Big Data for Computational Chemistry: Unified machine learning and sparse grid combination technique for quantum based molecular design

Research Project
|
01.01.2017
- 31.12.2019

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.

Funding

Big Data for Computational Chemistry: Unified machine learning and sparse grid combination technique for quantum based molecular design

SNF Projekt (GrantsTool), 01.2017-12.2019 (36)

PI : Harbrecht, Helmut.
CI : von Lilienfeld, Anatole.

Publications

Harbrecht, Helmut, Jakeman, John D. and Zaspel, Peter (2021) ‘Cholesky-based experimental design for Gaussian process and kernel-based emulation and calibration’, Communications in Computational Physics, 29(4), pp. 1152–1185. Available at: https://doi.org/10.4208/cicp.oa-2020-0060.

URLs

Harbrecht, Helmut and Multerer, Michael D. (2021) ‘A fast direct solver for nonlocal operators in wavelet coordinates’, Journal of computational physics, 428, p. 110056. Available at: https://doi.org/10.1016/j.jcp.2020.110056.

URLs

Harbrecht, Helmut and Zaspel, Peter (2019) ‘On the algebraic construction of sparse multilevel approximations of elliptic tensor product problems’, Journal of scientific computing, 78(2), pp. 1272–1290. Available at: https://doi.org/10.1007/s10915-018-0807-6.

URLs

Zaspel, Peter et al. (2019) ‘Boosting quantum machine learning models with multi-level combination technique: Pople diagrams revisited’, Journal of Chemical Theory and Computation, 15(3), pp. 1546–1559. Available at: https://doi.org/10.1021/acs.jctc.8b00832.

URLs

Big Data for Computational Chemistry: Unified machine learning and sparse grid combination technique for quantum based molecular design

Research Project
|
01.01.2017
- 31.12.2019

Funding

Big Data for Computational Chemistry: Unified machine learning and sparse grid combination technique for quantum based molecular design

SNF Projekt (GrantsTool), 01.2017-12.2019 (36)

PI : Harbrecht, Helmut.
CI : von Lilienfeld, Anatole.

Publications

Harbrecht, Helmut, Jakeman, John D. and Zaspel, Peter (2021) ‘Cholesky-based experimental design for Gaussian process and kernel-based emulation and calibration’, Communications in Computational Physics, 29(4), pp. 1152–1185. Available at: https://doi.org/10.4208/cicp.oa-2020-0060.

Harbrecht, Helmut and Multerer, Michael D. (2021) ‘A fast direct solver for nonlocal operators in wavelet coordinates’, Journal of computational physics, 428, p. 110056. Available at: https://doi.org/10.1016/j.jcp.2020.110056.

Harbrecht, Helmut and Zaspel, Peter (2019) ‘On the algebraic construction of sparse multilevel approximations of elliptic tensor product problems’, Journal of scientific computing, 78(2), pp. 1272–1290. Available at: https://doi.org/10.1007/s10915-018-0807-6.

Zaspel, Peter et al. (2019) ‘Boosting quantum machine learning models with multi-level combination technique: Pople diagrams revisited’, Journal of Chemical Theory and Computation, 15(3), pp. 1546–1559. Available at: https://doi.org/10.1021/acs.jctc.8b00832.

Members (4)

Helmut Harbrecht

Principal Investigator

Anatole von Lilienfeld

Co-Investigator

Bing Huang

Project Member

Peter Zaspel

Project Member

Research Groups

Computational Mathematics

Big Data for Computational Chemistry: Unified machine learning and sparse grid combination technique for quantum based molecular design

Research Project | 01.01.2017 - 31.12.2019

Funding

Big Data for Computational Chemistry: Unified machine learning and sparse grid combination technique for quantum based molecular design

SNF Projekt (GrantsTool), 01.2017-12.2019 (36)

PI : Harbrecht, Helmut.CI : von Lilienfeld, Anatole.

Publications

Harbrecht, Helmut, Jakeman, John D. and Zaspel, Peter (2021) ‘Cholesky-based experimental design for Gaussian process and kernel-based emulation and calibration’, Communications in Computational Physics, 29(4), pp. 1152–1185. Available at: https://doi.org/10.4208/cicp.oa-2020-0060.

Harbrecht, Helmut and Multerer, Michael D. (2021) ‘A fast direct solver for nonlocal operators in wavelet coordinates’, Journal of computational physics, 428, p. 110056. Available at: https://doi.org/10.1016/j.jcp.2020.110056.

Harbrecht, Helmut and Zaspel, Peter (2019) ‘On the algebraic construction of sparse multilevel approximations of elliptic tensor product problems’, Journal of scientific computing, 78(2), pp. 1272–1290. Available at: https://doi.org/10.1007/s10915-018-0807-6.

Zaspel, Peter et al. (2019) ‘Boosting quantum machine learning models with multi-level combination technique: Pople diagrams revisited’, Journal of Chemical Theory and Computation, 15(3), pp. 1546–1559. Available at: https://doi.org/10.1021/acs.jctc.8b00832.

Members (4)

Helmut Harbrecht

Principal Investigator

Anatole von Lilienfeld

Co-Investigator

Bing Huang

Project Member

Peter Zaspel

Project Member

Research Groups

Computational Mathematics

Research Project
|
01.01.2017
- 31.12.2019

PI : Harbrecht, Helmut.
CI : von Lilienfeld, Anatole.