Similar articles

Abstract: Calculating the inter-layer ion diffusion barrier, a crucial metric for evaluating the rate performance of 2D electrode materials, is time-consuming using the transition state search approach. A novel electrostatic potential distribution image (EPDI) transfer learning method has been proposed to efficiently and accurately predict the lithium diffusion barriers on metal element-doped transition metal dichalcogenide (TMD) surfaces. Through the analysis of the mean electrostatic potential (MEP) around binding sites, a positive correlation between binding energy and MEP in VIB-TMDs was identified. Subsequently, transfer learning techniques were used to develop a DenseNet121-TL model for establishing a more accurate mapping between the binding energy and electrostatic potential distribution. Trained on training sets containing 33% and 50% transition state search calculation results, which save 66% and 50% of the calculation time, respectively, the model achieves accurate predictions of the saddle point binding energy with mean absolute errors (MAEs) of 0.0444 and 0.0287 eV on the testing set. Based on the prediction of saddle point binding energies, we obtained a diffusion minimum energy profile with an MAE of 0.0235 eV. Furthermore, by analyzing the diffusion data, we observed that the diffusion barrier was lowered by 10% on V-doped TiS₂ compared to the stoichiometric surface. Our findings are expected to provide new insights for the high-throughput calculation of ion diffusion on 2D materials.

基于静电势分布图像迁移学习的过渡金属硫族化物表面锂扩散势垒高精度预测方法

[1]AhmedM, LiY, ChenWC, et al., 2020. Diffusion barrier prediction of graphene and boron nitride for copper interconnects by deep learning. IEEE Access, 8:210542-210549.

[2]BahariY, MortazaviB, RajabpourA, et al., 2021. Application of two-dimensional materials as anodes for rechargeable metal-ion batteries: a comprehensive perspective from density functional theory simulations. Energy Storage Materials, 35:203-282.

[3]BlöchlPE, 1994. Projector augmented-wave method. Physical Review B, 50(24):17953-17979.

[4]ChaneyG, IbrahimA, ErsanF, et al., 2021. Comprehensive study of lithium adsorption and diffusion on janus Mo/WXY (X, Y=S, Se, Te) using first-principles and machine learning approaches. ACS Applied Materials & Interfaces, 13(30):36388-36406.

[5]ChangJH, JørgensenPB, LoftagerS, et al., 2021. On-the-fly assessment of diffusion barriers of disordered transition metal oxyfluorides using local descriptors. Electrochimica Acta, 388:138551.

[6]ChenC, YeWK, ZuoYX, et al., 2019. Graph networks as a universal machine learning framework for molecules and crystals. Chemistry of Materials, 31(9):3564-3572.

[7]DasS, PeguH, SahuKK, et al., 2020. 19-machine learning in materials modeling—fundamentals and the opportunities in 2D materials. In: Yang EH, Datta D, Ding JJ (Eds.), Synthesis, Modeling, and Characterization of 2D Materials, and Their Heterostructures. Elsevier, p.445-468.

[8]DongXC, LiHW, JiangZT, et al., 2021. 3D deep learning enables accurate layer mapping of 2D materials. ACS Nano, 15(2):3139-3151.

[9]DongY, WuCH, ZhangC, et al., 2019. Bandgap prediction by deep learning in configurationally hybridized graphene and boron nitride. npj Computational Materials, 5(1):26.

[10]GiebelerL, BalachJ, 2021. Mxenes in lithium–sulfur batteries: scratching the surface of a complex 2D material–a minireview. Materials Today Communications, 27:102323.

[11]GrimmeS, AntonyJ, EhrlichS, et al., 2010. A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu. The Journal of Chemical Physics, 132(15):154104.

[12]HaastrupS, StrangeM, PandeyM, et al., 2018. The computational 2D materials database: high-throughput modeling and discovery of atomically thin crystals. 2D Materials, 5(4):042002.

[13]HeKM, ZhangXY, RenSQ, et al., 2016. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p.770-778.

[14]HenkelmanG, JónssonH, 2000. Improved tangent estimate in the nudged elastic band method for finding minimum energy paths and saddle points. The Journal of Chemical Physics, 113(22):9978-9985.

[15]HuangG, LiuZ, van der MaatenL, et al., 2017. Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p.2261-2269.

[16]KabirajA, MahapatraS, 2022. High-throughput assessment of two-dimensional electrode materials for energy storage devices. Cell Reports Physical Science, 3(1):100718.

[17]KangYQ, LiLJ, LiBH, 2021. Recent progress on discovery and properties prediction of energy materials: simple machine learning meets complex quantum chemistry. Journal of Energy Chemistry, 54:72-88.

[18]KresseG, FurthmüllerJ, 1996. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Physical Review B, 54(16):11169-11186.

[19]LangrethDC, MehlMJ, 1983. Beyond the local-density approximation in calculations of ground-state electronic properties. Physical Review B, 28(4):1809-1834.

[20]LeeSJ, TheerthagiriJ, NithyadharseniP, et al., 2021. Heteroatom-doped graphene-based materials for sustainable energy applications: a review. Renewable and Sustainable Energy Reviews, 143:110849.

[21]LeistC, HeM, LiuX, et al., 2022. Deep-learning pipeline for statistical quantification of amorphous two-dimensional materials. ACS Nano, 16(12):20488-20496.

