Autonomous Materials Discovery and Optimization Proceedings of a Workshop–in Brief (2023) / Chapter Skim
Currently Skimming:
Autonomous Materials Discovery and Optimization: Proceedings of a Workshop - in Brief
Autonomous Materials Discovery and Optimization: Proceedings of a Workshop - in Brief
Pages 1-13
The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.
From page 1... ...
The key to speeding Workshop planning committee chair Andrea Hodge of up this discovery and development process is what the University of Southern California added that this Aspuru-Guzik called the "self-driving lab" -- a machine meeting would bring together diverse experts to discuss that analyzes data from samples that have already been how to integrate autonomous materials discovery and made and uses those data to decide what material to optimization into the research and development process. make next.
|
From page 2... ...
However, Dehoff's team found that blades produced by AM failed in consistent AUTONOMOUS MATERIALS DESIGN ways. This ability to control the blades' properties made The day's first session was led by workshop planning it possible to optimize the AM process to produce blades committee members Susan Sinnott of The Pennsylvania that were extremely resistant to cracking.
|
From page 3... ...
Their AMANDA Line 1, for example, design process involves finding a material that meets is an automated device line that can start with basic specifications provided by a customer, including the materials, build a device, and then test it to create all of material properties, raw materials, and manufacturing the data necessary for understanding the performance constraints. Designers then use multi-objective of the device over time.
|
From page 4... ...
at NIST to use autonomous design and ML in the design and characterization of materials. AI has been a major Among the NSF programs that support research into focus at NIST for several years, she said, with dozens of autonomous materials discovery, Boswell-Koller said, AI-focused projects; Tavazza focused on efforts to apply the materials research science and engineering centers AI research to materials measurement.
|
From page 5... ...
Hattrick-Simpers concluded that the use of AI in autonomous learning in creating and testing hypotheses Dealing with Bias in Autonomous Learning Systems is very much a human endeavor despite the emphasis Jason Hattrick-Simpers of the University of Toronto on machines. Thus, in developing AI models for data offered some caveats on AI and autonomous learning analysis, he suggested that people specify constraints, based on how human biases can influence AI-based utilize statistical tools when possible, and create analyses.
|
From page 6... ...
Autonomous Research System, the first autonomous closed-loop research robot for materials, which learned This is where autonomous material synthesis and how to grow carbon nanotubes on its own. Autonomous testing could make a big difference, he said, by rapidly research robots are revolutionizing how research is generating data sets of design-relevant properties.
|
From page 7... ...
Because not MEASUREMENT TOOLS all of the chemicals they found in their search had data The day's first session was led by workshop planning on all of the important properties, they filled in gaps in committee members Robert Hull of Rensselaer the composition space with computations. They brought Polytechnic Institute and David Aspnes of North Carolina in human experts to filter the candidates that had State University, and consisted of two main presentations been identified in the search and also used a surrogate plus discussion by a four-person panel.
|
From page 8... ...
tool piezoelectrically active, which means that applying developed by Zeiss to study materials of various sorts. strain to them results in the production of an electric Instead of the single electron beam in a standard SEM, charge across the material and, vice versa, applying the MultiSEM has many parallel electron beams that an electric charge causes them to deform.
|
From page 9... ...
discussed the challenges inherent in autonomous Artificial Intelligence in Materials Testing materials discovery. A major issue driving the push for Brian Sheldon of Brown University offered two examples autonomous discovery is the "curse of dimensionality" -- of using AI in materials testing and then provided lessons that is, the vast number of factors that must be taken from his work in materials synthesis and testing.
|
From page 10... ...
Second, electrochemically materials such as those The day's second session was led by workshop planning used in batteries are messy to work with, and could be committee members John Koszewnik of Achates Power, challenging to develop such materials autonomously. Inc., and Lourdes Salamanca-Riba of the University of Maryland, and consisted of two main presentations plus Building Trust in Novel Materials Created by High-Throughput discussion by a three-person panel.
|
From page 11... ...
In general, Kusne Bukkapatnam described work being done at the Texas noted, ML is good at interpolating but terrible at A&M Engineering Experiment Station on an all-in-one extrapolating; the addition of physics knowledge allowed machine tool that combines directed energy deposition their system to overcome that limitation. addition with subtraction processing, heat treatment, and Then, Kusne touched briefly on two other examples of finishing in a single platform to simultaneously produce using autonomous technologies in physics.
|
From page 12... ...
Because data play a crucial role in enabling ML, thought He sees autonomous processes as just one more tool in needs to be given to the best ways to handle and enable his toolkit and that they still require a knowledgeable access to data. There is much to be done, but ML and AI human experimenter thinking about how to use them have the potential to accelerate materials discovery and efficiently and productively and not simply setting them optimization.
|
From page 13... ...
2023. Autonomous Materials Discovery and Optimization: Proceedings of a Workshop -- in Brief.
|
Key Terms
This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More
information on Chapter Skim is available.