請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96262完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 趙聖德 | zh_TW |
| dc.contributor.advisor | Sheng-Der Chao | en |
| dc.contributor.author | 楊昇翰 | zh_TW |
| dc.contributor.author | Sheng-Han Yang | en |
| dc.date.accessioned | 2024-11-28T16:27:49Z | - |
| dc.date.available | 2024-11-29 | - |
| dc.date.copyright | 2024-11-28 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-11-07 | - |
| dc.identifier.citation | 1.Chao, S.W., A.H.T. Li, and S.D. Chao, Molecular Dynamics Simulations of Fluid Methane Properties Using Ab Initio Intermolecular Interaction Potentials. Journal of Computational Chemistry, 2009. 30(12): p. 1839-1849.
2.Chung, Y.H., A.H.T. Li, and S.D. Chao, Computer Simulation of Trifluoromethane Properties with Ab Initio Force Field. Journal of Computational Chemistry, 2011. 32(11): p. 2414-2421. 3.Wang, S.B., A.H.T. Li, and S.D. Chao, Simulations of dimethyl ether with a new ab initio force field. Abstracts of Papers of the American Chemical Society, 2012. 243: p. 1. 4.Yin, C.C., A.H.T. Li, and S.D. Chao, Liquid chloroform structure from computer simulation with a full ab initio intermolecular interaction potential. Journal of Chemical Physics, 2013. 139(19): p. 7. 5.Li, A.H.T. and S.D. Chao, A Refined Intermolecular Interaction Potential for Methane: Spectral Analysis and Molecular Dynamics Simulations. Journal of the Chinese Chemical Society, 2016. 63(3): p. 282-289. 6.Fan, Z.X. and S.D. Chao, A Machine Learning Force Field for Bio-Macromolecular Modeling Based on Quantum Chemistry-Calculated Interaction Energy Datasets. Bioengineering-Basel, 2024. 11(1): p. 17. 7.Behler, J., Perspective: Machine learning potentials for atomistic simulations. Journal of Chemical Physics, 2016. 145(17): p. 9. 8.Behler, J., Constructing high-dimensional neural network potentials: A tutorial review. International Journal of Quantum Chemistry, 2015. 115(16): p. 1032-1050. 9.Wu, X.J., et al., A survey of human-in-the-loop for machine learning. Future Generation Computer Systems-the International Journal of Escience, 2022. 135: p. 364-381. 10.Tyagi, O.S., H.S. Bisht, and A.K. Chatterjee, Phase transition, conformational disorder, and chain packing in crystalline long-chain symmetrical alkyl ethers and symmetrical alkenes. Journal of Physical Chemistry B, 2004. 108(9): p. 3010-3016. 11.Hobza, P. and R. Zahradník, Intermolecular Complexes: The Role of Van Der Waals Systems in Physical Chemistry and in the Biodisciplines. 1988: Elsevier. 12.Jeffrey, G.A. and W. Saenger, Hydrogen Bonding in Biological Structures. 1991: Springer Berlin Heidelberg. 13.Stone, A.J., The Theory of Intermolecular Forces. 2013: OUP Oxford. 14.Dunning, T.H., A road map for the calculation of molecular binding energies. Journal of Physical Chemistry A, 2000. 104(40): p. 9062-9080. 15.Grimme, S., et al., A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu. Journal of Chemical Physics, 2010. 132(15): p. 19. 16.Raghavachari, K., et al., A fifth-order perturbation comparison of electron correlation theories (Reprinted from Chemical Physics Letters). Chemical Physics Letters, 2013. 589: p. 37-40. 17.Simon, S., M. Duran, and J.J. Dannenberg, How does basis set superposition error change the potential surfaces for hydrogen bonded dimers? Journal of Chemical Physics, 1996. 105(24): p. 11024-11031. 18.Boys, S.F. and F. Bernardi, The calculation of small molecular interactions by the differences of separate total energies. Some procedures with reduced errors (Reprinted from Molecular Physics, vol 19, pg 553-566, 1970). Molecular Physics, 2002. 100(1): p. 65-73. 19.Jeziorski, B., R. Moszynski, and K. Szalewicz, Perturbation Theory Approach to Intermolecular Potential Energy Surfaces of van der Waals Complexes. Chemical Reviews, 1994. 94(7): p. 1887-1930. 20.Goodfellow, I., Y. Bengio, and A. Courville, Deep Learning. 2016: MIT Press. 21.Sutton, R.S. and A.G. Barto, Reinforcement Learning, second edition: An Introduction. 2018: MIT Press. 22.Pastorczak, E. and C. Corminboeuf, Perspective: Found in translation: Quantum chemical tools for grasping non-covalent interactions. Journal of Chemical Physics, 2017. 