Preface: AAAI-MLPS 2021 Combining Artificial Intelligence and Machine Learning with Physical Sciences Jonghyun Lee1 * , Eric F. Darve2 , Peter K. Kitanidis2 , Michael W. Mahoney3 , Anuj Karpatne4 , Matthew W. Farthing5 Tyler Hesser5 1 University of Hawai‘i at Mānoa, HI, USA 2 Stanford University, CA, USA 3 Univeristy of California Berkerley, CA, USA 4 Virginia Tech, VA, USA 5 U.S. Army Engineer Research and Development Center, MS, USA This volume contains the contributed papers selected of • Surya Ganguli, Stanford University the AAAI 2021 spring symposium on “Combining Artificial • Ben Adcock, Simon Fraser University Intelligence and Machine Learning with Physics Sciences.” The symposium was held on 22 to 24 March 2021 in a virtual • Animashree Anandkumar, Caltech/NVIDIA form because of the Covid-19 outbreak. • Nathan Kutz, University of Washington This symposium aimed to present the current state of • Jan S. Hesthaven, EPFL the art and identify opportunities and gaps in AI/ML-based physics modeling and analysis. With recent advances in for presenting their works to the audience of AAAI- scientific data acquisition and high-performance comput- MLPS2021. We thank all authors who submitted their pa- ing, Artificial Intelligence (AI) and Machine Learning (ML) pers for consideration. AAAI-MLPS Program Committee have received significant attention from the applied mathe- includes matics and physics science community. From successes re- • Kevin Carlberg, Facebook ported by industry, academia, and the research community • Marta D’Elia, Sandia National Laboratories at large, we observe that AI and ML hold great potential for leveraging scientific domain knowledge to support new sci- • Ramakrishnan Kannan, Oak Ridge National Laboratory entific discoveries and enhance the development of physical • Sanghyun Lee, Florida State University models for complex natural and engineered systems. • Yan Liu, University of Southern California The accepted papers were presented over 3 days with two invited talks each day. The symposium was broadcast live • Paris Perdikaris, University of Pennsylvania and camera-ready presentations were posted on the sympo- • Chris Rackauckas, MIT sium YouTube channel (link). More than 100 participants • Peter Sadowski, University of Hawai’i at Manoa contributed to intense discussion during presentation. Pre- senting topics include 1) state-of-art learning frameworks • Nathaniel Trask, Sandia National Laboratories that can seamlessly synthesize models, governing equations • Hongkyu Yoon, Sandia National Laboratories and data, 2) architectural and algorithmic improvements for scalable physics-informed learning, 3) stability and error • Rose Yu, University of California, San Diego analysis for physics-informed learning, 4) software develop- We also thank all Program Committee members and anony- ment facilitating the inclusion of physics domain knowledge mous referees for their reviewing of the submissions. The in learning, and 5) discovery of physically interpretable laws work was carried out using the EasyChair system supported from data. Applications included fluid mechanics, quantum by AAAI, and we gratefully acknowledge AAAI. mechanics, material sciences, and chemistry, and provided recent efforts in incorporating domain knowledge into ma- chine learning. As editors of the proceedings we are grateful to everyone who contributed to the symposium. We would like to thank the invited speakers: * jonghyun.harry.lee@hawaii.edu Copyright © 2021 for the individual papers by the papers’ authors. Copyright © 2021 for the volume as a collection by its editors. This volume and its papers are published under the Creative Commons License Attribution 4.0 International (CC BY 4.0).