Explore a Decisive Collection of Research Resources

A Framework for the Systematic Design of Segmentation Workflows

This paper lays the foundations to develop automated segmentation workflows. It systematically identifies the various steps and the sequence in which they should be applied to obtain good segmentation results. The proposed framework is validated on diverse collections of micrographs from very different material systems.

Iskakov, A., Kalidindi, S.R. A Framework for the Systematic Design of Segmentation Workflows. Integr Mater Manuf Innov 9, 70–88 (2020). https://doi.org/10.1007/s40192-019-00166-z

A Bayesian framework for materials knowledge systems

This prospective offers a new Bayesian framework that could guide the systematic application of the emerging toolsets of machine learning in the efforts to address two of the central bottlenecks encountered in materials innovation: (i) the capture of core materials knowledge in reduced-order forms that allow one to rapidly explore the vast materials design spaces, and (ii) objective guidance in the selection of experiments or simulations needed to identify the governing physics in the materials phenomena of interest. The framework builds on recent advances in the low-dimensional representation of the statistics describing the material’s hierarchical structure.

Kalidindi, S.R. A Bayesian framework for materials knowledge systems. MRS Communications 9, 518–531 (2019). https://doi.org/10.1557/mrc.2019.56

Feature engineering of material structure for AI-based materials knowledge systems

This article introduces systematically the foundational concepts undergirding the recently formulated AI (artificial intelligence)-based materials knowledge system (AI-MKS) framework. More specifically, these concepts deal with features engineering the heterogeneous material internal structure to obtain low-dimensional representations that can then be combined with machine learning models to establish low computational cost surrogate models for capturing the process–structure–property linkages over a hierarchy of material structure/lengths scales.

Journal of Applied Physics 128, 041103 (2020); https://doi.org/10.1063/5.0011258

UNLOCK INSIGHT

Real breakthroughs – the kind that can boost jet engine efficiency, enable novel medical devices and improve the performance of semiconductors – greatly depend on the understanding of new and available materials. Our platform unlocks critical insights faster – so you receive the best guidance for the next step of your vision.

Increased Velocity of Innovation
Achieve cost and time savings with fewer fabrication/manufacturing runs or fewer experiments and simulations.
Increased R&D Productivity
Automation of ingestion and curation of data from disparate sources, automated workflows for data analysis, reuse of high value datasets and models, increased enterprise-wide collaboration, and a continually improving knowledge system.

UNLOCK INSIGHT

Real breakthroughs – the kind that can boost jet engine efficiency, enable novel medical devices and improve the performance of semiconductors – greatly depend on the understanding of new and available materials. Our platform unlocks critical insights faster – so you receive the best guidance for the next step of your vision.

Increased Velocity of Innovation
Achieve cost and time savings with fewer fabrication/manufacturing runs or fewer experiments and simulations.
Increased R&D Productivity
Automation of ingestion and curation of data from disparate sources, automated workflows for data analysis, reuse of high value datasets and models, increased enterprise-wide collaboration, and a continually improving knowledge system.

MULTISCALE AI PLATFORM

No code enterprise grade solutions for materials innovation

Ecosystem-1

WORKFLOW AUTOMATION

Templates for mining Process-Structure-Property Linkages as core materials knowledge

Ecosystem-5

UNCERTAINTY QUANTIFICATION

Bayesian learning for sparse high dimensional datasets

Ecosystem-2

STRUCTURE QUANTIFICATION

Feature engineering of hierarchical material structure for AI-based materials knowledge

Ecosystem-3

MULTISCALE MATERIALS DESIGN

AI powered exploration and optimization of both materials and manufacturing processes

CREATE AN INNOVATION ECOSYSTEM

Connect experiments, simulations, and materials domain expertise through data-driven fusion.

Ecosystem-1

WORKFLOW AUTOMATION

Templates for mining Process-Structure-Property Linkages as core materials knowledge

Ecosystem-5

UNCERTAINTY QUANTIFICATION

Bayesian learning for sparse high dimensional datasets

Ecosystem-2

STRUCTURE QUANTIFICATION

Feature engineering of hierarchical material structure for AI-based materials knowledge

Ecosystem-3

MULTISCALE MATERIALS DESIGN

AI powered exploration and optimization of both materials and manufacturing processes

SPEED UP INNOVATION

DISCOVER MULTISCALE

SPEED UP INNOVATION

DISCOVER MULTISCALE

COPYRIGHT & PUBLISHED 2022