146(12): p. 13. 23.Hohenstein, E.G. and C.D. Sherrill, Wavefunction methods for noncovalent interactions. Wiley Interdisciplinary Reviews-Computational Molecular Science, 2012. 2(2): p. 304-326. 24.Haykin, S.S., Neural Networks and Learning Machines. Pearson International Edition. 2009: Pearson. 25.Parker, T.M., et al., Levels of symmetry adapted perturbation theory (SAPT). I. Efficiency and performance for interaction energies. Journal of Chemical Physics, 2014. 140(9): p. 16. 26.Hobza, P., Calculations on Noncovalent Interactions and Databases of Benchmark Interaction Energies. Accounts of Chemical Research, 2012. 45(4): p. 663-672. 27.Marshall, M.S., L.A. Burns, and C.D. Sherrill, Basis set convergence of the coupled-cluster correction, δMP2CCSD(T): Best practices for benchmarking non-covalent interactions and the attendant revision of the S22, NBC10, HBC6, and HSG databases. Journal of Chemical Physics, 2011. 135(19): p. 10. 28.Burns, L.A., et al., The BioFragment Database (BFDb): An open-data platform for computational chemistry analysis of noncovalent interactions. Journal of Chemical Physics, 2017. 147(16): p. 15. 29.Villot, C. and K.U. Lao, Ab initio dispersion potentials based on physics-based functional forms with machine learning. The Journal of Chemical Physics, 2024. 160(18). 30.Smith, D.G.A., et al., PSI4 1.4: Open-source software for high-throughput quantum chemistry. Journal of Chemical Physics, 2020. 152(18): p. 21. 31.Chang, Y.M., Y.S. Wang, and S.D. Chao, A minimum quantum chemistry CCSD(T)/CBS dataset of dimeric interaction energies for small organic functional groups. Journal of Chemical Physics, 2020. 153(15): p. 13. 32.Huang, H.H., Y.S. Wang, and S.D. Chao, A Minimum Quantum Chemistry CCSD(T)/CBS Data Set of Dimeric Interaction Energies for Small Organic Functional Groups: Heterodimers. Acs Omega, 2022. 7(23): p. 20059-20080. 33.Donchev, A.G., et al., Quantum chemical benchmark databases of gold-standard dimer interaction energies. Scientific Data, 2021. 8(1): p. 9. 34.Glick, Z.L., et al., AP-Net: An atomic-pairwise neural network for smooth and transferable interaction potentials. Journal of Chemical Physics, 2020. 153(4): p. 14. 35.Behler, J., Atom-centered symmetry functions for constructing high-dimensional neural network potentials. Journal of Chemical Physics, 2011. 134(7): p. 13. 36.Harder, E., et al., Atomic level anisotropy in the electrostatic modeling of lone pairs for a polarizable force field based on the classical Drude oscillator. Journal of Chemical Theory and Computation, 2006. 2(6): p. 1587-1597. 37.Millot, C., et al., Revised anisotropic site potentials for the water dimer and calculated properties. Journal of Physical Chemistry A, 1998. 102(4): p. 754-770. 38.羅卓軒, 基於官能基分類量子化學數據集應用於機器學習預測分子間相互作用能, in 應用力學研究所. 2022, 國立臺灣大學. p. 1-88. 39.Weininger, D., SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. Journal of Chemical Information and Computer Sciences, 1988. 28(1): p. 31-36. 40.林泳廷, 以非監督式機器學習模型預測二聚體分子之總能量曲線, in 應用力學研究所. 2023, 國立臺灣大學. p. 1-78. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96262 | - |
| dc.description.abstract | 準確的非共價相互作用對於超分子化學、材料科學和生物化學等領域皆是研究的重點，而過去實驗室也針對不同的二聚體分子進行大量的相互作用能計算，並建立了SOFG-31資料集，而為了應對廣泛的分子系統，我們需要建構更大的資料集。因此在本研究第一部分，我們建立了DES133資料集，包含了39220筆非共價相互作用能與其結合能量（靜電、交換、誘導和色散），其中涵蓋1961個獨特的二聚體，並使用高階對稱適應微擾理論SAPT銅(SAPT2/jVTZ)與銀(SAPT2+/aVDZ)標準進行計算，最後根據SAPT的計算結果進行能量分析。此外，基於先前的機器學習力場技術(AP-Net)的開發，並在先前的研究中透過特定的方式以數十筆的資料來預測數百筆的資料。因此，在研究的第二部分，我們使用此方法透過DES133資料集中數百筆同源二聚體分子作為訓練集，以預測相同資料集中的數千筆異源二聚體。結果顯示，整體的預測誤差低於化學精度1kcal/mol，僅用特定二聚體分子作為訓練就可重現各種二聚體相互作用能，因此透過此種方法，我們就能以更少的時間與計算成本建構一個機器學習力場，以應用於各種分子間勢能表面。 | zh_TW |
