Date:
Tuesday, March 12, 2019
Location:
Henry B. Gonzalez Convention Center, Room 221D
Organizer:
James Warren, National Institute of Standards and Technology
This special session will feature four leaders in the emerging discipline of autonomous materials research. Autonomous research employs artificial intelligence, robotics, and statistics to perform both experiments and simulations that optimally increase the information needed to map the performance-property-structure-processing linkages needed to design new materials.
Featured Speakers:
Stefano Curtarolo, Duke University
Presentation Title: "Data, Disorder and Materials"
About the Presentation
Critical understanding of large amounts of data exposes the unavoidability of disorder and leads to new descriptors for discovering entropic materials. The formalism, based on the energy distribution spectrum of randomized calculations, captures the accessibility of equally-sampled states near the ground state and quantifies configurational disorder capable of stabilizing high-entropy homogeneous phases. The methodology—applied to disordered refractory 5-metal carbides (promising candidates for high-hardness applications)—uncovers scientific surprises.
Benji Maruyama, Air Force Research Laboratory
Presentation Title: "Autonomous Experimentation Applied to Carbon Nanotube Synthesis"
About the Presentation
This presentation will discuss a first-of-its-kind Autonomous Research System, ARES, capable of designing, executing, and analyzing its own experiments autonomously using artificial intelligence (AI) and Machine Learning (ML). The closed loop, iterative method enables ARES to design new experiments based on prior results dynamically, after each experiment; a first for materials research. We are applying this method to understand and control the synthesis of single wall carbon nanotubes, in this case optimizing growth rate in (7) - dimensional parameter space. We use automated in situ Raman spectroscopy characterization of growth rate for CVD synthesis of carbon nanotubes as a metric for a target objective used by our AI planner. We use a random forest learning approach which models experimental results, and a genetic algorithm planner to propose new experiments expected to achieve the targeted growth rate. We expect ARES to be a disruptive advance in the near future, combining advances in robotics, AI, data sciences and operando methods to enable us to attack high dimensional research problems that were previously intractable by current research processes. We are applying the ARES method to multiple problems, including Additive Manufacturing and defect engineering in graphene. Human-robot research teams have the potential to redefine the research process and lead to a Moore’s Law for the speed of research.
Carla Gomes, Cornell University
Presentation Title: "SARA: Scientific Autonomous Reasoning Agent to Accelerate Materials Discovery"
About the Presentation
Artificial Intelligence (AI) is a rapidly advancing field. Novel machine learning methods combined with reasoning and search techniques have led us to reach new milestones, from self-driving cars to computer vision, machine translation, and Go and Chess world-champion level play using pure self-training strategies. These ever-expanding AI capabilities open up exciting new avenues for automating scientific discovery. This presentation will discuss work on using AI for accelerating and automating materials discovery. In particular, it will focus on high-throughput structure determination for combinatorial materials discovery and the phase map diagram problem for composition libraries. I will also describe SARA (Scientific Autonomous Reasoning Agent), a multi-Agent system to accelerate materials discovery integrating in a synergistic and complementary way, first principles quantum physics, experimental materials synthesis, processing, and characterization, and AI based algorithms for reasoning and scientific discovery, including the representation, planning, optimization, and learning of materials knowledge.
Jason Hattrick-Simpers, National Institute of Standards and Technology
Presentation Title: "Towards Autonomous Materials Research Systems"
About the Presentation
In the past five years, there has been an acceleration in the use of artificial intelligence (AI) in materials science. AI now pervades the entire materials science workflow from new hypothesis generation through knowledge extraction. In fact, when combined with automated synthesis and characterization robots and the state-of-the-art data infrastructure tools, AI closed-loop autonomous materials research systems become tangible possibilities. Such systems would use existing materials data to build AI derived testable hypotheses, identify appropriate materials to test these hypotheses, synthesize and characterize them, perform automated knowledge extraction and then begin the cycle anew without the need for human intervention. This presentation will discuss the bleeding edge of autonomous materials research including the 2018 Materials Accelerator Platform report and the autonomous systems predating it and inspired by it. It will also discuss recent NIST efforts at building multiple autonomous measurement systems to target structure and functionality in corrosion-resistant alloys.
The session will conclude with a panel discussion.
Following the panel discussion, a one-hour session on the new National Academies report, Frontiers of Materials Research: A Decadal Study, will be held in the same room.