Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 11 views

    Sebastian Dick Presentation

    Uploaded by

    Johnnypetra
    This document discusses combining density functional theory (DFT) calculations with machine learning to provide faster and more accurate simulations. It proposes training a neural network on the difference between lower-accuracy DFT methods and higher-level references to create machine-learned correcting functionals (MLCFs) that can improve the accuracy of DFT at a lower computational cost. Initial tests on water clusters show the MLCF approach reduces DFT errors in energies by an order of magnitude. The document outlines ongoing work to implement MLCFs in molecular dynamics simulations and release the methods in an open-source Python toolkit to make them broadly available.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Sebastian Dick Presentation

    Uploaded by

    Johnnypetra
    11 views20 pages
    This document discusses combining density functional theory (DFT) calculations with machine learning to provide faster and more accurate simulations. It proposes training a neural network on the difference between lower-accuracy DFT methods and higher-level references to create machine-learned correcting functionals (MLCFs) that can improve the accuracy of DFT at a lower computational cost. Initial tests on water clusters show the MLCF approach reduces DFT errors in energies by an order of magnitude. The document outlines ongoing work to implement MLCFs in molecular dynamics simulations and release the methods in an open-source Python toolkit to make them broadly available.

    Original Description:

    Presentation

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses combining density functional theory (DFT) calculations with machine learning to provide faster and more accurate simulations. It proposes training a neural network on the difference between lower-accuracy DFT methods and higher-level references to create machine-learned correcting functionals (MLCFs) that can improve the accuracy of DFT at a lower computational cost. Initial tests on water clusters show the MLCF approach reduces DFT errors in energies by an order of magnitude. The document outlines ongoing work to implement MLCFs in molecular dynamics simulations and release the methods in an open-source Python toolkit to make them broadly available.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    11 views20 pages

    Sebastian Dick Presentation

    Uploaded by

    Johnnypetra
    This document discusses combining density functional theory (DFT) calculations with machine learning to provide faster and more accurate simulations. It proposes training a neural network on the difference between lower-accuracy DFT methods and higher-level references to create machine-learned correcting functionals (MLCFs) that can improve the accuracy of DFT at a lower computational cost. Initial tests on water clusters show the MLCF approach reduces DFT errors in energies by an order of magnitude. The document outlines ongoing work to implement MLCFs in molecular dynamics simulations and release the methods in an open-source Python toolkit to make them broadly available.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 20

    Combining DFT and Machine Learning

    Towards faster and more accurate ab-initio calculations


    Sebastian Dick, Department of Physics and Astronomy, Stony Brook University
    Fernandez-Serra Group
    Jr. Researcher Award, 08/16/2018
    Introduction
    Simulations in Molecular Sciences

    ● Force Fields Energies,


    Atomic Forces,
    coordinates ● Density Functional Theory Stress,
    (DFT) Electron density,
    ● Quantum Chemistry Spectra, ...

    We use DFT because:


    ● Can scale to large systems sizes (100s to
    1000s of atoms) + Periodic boundary
    conditions
    → Condensed systems
    ● Non-empirical, hence unbiased
    ● Fully reactive

    3
    How does DFT work ?

    Quantum Hohenberg - Kohn


    Mechanics ?

    4
    How does DFT work ?

    Quantum Hohenberg - Kohn


    Mechanics

    5
    Jacob’s ladder
    ● A density functional approximation is uniquely defined by choosing
    ● Accuracy, Cost ↔ Locality

    PBE0,
    B3LYP Hybrid functionals, MP2, RPA ... What we would like
    to do

    TPSS meta-GGA
    Accuracy

    PBE, Generalized-Gradient What we end up


    BLYP Approximation (GGA) doing...

    PW92 Local Density Approximation (LDA)

    6
    Machine learning in Molecular Sciences

    Force Fields Electronic Structure

    Towards Exact Molecular Dynamics Simulations By-passing the Kohn-Sham equations


    with Machine-Learned Force Fields with machine learning
    Chmiela et al, arXiv:1802.09238 (2018) Brockerde et al., Nature Comm. 8 (2017)

    SchNet – A deep learning architecture Finding density functionals with machine learning
    for molecules and materials Snyder et al, Phys. Rev. Lett. 108 (2012)
    JCP 148 (2018), Schutt et al

    Generalized Neural-Network Representation of Semi-local machine-learned kinetic


    High-Dimensional Potential-Energy Surfaces energy density functional
    PRL 98 (2007), Behler, Parrinello with third-order gradients of electron density
    Seino et al, JCP 148 (2018)

    7
    Machine learning in Molecular Sciences

    Our idea: Machine Learned Correcting Functionals


    (MLCFs)
    Train a neural network on the difference in predictions of
    physical observables (E, F, ...) of a lower accuracy
    baseline method (GGA) and a higher level reference MLCF
    method (Hybrid DFT, Coupled Cluster, …)
    → get a higher accuracy at the cost of the baseline method

