动的 GSA 被部署为不确定性量化仿真器以关闭设计循环。作为询问代理的不确定性量化方法,该框架与各种黑盒模型兼容。我们证明了代理驱动的互信息 GSA 通过验证步骤为感兴趣的储能应用提供了有用且可区分的排名。因此,我们的信息论 GSA 通过识别最敏感和最不敏感的输入方向并在适当减少的参数子空间上执行后续优化,为加速产品设计提供了一个“外循环”。我们证明了代理驱动的互信息 GSA 通过验证步骤为感兴趣的储能应用提供了有用且可区分的排名。因此,我们的信息论 GSA 通过识别最敏感和最不敏感的输入方向并在适当减少的参数子空间上执行后续优化,为加速产品设计提供了一个“外循环”。我们证明了代理驱动的互信息 GSA 通过验证步骤为感兴趣的储能应用提供了有用且可区分的排名。因此,我们的信息论 GSA 通过识别最敏感和最不敏感的输入方向并在适当减少的参数子空间上执行后续优化,为加速产品设计提供了一个“外循环”。

更新日期:2021-07-16
down
wechat
bug