Intellectual Community as a Bridge of Interdisciplinary Graduate Education in Materials Data Science

MRS Advances ◽  
2020 ◽  
Vol 5 (7) ◽  
pp. 355-362
Author(s):  
Chi-Ning Chang ◽  
Clinton A. Patterson ◽  
Willie C. Harmon ◽  
Debra A. Fowler ◽  
Raymundo Arroyave
Keyword(s):  
Data Science ◽  
Graduate Program ◽  
Materials Science ◽  
Training Model ◽  
Materials Informatics ◽  
Materials Development ◽  
Intellectual Community ◽  
Interdisciplinary Learning ◽  
Interdisciplinary Approaches ◽  
Materials Genome

AbstractRecognizing materials development was advancing slower than technological needs, the 2011 the Materials Genome Initiative (MGI) advocated interdisciplinary approaches employing an informatics framework in materials discovery and development. In response, an interdisciplinary graduate program, funded by the National Science Foundation, was designed at the intersection of materials science, materials informatics, and engineering design, aiming to equip the next generation of scientists and engineers with Material Data Science. Based on the 4- year implementation experience, this report demonstrates how intellectual communities bridge students interdisciplinary learning processes and support a transition from disciplinary grounding to interdisciplinary learning and research. We hope this training model can benefit other interdisciplinary graduate programs, and produce a more productive and interdisciplinary materials workforce.

Data-Enabled Discovery and Design of Energy Materials (D3EM): Structure of An Interdisciplinary Materials Design Graduate Program

MRS Advances ◽  
2017 ◽  
Vol 2 (31-32) ◽  
pp. 1693-1698 ◽  
Author(s):  
Chi-Ning Chang ◽  
Brandie Semma ◽  
Marta Lynn Pardo ◽  
Debra Fowler ◽  
Patrick Shamberger ◽  
...  
Keyword(s):  
Graduate Program ◽  
Materials Science ◽  
Systems Design ◽  
Major Elements ◽  
Energy Materials ◽  
Materials Development ◽  
Development Cycle ◽  
Materials Genome ◽  
The Creation ◽  
Development Paradigm

ABSTRACTThe Materials Genome Initiative (MGI) calls for the acceleration of the materials development cycle through the integration of experiments and simulations within a data-aware/enabling framework. To realize this vision, MGI recognizes the need for the creation of a new kind of workforce capable of creating and/or deploying advanced informatics tools and methods into the materials discovery/development cycle. An interdisciplinary team at Texas A&M seeks to address this challenge by creating an interdisciplinary program that goes beyond MGI in that it incorporates the discipline of engineering systems design as an essential component of the new accelerated materials development paradigm. The Data-Enabled Discovery and Development of Energy Materials (D3EM) program seeks to create an interdisciplinary graduate program at the intersection of materials science, informatics, and design. In this paper, we describe the rationale for the creation of such a program, present the pedagogical model that forms the basis of the program, and describe some of the major elements of the program.

Merging Materials and Data Science: Opportunities, Challenges, and Education in Materials Informatics

MRS Advances ◽  
2020 ◽  
Vol 5 (7) ◽  
pp. 329-346 ◽  
Author(s):  
Thomas J. Oweida ◽  
Akhlak Mahmood ◽  
Matthew D. Manning ◽  
Sergei Rigin ◽  
Yaroslava G. Yingling
Keyword(s):  
Data Science ◽  
Materials Science ◽  
Optimization Techniques ◽  
Materials Informatics ◽  
Science And Engineering ◽  
Educational Challenges ◽  
Engineering Problems ◽  
Materials Science And Engineering ◽  
Materials Genome ◽  
Materials Genome Initiative

ABSTRACTSince the launch of the Materials Genome Initiative (MGI) the field of materials informatics (MI) emerged to remove the bottlenecks limiting the pathway towards rapid materials discovery. Although the machine learning (ML) and optimization techniques underlying MI were developed well over a decade ago, programs such as the MGI encouraged researchers to make the technical advancements that make these tools suitable for the unique challenges in materials science and engineering. Overall, MI has seen a remarkable rate in adoption over the past decade. However, for the continued growth of MI, the educational challenges associated with applying data science techniques to analyse materials science and engineering problems must be addressed. In this paper, we will discuss the growing use of materials informatics in academia and industry, highlight the need for educational advances in materials informatics, and discuss the implementation of a materials informatics course into the curriculum to jump-start interested students with the skills required to succeed in materials informatics projects.

