Materials design traditionally relies on numerical simulation, theoretical analysis, and topology optimization. Materials scientists manually analyze various kinds of materials data such as 1D spectra, 2D images, and 3D point clouds to investigate or characterize structural or functional metallic materials. However, these methods have severe drawbacks, such as the demand for expertise, poor repeatability, and time-consuming processes. With the rise of high-throughput experiments and calculations, manual data analysis is no longer efficient or effective for materials development, and it heavily hinders the advances in materials science.
In the recent past, materials informatics emerged as a solution to this problem through data-driven techniques, including machine learning (ML) and other artificial intelligence (AI) approaches. Combining ML with simulations or experiments is an emerging topic at the frontier of science. It provides a data-efficient paradigm for fast and intelligent materials design with tailored mechanical, physical, and chemical properties. Image recognition algorithms, as a representative of deep learning, can speed up the analysis of micrographs, improve the repeatability of the analysis, and reveal unforeseen patterns and details that would be hidden without the application of advanced data-mining techniques.
This article collection on Artificial Intelligence for Metallic Materials aims to focus on the latest research relevant to solving challenges in metallic materials via AI. It comprises advanced structural or functional materials design, complex experimental and simulated data analysis, high-throughput experiments and calculations, text/reference data mining, standard materials data analysis workflows, and so on. Through the integration of diverse AI techniques, the desired outcome should tackle material science problems with greater efficiency and accuracy.
This collection provides a forum for publishing original full-length papers and reviews that advance the field of metallic materials and push the boundaries of what is possible. Papers with a high impact potential and/or substantially advance the field are sought.
The following aspects of the science and engineering of metals and alloys are of particular interest:
1. AI-aided multi-objective design of metallic materials
2. Advanced metallic materials design under uncertainty analysis
3. AI for materials characterization
4. AI for numerical simulation
5. High-throughput experiments
6. High-throughput calculations
7. ML model development, applications, and validation in metallic materials
8. Standard materials data management: FAIR
Keywords:
Structural materials, functional materials, machine learning, materials design, characterization, material simulation, materials data science
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Materials design traditionally relies on numerical simulation, theoretical analysis, and topology optimization. Materials scientists manually analyze various kinds of materials data such as 1D spectra, 2D images, and 3D point clouds to investigate or characterize structural or functional metallic materials. However, these methods have severe drawbacks, such as the demand for expertise, poor repeatability, and time-consuming processes. With the rise of high-throughput experiments and calculations, manual data analysis is no longer efficient or effective for materials development, and it heavily hinders the advances in materials science.
In the recent past, materials informatics emerged as a solution to this problem through data-driven techniques, including machine learning (ML) and other artificial intelligence (AI) approaches. Combining ML with simulations or experiments is an emerging topic at the frontier of science. It provides a data-efficient paradigm for fast and intelligent materials design with tailored mechanical, physical, and chemical properties. Image recognition algorithms, as a representative of deep learning, can speed up the analysis of micrographs, improve the repeatability of the analysis, and reveal unforeseen patterns and details that would be hidden without the application of advanced data-mining techniques.
This article collection on Artificial Intelligence for Metallic Materials aims to focus on the latest research relevant to solving challenges in metallic materials via AI. It comprises advanced structural or functional materials design, complex experimental and simulated data analysis, high-throughput experiments and calculations, text/reference data mining, standard materials data analysis workflows, and so on. Through the integration of diverse AI techniques, the desired outcome should tackle material science problems with greater efficiency and accuracy.
This collection provides a forum for publishing original full-length papers and reviews that advance the field of metallic materials and push the boundaries of what is possible. Papers with a high impact potential and/or substantially advance the field are sought.
The following aspects of the science and engineering of metals and alloys are of particular interest:
1. AI-aided multi-objective design of metallic materials
2. Advanced metallic materials design under uncertainty analysis
3. AI for materials characterization
4. AI for numerical simulation
5. High-throughput experiments
6. High-throughput calculations
7. ML model development, applications, and validation in metallic materials
8. Standard materials data management: FAIR
Keywords:
Structural materials, functional materials, machine learning, materials design, characterization, material simulation, materials data science
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.