Big Data for Computational Chemistry: Unified machine learning and sparse grid combination technique for quantum based molecular design
Third-party funded project
Project title Big Data for Computational Chemistry: Unified machine learning and sparse grid combination technique for quantum based molecular design
Principal Investigator(s) Harbrecht, Helmut
Co-Investigator(s) von Lilienfeld, Anatole
Project Members Zaspel, Peter
Huang, Bing
Organisation / Research unit Departement Mathematik und Informatik / Computational Mathematics (Harbrecht)
Project start 01.01.2017
Probable end 31.12.2019
Status Completed
Abstract

We propose to explore an unprecedented amount of molecular data (166B molecules) with quantum chemical precision. For this, chemically accurate and transferable machine learning property models of unprecedented computational efficiency will be developed using special purpose tailored training sets designed according to unified multilevel techniques (sparse grids plus combination rules). We will subsequently apply the method to iteratively optimize molecular property objective functions which enable the routine discovery of new molecules with pre-defined specific properties – in real time. The objective for this effort is twofold: We plan to (a) provide experimental chemists with a powerful computational tool to guide design, synthesis, and characterization efforts of new and interesting molecules, and (b) gain a better understanding of the nature, landscape, and relationships among chemical structure and properties throughout chemical space.

Keywords quantum chemistry, machine learning, molecular properties, chemical space, sparse grid combination technique
Financed by Swiss National Science Foundation (SNSF)

Published results ()

  ID Autor(en) Titel ISSN / ISBN Erschienen in Art der Publikation
4499677  Harbrecht, Helmut; Zaspel, Peter  On the algebraic construction of sparse multilevel approximations of elliptic tensor product problems  0885-7474 ; 1573-7691  Journal of scientific computing  Publication: JournalArticle (Originalarbeit in einer wissenschaftlichen Zeitschrift) 
   

MCSS v5.8 PRO. 0.716 sec, queries - 0.000 sec ©Universität Basel  |  Impressum   |    
14/08/2020