On-line transfer learning for multi-fidelity data fusion with ensemble of deep neural networks

Li, Zengcong; Zhang, Shu; Li, Hongqing; Tian, Kuo; Cheng, Zhizhong; Chen, Yan; Wang, Bo

doi:10.1016/j.aei.2022.101689

Cited by 23 publications

(1 citation statement)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This requires an efficient and accurate way to predict behavior in a wide parameter space with sparse coverage of the space by the training data set. To overcome this difficulty, an adaptive or multifidelity [151][152][153][154][155] ML approach may be required. One of the common methods to speed up predictions at unknown points in the parameter space, using knowledge obtained at sparse locations, is transfer learning [156][157].…”

Section: Transfer Learning: Scaling Ai/ml Models To Different Operati...mentioning

confidence: 99%

Artificial Intelligence Approaches for Energetic Materials by Design: State of the Art, Challenges, and Future Directions

Choi

Nguyen

Sen

et al. 2023

Propellants Explo Pyrotec

View full text Add to dashboard Cite

Artificial intelligence (AI) is rapidly emerging as a enabling tool for solving complex materials design problems. This paper aims to review recent advances in AI-driven materials-by-design and their applications to energetic materials (EM). Trained with data from numerical simulations and/or physical experiments, AI models can assimilate trends and patterns within the design parameter space, identify optimal material designs (micro-morphologies, combinations of materials in composites, etc.), and point to designs with superior/ targeted property and performance metrics. We review approaches focusing on such capabilities with respect to the three main stages of materials-by-design, namely representation learning of microstructure morphology (i. e., shape descriptors), structure-property-performance (SÀ PÀ P) linkage estimation, and optimization/design exploration. We leave out "process" as much work remains to be done to establish the connectivity between process and structure. We provide a perspective view of these methods in terms of their potential, practicality, and efficacy towards the realization of materialsby-design. Specifically, methods in the literature are evaluated in terms of their capacity to learn from a small/limited number of data, computational complexity, generalizability/scalability to other material species and operating conditions, interpretability of the model predictions, and the burden of supervision/data annotation. Finally, we suggest a few promising future research directions for EM materials-by-design, such as meta-learning, active learning, Bayesian learning, and semi-/weakly-supervised learning, to bridge the gap between machine learning research and EM research.

show abstract