• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2023 Fiscal Year Research-status Report

Accelerating AFIR reaction path search using Neural Network Potentials

Research Project

Project/Area Number 23K13702
Research InstitutionHokkaido University

Principal Investigator

STAUB RUBEN・MORGAN・ADRIEN  北海道大学, 化学反応創成研究拠点, 特任助教 (20940274)

Project Period (FY) 2023-04-01 – 2026-03-31
KeywordsNN Potentials / Reaction Path Search / Machine Learning / Artificial Intelligence / Theoretical Chemistry / Kinetics simulation
Outline of Annual Research Achievements

While general-purpose Neural Network Potentials (NNP) can provide very accurate predictions at a much lower cost, these NNPs were found to suffer from robustness issues when applied to force-induced reaction path search. Therefore, combining them with approximate but robust models was demonstrated to produce combined models that are robust, fast and accurate. In particular, the semi-empirical xTB potential was found to yield an appropriate robustness/cost ratio to design combined models adapted for reaction path search.
Using these models, an automated framework was designed, implemented and tested for the AI-driven acceleration of reaction path search, by combining the Artificial Force Induced Reaction (AFIR) method with AI models based on NNPs. Combined with a newly designed training procedure, this recently implemented NNP-AFIR framework now achieves an effective few hundred times acceleration of traditional reaction path searches, with similar accuracy. This development now enables us to perform extensive reaction path searches on much larger systems, allowing to carefully study the influence of substituents on the chemical reactivity, instead of considering only the reaction centers.
As a consequence, this NNP-accelerated AFIR framework is being applied to study several chemical systems that were previously inaccessible.

Current Status of Research Progress
Current Status of Research Progress

2: Research has progressed on the whole more than it was originally planned.

Reason

An NNP-AFIR framework was implemented and deployed on the clusters of the host institute, using a dual CPU server (for DFT calculations) + GPU server (for Neural Network training) design. It appeared that using only Equilibrium States and Transition States, obtained during previous searches, provides enough diversity for training the NNP. The iterative learning scheme (with an improved sweep rehearsal mechanism) developed now leads to a ~500x acceleration compared to traditional DFT-based reaction path search. Thanks to this performance, the NNP-AFIR framework is now being applied on several chemical systems with up to 200+ atoms.

Strategy for Future Research Activity

A major focus will be the publication of the ongoing applications of the developed NNP-AFIR framework in the context of this project. In particular, the methodology of the NNP-AFIR method will be showcased in a study to solve the ongoing controversy on the Passerini reaction, which has been one of the earliest application of NNP-AFIR, despite its high sensitivity to the AFIR search options. As planned, efforts will be pursued to adapt and improve the NNP-AFIR framework for the current applications as well as the potential new collaborations. Especially, heterogeneous catalysis was recently identified as an application target that could greatly benefit from the NNP-AFIR approach.

Causes of Carryover

There are two pieces of equipment that are mainly required for this project, as written in the application: a GPU-enabled Linux laptop for easy debugging, and computational nodes (to be installed in clusters) for working on the development version. The price of both the GPU Linux laptop and a single cluster node was more than the amount allocated for FY2023.
The laptop was more urgent for helping to develop the iterative training process, so it was purchased first. However, the cluster node will be important for securing computational resources, by creating a private queue to quickly send small jobs, which is particularly relevant for working on the development version.
The cluster onto which this node will be installed is already available in the host institute, and an agreement is already in place with other groups in the institute to purchase in common to bargain with the vendor and obtain reduced prices. Therefore, the cluster node should now cost a bit less than 2M yen, which will be purchased in FY2024 thanks to the amount being carried over.

  • Research Products

    (6 results)

All 2024 2023

All Journal Article (1 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (5 results) (of which Invited: 1 results)

  • [Journal Article] Challenges for Kinetics Predictions via Neural Network Potentials: A Wilkinson’s Catalyst Case2023

    • Author(s)
      Staub Ruben、Gantzer Philippe、Harabuchi Yu、Maeda Satoshi、Varnek Alexandre
    • Journal Title

      Molecules

      Volume: 28 Pages: 4477~4477

    • DOI

      10.3390/molecules28114477

    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Presentation] Accelerating Reaction Path Search using Neural Network Potentials2024

    • Author(s)
      Ruben STAUB, Alexandre VARNEK
    • Organizer
      7th ICReDD International Symphosium
    • Invited
  • [Presentation] Accelerating Artificial Force Induced Reaction Path Search using Neural Network Potentials2023

    • Author(s)
      Ruben STAUB, Alexandre VARNEK
    • Organizer
      5th conference of Theory and Applications of Computational Chemistry (TACC)
  • [Presentation] Accelerating Artificial Force Induced Reaction Path Search using Neural Network Potentials2023

    • Author(s)
      Ruben STAUB, Philippe GANTZER, Yu HARABUCHI, Satoshi MAEDA, Alexandre VARNEK
    • Organizer
      6th ICReDD International Symphosium
  • [Presentation] Accelerating Artificial Force Induced Reaction Path Search using Neural Network Potentials2023

    • Author(s)
      Ruben STAUB, Philippe GANTZER, Yu HARABUCHI, Satoshi MAEDA, Alexandre VARNEK
    • Organizer
      9th Hokkaido University Cross-Departmental Symposium
  • [Presentation] Accelerating Artificial Force Induced Reaction Path Search using Neural Network Potentials2023

    • Author(s)
      Ruben STAUB, Philippe GANTZER, Yu HARABUCHI, Satoshi MAEDA, Alexandre VARNEK
    • Organizer
      8th Autumn School of Chemoinformatics in Nara

URL: 

Published: 2024-12-25  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi