Explainable and trustworthy artificial intelligence for correctable modeling in chemical sciences
| Autor: | Dionisios G. Vlachos, Joshua L. Lansford, Jinchao Feng, Markos A. Katsoulakis |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Multidisciplinary
business.industry Computation Big data Probabilistic logic SciAdv r-articles 02 engineering and technology 010402 general chemistry 021001 nanoscience & nanotechnology Information theory 01 natural sciences 0104 chemical sciences Chemistry Trustworthiness Applied Sciences and Engineering Artificial intelligence Noise (video) Graphical model Uncertainty quantification 0210 nano-technology business Research Articles Mathematics Research Article |
| Zdroj: | Science Advances |
| ISSN: | 2375-2548 |
| DOI: | 10.1126/sciadv.abc3204 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|