鋰離子電池在現代社會中扮演著不可或缺的角色。本研究旨在開發新型鋰離子電池的電解液溶劑分子，並利用決策樹演算法和第一原理計算來幫助我們選擇對目標性質有預期影響的子結構，提供分子設計的方向。
在本研究中，我將研究分為兩個階段進行。在第一階段，我們著重於電解液溶劑分子的電化學穩定性窗口（Electrochemical stability window, ESW）。還原電位（Reduction potential, RP）和氧化電位（Oxidation potential, OP）決定了電解液在電池中的ESW，理想的電解液溶劑分子應具有較高的OP和較低的RP。首先，我使用MP資料集訓練機器學習模型中的決策樹，以找出哪些特徵對於預測RP和OP具有較高的重要性。我們期望在設計的電解液溶劑分子中添加特定的子結構，或選用具有特定子結構的分子時，能夠對所設計的電解液溶劑分子的RP和OP產生預期的影響。基於以MP資料集訓練決策樹的結果顯示，具有特徵1850 'COC' 的分子在提升OP和降低RP方面表現理想。此外，尚未發現具備超過碳酸乙烯酯（Ethylene Carbonate, EC）氧化電位或低於EC還原電位潛力的子結構，這也確認了EC的優越性。值得注意的是，EC正好擁有 'COC' 子結構。因此，我們希望設計的分子能夠具備EC有的特徵之一，即1850的 'COC' 子結構。
接續第一階段，即使我們更換多種演算法來求得特徵重要性，效果也遠不及使用不同資料集所能獲得的多樣與可靠。因此，我們使用了第二組資料集，即PubChemQC資料集，來訓練隨機森林模型。結果顯示未能找到同時在提升OP和降低RP方面表現理想的子結構，並且發現位元碰撞問題隨著資料量的增加變得更加嚴重。
在研究的第二階段，我們承接EC本質上相較於大多分子已經具備較寬廣ESW的觀點。在鋰離子電池的充放電過程中，電解液中的環型碳酸酯溶劑EC因為其偶極矩較強而相較於線型碳酸酯會優先溶解鋰鹽，傾向與鋰離子形成Li+(EC)4的複合物，導致RP上升，從而減小ESW。從能階角度來看，溶劑化會導致EC的最高佔據分子軌域（HOMO）和最低未佔據分子軌域（LUMO）下降，尤其是LUMO的下降進一步確認了溶劑化會減少溶劑分子的還原穩定性。我們透過設置特定的條件篩選MP資料集內的分子，並對這些分子與它們和鋰離子所形成的複合物進行HOMO與LUMO的計算，期望能歸納出哪些特徵影響能階下降。這些特徵可能是分子性質或分子結構，例如有文獻提及能階下降程度與反應的溶劑化能量存在相關性。
首先，我們計算了最終篩選出的21種分子的能階下降幅度。由於分子在溶劑化過程中會面臨能階下降的問題，我們希望找到的是LUMO下降幅度較小的特徵，以便在溶劑化後，分子仍能保持相對較好的穩定性。結果顯示，在LUMO能階下降幅度較小的6個分子中，有5個含有氮原子。透過對這些分子的能階可視化和Mulliken電荷分析，我們發現HOMO軌域通常集中於Mulliken電荷為負且電負度較高的原子周圍，而LUMO軌域則集中於Mulliken電荷為正且電負度較低的原子一側。此外，我們觀察到，分子的偶極矩愈高時，LUMO的下降幅度愈小，降低了分子被還原的可能性。因此，我們認為，溶劑分子中具有較大電負度差異的原子會影響分子的偶極矩，是導致LUMO下降幅度的關鍵因素。
本研究透過決策樹演算法和第一原理計算，找出了能影響電化學穩定性窗口或HOMO與LUMO下降幅度的關鍵子結構。最終，我們希望這些發現能為開發新型鋰離子電池電解液溶劑分子提供一種創新且可行的分子設計方法。

This study aims to develop new electrolyte solvent molecules by using Decision Trees algorithms and First-Principles calculation to identify substructures expected to influence the target properties, thereby guiding molecular design.
