Estimation of material distributions and energy conditions for chemical reactions using machine learning

2017 Fiscal Year Final Research Report

• Project/Area Number: 25730154
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Soft computing
• Research Institution: National Institute of Advanced Industrial Science and Technology
• Principal Investigator: Shiro Masanori 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究グループ付 (90357244)
• Project Period (FY): 2013-04-01 – 2018-03-31
• Keywords: 化学反応 / シミュレーション / モンテカルロ法 / 無機分子 / 逆問題 / 機械学習 / 低分子 / 生命発生

Outline of Final Research Achievements

Usually, quantum-mechanical calculations with heavy resources are necessary for the simulation of the chemical reactions even if for a small molecule. In this study, we expressed quantity of molecules and each of the energy of molecules with statistical distributions, and proposed a method by Monte Carlo simlation as the substitute for the quantum-mechanical based. We implemented our method partly used standard C++ language. Our method is not suitable for the reactions depends on the molecular structures in many of high polymers, but can get the most suitable result by the adjusted accuracy of the computer ability. We are now preparing to be able to use the program widely.

Free Research Field

非線形時系列解析、機械学習