    Force Fields Electronic Structure

    Towards Exact Molecular Dynamics Simulations By-passing the Kohn-Sham equations


    with Machine-Learned Force Fields with machine learning
    Chmiela et al, arXiv:1802.09238 (2018) Brockerde et al., Nature Comm. 8 (2017)

    SchNet – A deep learning architecture Finding density functionals with machine learning
    for molecules and materials Snyder et al, Phys. Rev. Lett. 108 (2012)
    JCP 148 (2018), Schutt et al

    Generalized Neural-Network Representation of Semi-local machine-learned kinetic


    High-Dimensional Potential-Energy Surfaces energy density functional
    PRL 98 (2007), Behler, Parrinello with third-order gradients of electron density
    Seino et al, JCP 148 (2018)

    8
    Machine learned correcting
    functionals (MLCFs)
    Machine Learning

    Informed Machine Learning for Maximal Extrapolation


    Rather than provide all available (raw) data in an
    unbiased way, knowledge about the physical
    mechanisms involved is used to pre-process and
    select relevant data.
    Trained on a small representative dataset the
    model should generalize to unseen data.
    In particular, the model has to be valid for
    arbitrary system sizes.

    10
    Data

    Dataset: Water
    – Training: 640 Monomers, 1600 Dimers, 1200 Trimers
    – Testing: 160 Monomers, 400 Dimers, 300 Trimers, 50 Tetramers, 50 Pentamers, …


    Input: Expansion of electron density around each
    atom into basis functions:

    Electronic
    descriptors:
    Atomic species Atom index


    Targets: Difference between reference (MB-pol) and baseline (GGA + vdW)
    energies(/forces)

    11
    Architecture

    12
    Performance on water clusters
    2-body energy Molecules
    DFT DFT+MLCF DFT DFT+MLCF

    1 -4.2 -1.4 64.3 2.0


    2 -5.8 -1.3 42.5 3.4
    3 -14.8 0.6 31.9 2.3
    4 -31.2 -1.0 9.4 2.7
    5 -31.9 0.0 12.3 3.0
    8 -28.9 2.3 9.3 3.1
    16 -26.1 6.6 6.2 2.5
    Energies in meV/molecule

    3-body energy Hexamers

    Fritz, Fernandez-Serra, Soler, J. Chem. Phys.


    144, 224101 (2016), Supplementary
    Information

    13
    Correcting molecular dynamics simulations

    ● Ab initio molecular dynamics: Integrate the equations of motion


    with forces obtained from ab-intio calculations.
    ● GGA (DFT) is known to over-structure liquid water (peaks too high)
    ● Even though simulations not well converged yet (simulation time too
    short), MLCFs seem to correct this over-structuring

    Simulation of a box with periodic DFT


    boundary conditions containing Reference
    128 water molecules, with (MB-pol)
    Nose-Hoover DFT + MLCF
    Thermostat at 300 K

    14
    Using MLCFs to speed up MD calculations

    ● Start from very fast DFT calculation with very low accuracy (GGA, minimal
    basis set, coarse grid, relaxed convergence criteria)
    ● Large difference between baseline and reference → only approximate
    correction
    ● Solution: Every n-th MD step use reference method to calculate correction
    ● Speed-ups of up to a factor of 8 for water
    ● But: possible speed-up system dependent, careful validation necessary

    15
    Outlook
    Python toolkit
    * Implementation with C++ kernel and
    MPI/CUDA planned
    Electronic
    Structure code ** Uses GPUs through Tensorflow

    Import and preprocess


    electron density
    * Energy calculations,
    Structural relaxation,
    Molecular dynamics,
    ...
    Propose NN based on User can make
    Provided data adjustments

    Cross-validation and Final model: Atomic simulation


    training ASE Calculator Environment
    ** ** (ASE)

    Python toolkit
    17
    Timeline

    Timeline for 2018/2019:


    ● Sep – Dec:
    ● Implementation of basic Python toolkit, v0.1 on Github
    ● First publication on MLCFs
    ● Using MLCFs to study the solvation of NaCl in water (together with Alec Wills)
    ● Jan – Apr:
    ● Performance optimization (C++ and MPI/CUDA), v1.0 on Github
    ● MLCF accelerated simulations of water-metal interfaces

    ● May – Aug:
    ● MLCF accelerated simulations of water-metal interfaces
    ● MLCFs as an alternative to QM/MM? Implementation of QM/QM-MLCF algorithms.

    Plans for 2019/2020:


    ● Can ML be used to correct the self consistent electron density?
    (Possible collaboration with Alan Aspuru Guzik @ Toronto)
    ● Machine learned density functional kernels?
    ● Other semi-empirical methods for faster electronic sturcture calculations
    (Electron ‘force-field’, Collaboration with Jose Solers group @ Madrid)
    18
    Thank you!
    Using MLCFs to speed up MD calculations

    Replace QM/MM with QM/QM-MLCF:

    MM QM-MLCF

    ?
    QM QM

    20

    You might also like