In the first phase, our Decision Trees model, trained on the MP dataset, identified that molecules with the 'COC' substructure statistically effectively enhance oxidation potential (OP) and reduce reduction potential (RP).
Subsequently, we trained a Random Forests on the PubChemQC dataset. The results showed that no substructure excels in both enhancing OP and reducing RP. Additionally, as the dataset size increased, the issue of bit confusion became more severe, affecting the interpretability of FCFPNUM.
A comparison of the top fifteen important substructures from the MP and PubChemQC datasets revealed that differences in potential distribution across datasets can lead to varying feature importance rankings.
In the second phase, we calculated the extent of HOMO and LUMO reduction for 21 selected molecules. Among the six molecules with the smallest LUMO reduction, five contained nitrogen atoms. Visualization energy levels and Mulliken charge analysis revealed that HOMO orbitals are typically concentrated around atoms with negative Mulliken charges and higher electronegativity, while LUMO orbitals are localized on atoms with positive Mulliken charges and lower electronegativity. Moreover, we observed that as the dipole moment of a molecule increases, the LUMO reduction decreases. Therefore, we conclude that the presence of atoms with significant differences in electronegativity within a solvent molecule influences its dipole moment, which is a key factor in determining the extent of LUMO reduction.

1.Ming Chen, Jinkai Zhang, Xiangyu Ji, Jiaping Fu, and Guang Feng, Progress on predicting the electrochemical stability window of electrolytes. Current Opinion in Electrochemistry, 2022. 34.
2.Xiang Chen, Nan Yao, Bo-Shen Zeng, and Qiang Zhang, Ion–solvent chemistry in lithium battery electrolytes: From mono-solvent to multi-solvent complexes. Fundamental Research, 2021. 1(4): p. 393-398.
3.Yunxian Qian, Shiguang Hu, Xianshuai Zou, Zhaohui Deng, Yuqun Xu, Zongze Cao, Yuanyuan Kang, Yuanfu Deng, Qiao Shi, Kang Xu, and Yonghong Deng, How electrolyte additives work in Li-ion batteries. Energy Storage Materials, 2019. 20: p. 208-215.
4.S. Kazemiabnavi, Z. Zhang, K. Thornton, and S. Banerjee, Electrochemical Stability Window of Imidazolium-Based Ionic Liquids as Electrolytes for Lithium Batteries. J Phys Chem B, 2016. 120(25): p. 5691-702.
5.N. Shao, X. G. Sun, S. Dai, and D. E. Jiang, Electrochemical windows of sulfone-based electrolytes for high-voltage Li-ion batteries. J Phys Chem B, 2011. 115(42): p. 12120-12125.
6.Shyue Ping Ong, Oliviero Andreussi, Yabi Wu, Nicola Marzari, and Gerbrand Ceder, Electrochemical Windows of Room-Temperature Ionic Liquids from Molecular Dynamics and Density Functional Theory Calculations. Chemistry of Materials, 2011. 23(11): p. 2979-2986.
7.M. Shakourian-Fard, G. Kamath, and S. K. Sankaranarayanan, Evaluating the Free Energies of Solvation and Electronic Structures of Lithium-Ion Battery Electrolytes. Chemphyschem, 2016. 17(18): p. 2916-2930.
8.Narendra Kumar and Jorge M. Seminario, Lithium-Ion Model Behavior in an Ethylene Carbonate Electrolyte Using Molecular Dynamics. The Journal of Physical Chemistry C, 2016. 120(30): p. 16322-16332.
9.Jiamei Yu, Perla B. Balbuena, Joanne Budzien, and Kevin Leung, Hybrid DFT Functional-Based Static and Molecular Dynamics Studies of Excess Electron in Liquid Ethylene Carbonate. Journal of The Electrochemical Society, 2011. 158(4).
10.Mahesh Datt Bhatt, Maenghyo Cho, and Kyeongjae Cho, Conduction of Li+ cations in ethylene carbonate (EC) and propylene carbonate (PC): comparative studies using density functional theory. Journal of Solid State Electrochemistry, 2011. 16(2): p. 435-441.