Data-driven visualization schema of a materials informatics curriculum: Convergence of materials science and information science

MRS Advances ◽  
2020 ◽  
Vol 5 (7) ◽  
pp. 293-303
Author(s):  
Erik Einarsson ◽  
Olga Wodo ◽  
Prathima C. Nalam ◽  
Scott R. Broderick ◽  
Kristofer G. Reyes ◽  
...  
Keyword(s):  
Data Science ◽  
Information Science ◽  
Materials Science ◽  
Student Assessment ◽  
Critical Element ◽  
Illustrative Case ◽  
Materials Informatics ◽  
Curriculum Assessment ◽  
Illustrative Case Study

AbstractIn addition to student assessment, curriculum assessment is a critical element to any pedagogy. It helps the educator assess the teaching of concepts, determine what may be lacking, and make changes for continual improvement. Meaningful assessment can be complicated when disciplines converge or when new approaches are implemented. To facilitate this, we present a network-based visualization schema to represent a materials informatics curriculum that combines materials science and data science concepts. We analyze the curriculum using network representations and relevant concepts from graph theory. This reveals established connections, linkages between materials science and data science, and the extent to which different concepts are connected. We also describe how some materials science topics are introduced from a data perspective, and present an illustrative case study from the curriculum.

scholarly journals Materials informatics and sustainability—The case for urgency

2021 ◽  
Vol 2 ◽  
Author(s):  
Hannah R. Melia ◽  
Eric S. Muckley ◽  
James E. Saal
Keyword(s):  
Data Science ◽  
Materials Science ◽  
Advanced Materials ◽  
Materials Informatics ◽  
Design Development ◽  
Cultural Resistance ◽  
Scientific Methods ◽  
Skill Gaps ◽  
Digital Twins ◽  
Global Environmental

Abstract The development of transformative technologies for mitigating our global environmental and technological challenges will require significant innovation in the design, development, and manufacturing of advanced materials and chemicals. To achieve this innovation faster than what is possible by traditional human intuition-guided scientific methods, we must transition to a materials informatics-centered paradigm, in which synergies between data science, materials science, and artificial intelligence are leveraged to enable transformative, data-driven discoveries faster than ever before through the use of predictive models and digital twins. While materials informatics is experiencing rapidly increasing use across the materials and chemicals industries, broad adoption is hindered by barriers such as skill gaps, cultural resistance, and data sparsity. We discuss the importance of materials informatics for accelerating technological innovation, describe current barriers and examples of good practices, and offer suggestions for how researchers, funding agencies, and educational institutions can help accelerate the adoption of urgently needed informatics-based toolsets for science in the 21st century.

scholarly journals Enabling deeper learning on big data for materials informatics applications

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Dipendra Jha ◽  
Vishu Gupta ◽  
Logan Ward ◽  
Zijiang Yang ◽  
Christopher Wolverton ◽  
...  
Keyword(s):  
Neural Networks ◽  
Big Data ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Materials Science ◽  
Prediction Models ◽  
Model Performance ◽  
Materials Informatics ◽  
Learning Framework ◽  
Significant Attention

AbstractThe application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data.