| dc.description.abstract | Accurate non-covalent interactions are crucial for research in fields such as supramolecular chemistry, materials science, and biochemistry. Our laboratory has previously conducted extensive interaction energy calculations for various dimer molecules, resulting in the establishment of the SOFG-31 datasets. However, to address a wider range of molecular systems, a larger dataset is necessary. Therefore, in the first part of this study, we have developed the DES133 dataset, which includes 39220 noncovalent interaction energies and their binding energy components (electrostatic, exchange, induction, and dispersion). This dataset includes 1961 unique dimers and was calculated using the higher-order symmetry-adapted perturbation theory (SAPT) bronze (SAPT2/jVTZ) and silver (SAPT2+/aVDZ) standards, followed by energy analysis based on the SAPT results. Furthermore, based on the preceding development of Machine Learning Force Field Technology (AP-Net) and the preceding study, we predicted a multitude of data points, ranging from hundreds to tens, in a specific manner. Consequently, in the second part of the study, this method was employed to predict thousands of heterodimers in the same dataset, utilising hundreds of homodimers in the DES133 dataset as a training set. The results demonstrate that the overall prediction error is less than the chemical accuracy of 1 kcal/mol, and a range of dimer interaction energies can be reproduced by utilising a single specific dimer molecule as the training set. Consequently, this approach enables the construction of a machine-learning force field for diverse intermolecular potential energy surfaces in a more time-efficient and cost-effective manner. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-11-28T16:27:49Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-11-28T16:27:49Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員會審定書 #
致謝 i 摘要 ii ABSTRACT iii 目次 iv 圖次 vii 表次 ix 第一章 緒論 1 1.1 研究動機 1 1.2 分子間作用力介紹 2 1.3 計算分子間作用力方法介紹 3 1.4 機器學習介紹 4 第二章 基本理論 5 2.1 量子力學理論 5 2.1.1 薛丁格方程式(Schrödinger equation) 5 2.1.2 波恩-歐本海默近似法(Born-Oppenheimer Approximation) 7 2.2 Ab initio分子軌域理論 9 2.3.1 微擾理論(Møller-Plesset perturbation theory) 9 2.2.2 對稱適應微擾理論(Symmetry-Adapted Perturbation Theory) 10 2.2.3 耦合簇理論(Coupled Cluster method) 12 2.3 機器學習基本理論 14 2.3.1 神經網路 14 2.3.2 激活函數(activation function) 16 2.3.3 優化器(Optimizer) 18 第三章 計算方法 21 3.1 資料集計算方法 21 3.1.1 對稱性匹配微擾理論的效率與準確性 21 3.1.2 計算流程 25 3.1.3 計算細節 26 3.1.4 資料集的介紹 26 3.1.4.1 SOFG-31資料集 26 3.1.4.2 SAPT10K 資料集 27 3.1.4.3 DES370K 資料集 28 3.2 機器學習方法 30 3.2.1 Atom-pairwise neural network(AP-Net)介紹 30 3.2.2 以SOFG-31同源二聚體平衡點能量預測SOFG-31異源二聚體之平衡點能量 32 3.2.3 以SOFG-31同源二聚體能量曲線預測SOFG-31異源二聚體之能量曲線 33 第四章 計算結果與討論 34 4.1 DES133資料集 34 4.1.1 資料集之分子分類 34 4.1.2 SAPT分析與準確性 36 4.1.3 能量曲線計算結果 38 4.1.4 能量資料總分析 41 4.2 機器學習訓練與測試結果 42 4.2.1 神經網路超參數選擇 42 4.2.2 以平衡同源二聚體分子交互作用能作為訓練集預測平衡異源二聚體交互作用能 42 4.2.3 以同源二聚體小分子能量曲線作為訓練集預測同源二聚體大分子能量曲線 50 4.2.4 以同源二聚體能量曲線作為訓練集預測異源二聚體能量曲線 54 4.2.5 以SAPT銀標準進行訓練及預測 58 第五章 結論與未來展望 59 5.1 結論 59 5.2 未來展望 60 參考文獻 61 附錄A 64 附錄B 78 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 分子結合能、機器學習力場 | zh_TW |
| dc.subject | 分子結合能 | zh_TW |
| dc.subject | 非共價相互做用 | zh_TW |
| dc.subject | 從頭計算方法 | zh_TW |
| dc.subject | 對稱適應微擾理論 | zh_TW |
| dc.subject | Noncovalent interaction | en |
| dc.subject | Machine learning force field | en |
| dc.subject | Molecular binding | en |
| dc.subject | Ab-initio methods | en |
| dc.subject | Symmetry-adapted perturbation theory | en |
| dc.title | 建立量子化學交互作用能資料集應用於機器學習勢能 | zh_TW |
| dc.title | Constructing quantum chemical interaction energy dataset for machine learning potential | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-1 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 包淳偉;游琇伃;李奕霈;楊珮芸 | zh_TW |
| dc.contributor.oralexamcommittee | Chun-Wei Pao;Hsiu-Yu Yu;Yi-Pei Li;Pei-Yun Yang | en |
| dc.subject.keyword | 非共價相互做用,對稱適應微擾理論,從頭計算方法,分子結合能,分子結合能、機器學習力場, | zh_TW |
| dc.subject.keyword | Noncovalent interaction,Symmetry-adapted perturbation theory,Ab-initio methods,Molecular binding,Machine learning force field, | en |
| dc.relation.page | 84 | - |
| dc.identifier.doi | 10.6342/NTU202404547 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2024-11-07 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 應用力學研究所 | - |
| dc.date.embargo-lift | 2027-12-01 | - |
| 顯示於系所單位： | 應用力學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-1.pdf 未授權公開取用 | 3.77 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。