11.Mahesh Datt Bhatt, Maenghyo Cho, and Kyeongjae Cho, Interaction of Li+ ions with ethylene carbonate (EC): Density functional theory calculations. Applied Surface Science, 2010. 257(5): p. 1463-1468.
12.吳明修, 運用機器學習設計鋰電池電解液分子/Electrolyte molecule design by using machine learning, in 材料科學及工程學系. 2020, 國立成功大學. p. 1-81.
13.M. Nakata, T. Shimazaki, M. Hashimoto, and T. Maeda, PubChemQC PM6: Data Sets of 221 Million Molecules with Optimized Molecular Geometries and Electronic Properties. J Chem Inf Model, 2020. 60(12): p. 5891-5899.
14.Jerome Friedman Leo Breiman, R.A. Olshen, and Charles J. Stone, Classification and Regression Trees. 1984. 368.
15.Leo Breiman, Random forests. Machine learning, 2001. 45: p. 5-32.
16.David Rogers and Mathew Hahn, Extended-Connectivity Fingerprints. Journal of Chemical Information and Modeling, 2010. 50(5): p. 742-754.
17.Chemaxon. Extended Connectivity Fingerprint ECFP. Available from: https://docs.chemaxon.com/display/docs/extended-connectivity-fingerprint-ecfp.md.
18.Greg Landrum, Rdkit documentation. Release, 2013. 1(1-79): p. 4.
19.M. J. Frisch, G. W. Trucks, H. B. Schlegel, G. E. Scuseria, M. A. Robb, J. R. Cheeseman, G. Scalmani, V. Barone, G. A. Petersson, H. Nakatsuji, X. Li, M. Caricato, A. V. Marenich, J. Bloino, B. G. Janesko, R. Gomperts, B. Mennucci, H. P. Hratchian, J. V. Ortiz, A. F. Izmaylov, J. L. Sonnenberg, Williams, F. Ding, F. Lipparini, F. Egidi, J. Goings, B. Peng, A. Petrone, T. Henderson, D. Ranasinghe, V. G. Zakrzewski, J. Gao, N. Rega, G. Zheng, W. Liang, M. Hada, M. Ehara, K. Toyota, R. Fukuda, J. Hasegawa, M. Ishida, T. Nakajima, Y. Honda, O. Kitao, H. Nakai, T. Vreven, K. Throssell, J. A. Montgomery Jr., J. E. Peralta, F. Ogliaro, M. J. Bearpark, J. J. Heyd, E. N. Brothers, K. N. Kudin, V. N. Staroverov, T. A. Keith, R. Kobayashi, J. Normand, K. Raghavachari, A. P. Rendell, J. C. Burant, S. S. Iyengar, J. Tomasi, M. Cossi, J. M. Millam, M. Klene, C. Adamo, R. Cammi, J. W. Ochterski, R. L. Martin, K. Morokuma, O. Farkas, J. B. Foresman, and D. J. Fox, Gaussian 16 Rev. C.01. 2016: Wallingford, CT.
20.Marcus D Hanwell, Donald E Curtis, David C Lonie, Tim Vandermeersch, Eva Zurek, and Geoffrey R Hutchison, Avogadro: an advanced semantic chemical editor, visualization, and analysis platform. Journal of cheminformatics, 2012. 4: p. 1-17.
21.陳祐頎、吳昱賢、張家欽, 鋰離子電池電解質─鋰離子傳遞的橋梁, in 科學發展月刊. 2019. p. 16-20.
22.David S. Hall, Julian Self, and J. R. Dahn, Dielectric Constants for Quantum Chemistry and Li-Ion Batteries: Solvent Blends of Ethylene Carbonate and Ethyl Methyl Carbonate. The Journal of Physical Chemistry C, 2015. 119(39): p. 22322-22330.
23.Pallavi Verma, Pascal Maire, and Petr Novák, A review of the features and analyses of the solid electrolyte interphase in Li-ion batteries. Electrochimica Acta, 2010. 55(22): p. 6332-6341.
24.M. Shakourian-Fard, G. Kamath, and S. K. Sankaranarayanan, Evaluating the Free Energies of Solvation and Electronic Structures of Lithium-Ion Battery Electrolytes. Chemphyschem, 2016. 17(18): p. 2916-30.
