Workshop Report on Basic Research Needs for Scientific Machine Learning: Core Technologies for Artificial Intelligence

By Nathan A. Baker, Frank Alexander, Timo Bremer, Aric A. Hagberg, Y. Kevrekidis, Habib N. Najm, M. Parashar, A. Patra, James A. Sethian, S. Wild and 1 more. 2018

321 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems and Management, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/aad3be5f9ec6aabd5a2f1201523e0a70de99abc7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xuhui Meng
2. G. Em Karniadakis
3. Zhiping Mao
4. Lu Lu
5. Michael S. Steinbach
6. Vipin Kumar
7. Xiaowei Jia
8. Jared D. Willard

In Information Systems and Management

1. Michael S. Steinbach
2. Xiaowei Jia
3. Jared D. Willard
4. Vipin Kumar

In Materials Chemistry

1. Xuhui Meng
2. G. Em Karniadakis
3. Ulisses M. Braga-Neto
4. T. Nissen‐Meyer
5. Panos Stinis
6. Michael S. Steinbach
7. Levi D. McClenny
8. Benjamin Moseley

Citations in the corpus

• Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism (2020, methodology): “(37) To allow a direct comparison to the Helmholtz PDE result reported in [12], we take a1 = 1 and a2 = 4 and use the same neural network architecture with layer sizes [2, 50, 50, 50, 50, 1].”
• Enforcing Constraints for Time Series Prediction in Supervised, Unsupervised and Reinforcement Learning (2019, background): “Several related priority research directions were stated in the recently published report (Baker et al. 2019).”
• Integrating Physics-Based Modeling with Machine Learning: A Survey (2020, background): “…approach can be considered sufficient for complex scientific and engineering applications, the research community is beginning to explore the continuum between mechanistic and ML models, where both scientific knowledge and data are integrated in a synergistic manner [2, 14, 126, 204].”
• Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems (2020, background): “Also, many workshops and symposiums have formed to focus on this field (e.g. [1–6 , 21]).”
• Finite basis physics-informed neural networks (FBPINNs): a scalable domain decomposition approach for solving differential equations (2021, methodology): “A more recent strategy is to blend together physical principles and traditional algorithms with machine learning in a more nuanced way to create more powerful models, in the burgeoning field of scientific machine learning (SciML) [10, 11].”
• DeepXDE: A Deep Learning Library for Solving Differential Equations (2019, background): “However, more recently, solving partial differential equations (PDEs) via deep learning has emerged as a potentially new sub-field under the name of Scientific Machine Learning [1].”
• Universal Differential Equations for Scientific Machine Learning (2020, background): “[12] Nathan Baker, Frank Alexander, Timo Bremer, Aric Hagberg, Yannis Kevrekidis, Habib Najm, Manish Parashar, Abani Patra, James Sethian, Stefan Wild, et al.”