Explainable and trustworthy artificial intelligence for correctable modeling in chemical sciences.
Explainable and trustworthy artificial intelligence for correctable modeling in chemical sciences.
复制标题
DOI：
10.1126/sciadv.abc3204
复制
发表时间：
2020-10
期刊：
影响因子：
13.6
通讯作者：
Vlachos DG
中科院分区：
文献类型：
--
作者：
Feng J;Lansford JL;Katsoulakis MA;Vlachos DG
开发的框架将模型误差分摊到输入，计算预测保证，并实现模型的可校正性。数据科学主要关注大数据，但对于许多物理、化学和工程应用程序来说，数据往往是小的、相关的，因此是低维的，并且来自计算和实验以及各种级别的噪声。典型的统计和机器学习方法不适用于这些情况。专家知识是必不可少的，但缺乏一个系统的框架来将其纳入不确定性下的基于物理的模型中。在这里，我们通过不确定性量化和概率图形模型(PGMS)，为基于概率人工智能(AI)的预测建模开发了一个数学和计算框架，将数据、专家知识、多尺度模型和信息理论结合在一起。我们专门将PGMS应用于化学领域，并一般地为PGMS开发预测保证。我们提出的框架，结合了人工智能和不确定性量化，提供了可解释的结果，导致了可纠正的，最终是值得信赖的模型。在氧还原反应的微观动力学模型上对所提出的框架进行了论证。
The developed framework apportions model error to inputs, computes predictive guarantees, and enables model correctability. Data science has primarily focused on big data, but for many physics, chemistry, and engineering applications, data are often small, correlated and, thus, low dimensional, and sourced from both computations and experiments with various levels of noise. Typical statistics and machine learning methods do not work for these cases. Expert knowledge is essential, but a systematic framework for incorporating it into physics-based models under uncertainty is lacking. Here, we develop a mathematical and computational framework for probabilistic artificial intelligence (AI)–based predictive modeling combining data, expert knowledge, multiscale models, and information theory through uncertainty quantification and probabilistic graphical models (PGMs). We apply PGMs to chemistry specifically and develop predictive guarantees for PGMs generally. Our proposed framework, combining AI and uncertainty quantification, provides explainable results leading to correctable and, eventually, trustworthy models. The proposed framework is demonstrated on a microkinetic model of the oxygen reduction reaction.