From Concept to Commerce: The Challenge of Technology Transfer in Materials

MRS Bulletin ◽  
1990 ◽  
Vol 15 (8) ◽  
pp. 49-53 ◽  
Author(s):  
Larry L. Hench
Keyword(s):  
Technology Transfer ◽  
Materials Science ◽  
Science Research ◽  
Private Industry ◽  
Commercial Development ◽  
Materials Development ◽  
University Policy ◽  
Transfer Case ◽  
Effective Form ◽  
The Government

Many millions of dollars are invested annually in materials science research and development in U.S. universities. Both the universities and the sponsors, either government or private industry, have enormous incentives for the R&D efforts to become commercial. For private industry a successful development means new or improved products or processes and ultimately more profits. For the government, successful materials development can lead to improved hardware or operations efficiency and lower costs. For a university the payoff can be more than economic.Ideally, successful commercial development leads to royalties paid to the universities in the form of the most precious of assets — Unrestricted or flexible income. Students and faculty can benefit from the additional income, both privately, depending on university policy, and through their departments. However, benefits can also accrue in the form of experience and knowledge gained while participating in the technology transfer process from university to corporation. Students who take part in such efforts gain invaluable experience in preparing and defending patent applications, designing and developing prototypes, and they are exposed to economic and legal issues that are seldom taught in the classroom. They become more valuable graduates. Taking part in a technology transfer case history is a far more effective form of learning than reading about it.These benefits to a university are offset by a number of potentially negative factors. The space, time, personnel, equipment, and deadline pressures involved in commercialization are often beyond the capabilities of a university program. However, these limitations may not be realized until the effort has begun, and it is costly to stop in midstream, as is discussed below.

Materials Science vs. Data Science

2019 ◽  
pp. 3-12
Author(s):  
Jeffrey P. Simmons ◽  
Lawrence F. Drummy ◽  
Charles A. Bouman ◽  
Marc De Graef
Keyword(s):  
Data Science ◽  
Materials Science

scholarly journals From Single Cells to Flowers – Biological Complexity Driving Plant Reproductive Development

2021 ◽  
Author(s):  
Isabel Schwarz ◽  
Manuel Neumann ◽  
Rosario Vega ◽  
Xiaocai Xu ◽  
Letizia Cornaro ◽  
...  
Keyword(s):  
Science Communication ◽  
Data Science ◽  
Single Cells ◽  
Reproductive Development ◽  
Floral Organ ◽  
Future Research ◽  
High Resolution Data ◽  
Interdisciplinary Approaches ◽  
Share Data ◽  
Plant Reproductive Development

The rise of data science in biology stimulates interdisciplinary collaborations to address fundamental questions. Here, we report the outcome of the first SINFONIA symposium focused on revealing the mechanisms governing plant reproductive development across biological scales. The intricate and dynamic target networks of known regulators of flower development remain poorly understood. To analyze development from the genome to the final floral organ morphology, high-resolution data that capture spatiotemporal regulatory activities are necessary and require advanced computational methods for analysis and modeling. Moreover, frameworks to share data, practices and approaches that facilitate the combination of varied expertise to advance the field are called for. Training young researchers in interdisciplinary approaches and science communication offers the opportunity to establish a collaborative mindset to shape future research.

Automated Machine Learning for Business

2021 ◽  
Author(s):  
Kai R. Larsen ◽  
Daniel S. Becker
Keyword(s):  
Machine Learning ◽  
Data Science ◽  
Graduate Program ◽  
School Curriculum ◽  
High School Curriculum ◽  
Stakeholder Groups ◽  
New Development ◽  
Automated Machine Learning ◽  
Undergraduate Programs

In Automated Machine Learning for Business, we teach the machine learning process using a new development in data science: automated machine learning. AutoML, when implemented properly, makes machine learning accessible to most people because it removes the need for years of experience in the most arcane aspects of data science, such as the math, statistics, and computer science skills required to become a top contender in traditional machine learning. Anyone trained in the use of AutoML can use it to test their ideas and support the quality of those ideas during presentations to management and stakeholder groups. Because the requisite investment is one semester-long undergraduate course rather than a year in a graduate program, these tools will likely become a core component of undergraduate programs, and over time, even the high school curriculum.

Sign in / Sign up

Export Citation Format

Share Document