25.X. Bogle, R. Vazquez, S. Greenbaum, Av Cresce, and K. Xu, Understanding Li(+)-Solvent Interaction in Nonaqueous Carbonate Electrolytes with (17)O NMR. J Phys Chem Lett, 2013. 4(10): p. 1664-8.
26.L. D. Gibson, J. Pfaendtner, and C. J. Mundy, Probing the thermodynamics and kinetics of ethylene carbonate reduction at the electrode-electrolyte interface with molecular simulations. J Chem Phys, 2021. 155(20): p. 204703.
27.A. Eilmes, P. Kubisiak, and P. Wrobel, Explicit and Hybrid Solvent Models for Estimates of Parameters Relevant to the Reduction Potential of Ethylene Carbonate. Int J Mol Sci, 2022. 23(24).
28.Gaël Varoquaux Fabian Pedregosa, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, Édouard Duchesnay, Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 2011. 12(85): p. 2825−2830.
29.Hugh A. Chipman, Edward I. George, and Robert E. McCulloch, Bayesian CART Model Search. Journal of the American Statistical Association, 2012. 93(443): p. 935-948.
30.Bani K. Mallick and Adrian F. M. Smith David G. T. Denison, A Bayesian CART algorithm. Biometrika, 1998. 85(2): p. 363-377.
31.Scott Lundberg, A unified approach to interpreting model predictions. arXiv preprint arXiv:1705.07874, 2017.
32.Lloyd S Shapley, A value for n-person games. Contributions to the Theory of Games, 1953. 2.
33.John Mingers, An Empirical Comparison of Pruning Methods for Decision Tree Induction. Machine Learning, 1989. 4: p. 227-243.
34.Indivar Mishra Soham Pathak, Aleena Swetapadma, An Assessment of Decision Tree based Classification and Regression Algorithms, in 2018 3rd International Conference on Inventive Computation Technologies (ICICT). 2018, IEEE: Coimbatore, India.
35.Thomas G Dietterich. Ensemble methods in machine learning. in International workshop on multiple classifier systems. 2000. Springer.
36.David Weininger, 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.
37.Arthur Weininger David Weininger, and Joseph L. Weininger, SMILES. 2. Algorithm for generation of unique SMILES notation. Journal of Chemical Information and Modeling, 1989. 29(2): p. 97-101.
38.Thomas MacDougall, Reduced Collision Fingerprints and Pairwise Molecular Comparisons for Explainable Property Prediction Using Deep Learning, in Maître ès sciences. 2021, Université de Montréal.
39.H. L. Morgan, The Generation of a Unique Machine Description for Chemical Structures-A Technique Developed at Chemical Abstracts Service. Journal of Chemical Documentation, 1965. 5(2): p. 107-113.
40.Richard L. Apodaca. Computing Extended Connectivity Fingerprints. 2019; Available from: https://depth-first.com/articles/2019/01/11/extended-connectivity-fingerprints/.
41.P. Hohenberg and W. Kohn, Inhomogeneous Electron Gas. Physical Review, 1964. 136(3B): p. B864-B871.
42.W. Kohn and L. J. Sham, Self-Consistent Equations Including Exchange and Correlation Effects. Physical Review, 1965. 140(4A): p. A1133-A1138.
43.J. P. Perdew and W. Yue, Accurate and simple density functional for the electronic exchange energy: Generalized gradient approximation. Phys Rev B Condens Matter, 1986. 33(12): p. 8800-8802.
44.Axel D. Becke, Density-functional thermochemistry. II. The effect of the Perdew–Wang generalized-gradient correlation correction. The Journal of Chemical Physics, 1992. 97(12): p. 9173-9177.
45.Kieron Burke John P. Perdew, and Matthias Ernzerhof, Generalized Gradient Approximation Made Simple. Phys. Rev. Lett., 1996. 77.
46.Axel D Beck, Density-functional thermochemistry. III. The role of exact exchange. J. Chem. Phys, 1993. 98(7): p. 5648-5652.
47.S. F. Boys, Electronic wave functions - I. A general method of calculation for the stationary states of any molecular system. 1950. 200(1063).