Person

Daniel Speckhard

Member since 01/2019
Phone: +49 30 8413 4854
Room: T 1.04
Email: speckhard@fhi.mpg.de

RESEARCH TOPICS

• Machine learning for materials science data
• Estimating uncertainty in heterogeneous DFT data
• Statistical learning of material properties
• Improving normalizing and parsing of DFT data in NOMAD

METHODS

• SISSO, Decision Trees, Neural Networks
• All electron Density Functional Theory codes (FHI-AIMs, Exciting)
• Kibana, Elastic Search

2021

Articles

1. C. W. Andersen, R. Armiento, E. Blokhin, G. J. Conduit, S. Dwaraknath, M. L. Evans, Á. Fekete, A. Gopakumar, S. Gražulis, A. Merkys, F. Mohamed, C. Oses, G. Pizzi, G.-M. Rignanese, M. Scheidgen, L. Talirz, C. Toher, D. Winston, R. Aversa, K. Choudhary, P. Colinet, S. Curtarolo, D. Di Stefano, C. Draxl, S. Er, M. Esters, M. Fornari, M. Giantomassi, M. Govoni, G. Hautier, V. Hegde, M. K. Horton, P. Huck, G. Huhs, J. Hummelshøj, A. Kariryaa, B. Kozinsky, S. Kumbhar, M. Liu, N. Marzari, A. J. Morris, A. Mostofi, K. A. Persson, G. Petretto, T. A. R. Purcell, F. Ricci, F. Rose, M. Scheffler, D. Speckhard, M. Uhrin, A. Vaitkus, P. Villars, D. Waroquiers, C. Wolverton, M. Wu, and X. Yang,
   OPTIMADE: an API for exchanging materials data.
   Scientific Data 8, 217 (2021); https://doi.org/10.1038/s41597-021-00974-z
   Download: pdf

Within the publication lists the label [abs,src,ps] links to abstract, source file, and postscript version of the respective paper on the e-print archives of xxx.lanl.gov. Source and postscript files are usually transfered as gz-compressed tar-files. If your browser cannot automatically unpack those files you should proceed as follows:

Save the file as paper.tar.gz Execute the following commands (on a UNIX machine): gunzip paper.tar.gz tar -xvf paper.tar

return