[22]LiWW, AndoY, MinamitaniE, et al., 2017. Study of Li atom diffusion in amorphous Li₃PO₄ with neural network potential. The Journal of Chemical Physics, 147(21):214106.

[23]LiuF, FanZX, 2023. Defect engineering of two-dimensional materials for advanced energy conversion and storage. Chemical Society Reviews, 52(5):1723-1772.

[24]LiuHP, LeiW, TongZM, et al., 2020. Defect engineering of 2D materials for electrochemical energy storage. Advanced Materials Interfaces, 7(15):2000494.

[25]LiuY, WuJM, AvdeevM, et al., 2020. Multi-layer feature selection incorporating weighted score-based expert knowledge toward modeling materials with targeted properties. Advanced Theory and Simulations, 3(2):1900215.

[26]LuGM, WitmanM, AgarwalS, et al., 2023. Explainable machine learning for hydrogen diffusion in metals and random binary alloys. Physical Review Materials, 7(10):105402.

[27]MasubuchiS, WatanabeE, SeoY, et al., 2020. Deep-learning-based image segmentation integrated with optical microscopy for automatically searching for two-dimensional materials. npj 2D Materials and Applications, 4(1):3.

[28]MommaK, IzumiF, 2011. VESTA 3 for three-dimensional visualization of crystal, volumetric and morphology data. Journal of Applied Crystallography, 44(6):1272-1276.

[29]PaszkeA, GrossS, MassaF, et al., 2019. PyTorch: an imperative style, high-performance deep learning library. In: Wallach H, Larochelle H, Beygelzimer A (Eds.), Advances in Neural Information Processing Systems, 32. Curran Associates, p.8024-8035.

[30]PerdewJP, BurkeK, ErnzerhofM, 1996. Generalized gradient approximation made simple. Physical Review Letters, 77(18):3865-3868.

[31]RyuB, WangLQ, PuHH, et al., 2022. Understanding, discovery, and synthesis of 2D materials enabled by machine learning. Chemical Society Reviews, 51(6):1899-1925.

[32]SendekAD, YangQ, CubukED, et al., 2017. Holistic computational structure screening of more than 12000 candidates for solid lithium-ion conductor materials. Energy & Environmental Science, 10(1):306-320.

[33]ShaoQJ, WuZS, ChenJ, 2019. Two-dimensional materials for advanced Li-S batteries. Energy Storage Materials, 22:284-310.

[34]SimonyanK, ZissermanA, 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556.

[35]TanCQ, SunFC, KongT, et al., 2018. A survey on deep transfer learning. The 27th International Conference on Artificial Neural Networks and Machine Learning, p.270-279.

[36]TheerthagiriJ, LeeSJ, KaruppasamyK, et al., 2021. Application of advanced materials in sonophotocatalytic processes for the remediation of environmental pollutants. Journal of Hazardous Materials, 412:125245.

[37]TheerthagiriJ, ParkJ, DasHT, et al., 2022a. Electrocatalytic conversion of nitrate waste into ammonia: a review. Environmental Chemistry Letters, 20(5):2929-2949.

[38]TheerthagiriJ, KaruppasamyK, LeeSJ, et al., 2022b. Fundamentals and comprehensive insights on pulsed laser synthesis of advanced materials for diverse photo- and electrocatalytic applications. Light: Science & Applications, 11(1):250.

[39]WangGY, FearnT, WangTY, et al., 2021. Machine-learning approach for predicting the discharging capacities of doped lithium nickel–cobalt–manganese cathode materials in Li-ion batteries. ACS Central Science, 7(9):1551-1560.

[40]WangRH, LiMH, SunKW, et al., 2022. Element-doped mxenes: mechanism, synthesis, and applications. Small, 18(25):2201740.

[41]WangXG, MengLJ, LiBX, et al., 2021. Heteroatoms/molecules to tune the properties of 2D materials. Materials Today, 47:108-130.

[42]WangXL, XiaoRJ, LiH, et al., 2017. Quantitative structure-property relationship study of cathode volume changes in lithium ion batteries using ab-initio and partial least squares analysis. Journal of Materiomics, 3(3):178-183.

[43]WuY, YuY, 2019. 2D material as anode for sodium ion batteries: recent progress and perspectives. Energy Storage Materials, 16:323-343.

[44]XieT, GrossmanJC, 2018. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Physical Review Letters, 120(14):145301.

[45]YosinskiJ, CluneJ, BengioY, et al., 2014. How transferable are features in deep neural networks? Proceedings of the 28th International Conference on Neural Information Processing Systems, Volume 2, p.3320-3328.

[46]ZhanC, SunWW, XieY, et al., 2019. Computational discovery and design of mxenes for energy applications: status, successes, and opportunities. ACS Applied Materials & Interfaces, 11(28):24885-24905.

[47]ZhangWS, LiuSY, ChenJ, et al., 2021. Exploring the potentials of Ti₃C_iN_2–iT_x (i=0, 1, 2)-mxene for anode materials of high-performance sodium-ion batteries. ACS Applied Materials & Interfaces, 13(19):22341-22350.

[48]ZhangXY, ZhouJ, LuJ, et al., 2022. Interpretable learning of voltage for electrode design of multivalent metal-ion batteries. npj Computational Materials, 8(1):175.

[49]ZhangYQ, TaoL, XieC, et al., 2020. Defect engineering on electrode materials for rechargeable batteries. Advanced Materials, 32(7):1905923.