Sort by
Refine Your Search
-
intelligence and machine learning tools. 1. S. M. Chavali, J. Roller, M. Dagenais and B. H. Hamadani, Sol. Eng. Mater. Sol. Cells, 236, 111543 (2022). 2. B. H. Hamadani, Appl. Phys. Lett., 117, 043904 (2020
-
advantage of associated particle separations, physical characterization, and chemical analysis. Projects incorporating machine learning and chemometric approaches are also welcome. We are seeking independent
-
) with an infrastructure that centrally archives and curates every dataset via NexusLIMS (publication and GitHub repo ). With close to 100 TB of machine-actionable data—ranging from 1D spectroscopy to 4D
-
Kumar Banerjee [email protected] 301.975.3538 Description The use of lightweight materials in vehicles will significantly increase fuel efficiency and cut emissions, but the auto industry lacks data
-
are not sufficiently accurate, or the methods are too expensive to accurately model sufficiently large systems. As a result, these computational problems are ideal for developing machine-learned potentials
-
that are difficult to obtain via traditional casting and subtractive machining. At the same time, additive materials are subject to extreme conditions that can include repeated thermal cycling both near and beyond
-
; Hyperspectral imaging; Data mining; Machine learning; Microspectroscopy;
-
alloys, carbon-based composites, and solid-state-biomolecule hybrid structures. Our data-driven development uses cheminformatics methodologies combined with machine learning methods to produce predictive
-
quantitative biophysical studies of cells and optical biopsies of tissues. Ongoing research in this area involves: (1) microscopy with label-free contrasts involving auto-fluorescence, absorption, and scattering
-
substances in a wide pressure and temperature ranges). We also possess significant computational resources necessary for successful implementation of molecular simulations and machine learning methods