Software
Materials Discovery
IAFD
A C++ source code package for IAFD is available. IAFD is a solver for the phase map identification problem, based on convolutive nonnegative matrix factorization. It includes performance improvements in the handling of constraints in comparison to AgileFD, and also supports additional constraints. IAFD accompanies the following publications:
- Gomes, C. P., Bai, J., Xue, Y., Björck, J., Rappazzo, B., Ament, S., Bernstein, R., Suram, S. K., van Dover, R. B., Gregoire, J. M. (2019). CRYSTAL: a multi-agent AI system for automated mapping of materials' crystal structures. MRS Communications, 1-9. 10.1557/mrc.2019.50
- Bai, J., Bjorck, J., Xue, Y., Suram, S. K., Gregoire, J., & Gomes, C. (2017). Relaxation Methods for Constrained Matrix Factorization Problems: Solving the Phase Mapping Problem in Materials Discovery. Fourteenth International Conference on Integration of Artificial Intelligence and Operations Research Techniques in Constraint Programming (CPAIOR), 104-112. doi: 10.1007/978-3-319-59776-8_9 [pdf]
For additional information, see the included README.
AgileFD
A C++ source code package for AgileFD is available. AgileFD is a solver for the phase map identification problem, based on convolutive nonnegative matrix factorization, with extensions to address additional challenges in this problem, including physical constraints. AgileFD accompanies the following publications:
- Xue, Y., Bai, J., Le Bras, R., Rappazzo, B., Bernstein, R., Bjorck, J., Longpre, L., Suram, S., van Dover, B., Gregoire, J., Gomes, C (2017). Phase-Mapper: An AI Platform to Accelerate High Throughput Materials Discovery. IAAI.
- Suram, S.K., Xue, Y., Bai, J., LeBras, R., Rappazzo, B.H., Bernstein, R., Bjorck, J., Zhou, L., van Dover, R.B., Gomes, C.P. and Gregoire, J.M. (2016). Automated Phase Mapping with AgileFD and its Application to Light Absorber Discovery in the V-Mn-Nb Oxide System. ACS Combinatorial Science. doi: 10.1021/acscombsci.6b00153 [pdf]
An example of the use of AgileFD and Phase Mapper is described in the video: Using Phase Mapper to discover a new light absorber material at JCAP.
For additional information, see the included README.
Data Instances
We provide a synthetic instance generator for the phase map identification problem. This generator requires Python and is cross-platform. For more information about how to use the generator, please read the README file contained in the package, as well as the publication:
- Le Bras, R., Bernstein, R., Gregoire, J. M., Suram, S. K., Gomes, C. P., Selman, B., & van Dover, R. B. (2014). A Computational Challenge Problem in Materials Discovery: Synthetic Problem Generator and Real-World Datasets. AAAI, 438-443. [pdf]
UDiscoverItViz
We also provide UDiscoverItViz, a graphical-user interface for visualizing instances and solutions to the phase map identification problem. This software allows you to visualize X-ray diffraction (XRD) patterns at different mixture compositions, to see how structure changes with composition, and to analyze a proposed solution to a given instance. It is a .NET application and runs only on Windows. For more information about how to use it, please read the README file contained in the package, as well as the publication listed above. For newly available features, here is the latest (beta) version of UDiscoverItViz.
