机器学习驱动新型发光材料的研究进展

doi:10.15541/jim20250368

摘要/Abstract

摘要：

发光材料是一类重要的战略性先进电子材料, 在新型显示、固态照明、生物医学和传感探测等领域展现出广阔的应用前景。然而, 实际应用对材料性能提出多维度严格要求, 依赖经验与试错的传统研发模式周期长、成本高, 严重制约高性能新材料的开发进程。近年来, 机器学习(Machine learning, ML)的快速发展为该领域瓶颈问题提供了新的解决途径。ML通过构建“组成-结构-性能”之间的复杂映射关系, 实现对候选材料的高通量虚拟筛选, 进而提升研发效率。此外, ML的特征重要性分析, 揭示了影响发光性能的关键物理化学因素, 为理解材料构效关系提供了新的理论支持。本文系统阐述了ML驱动发光材料研发的流程框架, 重点包括数据准备、特征工程、模型选择、模型评估与模型应用等关键环节, 并深入探讨了各阶段在发光材料研究中的特殊考量与应对策略。在此基础上, 本文还综述了ML在荧光粉关键性能预测方面的最新研究进展, 包括发射波长、半峰全宽(FWHM)、热稳定性、荧光寿命、质心位移及工艺优化等关键指标。最后, 对当前研究存在的挑战, 如可靠数据匮乏、材料性质复杂及参数难量化等问题进行了梳理, 并展望了未来人工智能(Artificial intelligence, AI)技术在发光材料研究中深度融合的发展趋势, 以期为推动荧光粉材料领域“AI for Science”新范式的建立提供有益参考。

关键词: 机器学习, 荧光粉, 人工智能, 数据驱动技术, 发光材料, AI for Science, 综述

Abstract:

Phosphor materials are essential functional components in modern optoelectronics, playing a crucial role in next-generation displays, solid-state lighting, biomedical imaging, and sensing applications. However, the properties of materials are stringently required in multiple dimensions for practical applications. The conventional trial-and-error approach impedes the development of novel high-performance phosphors due to its long cycles and high costs. In recent years, the rapidly advancing machine learning (ML) methodology presents an innovative solution to addressing these bottlenecks. It not only dramatically accelerates the high-throughput virtual screening of candidate materials by establishing complex mappings among “composition-structure-property”, substantially improving efficiency, but also provides novel theoretical insights into structure-property correlations through algorithm-derived importance weights. This review systematically outlines the methodological framework for ML-driven phosphor development, covering key stages including data preparation, feature engineering, model selection, model evaluation and application. It further discusses specific considerations and corresponding strategies for each stage of the process. Subsequently, it reviews recent research progress in applying ML to predict key phosphor properties, encompassing critical metrics such as emission wavelength, full width at half-maximum (FWHM), thermal stability, fluorescence lifetime, centroid shift, and process optimization. Finally, this review addresses existing challenges in current research, such as scarcity of reliable data, complexity of materials properties, and difficulties in parameter quantification. The article outlines future development trends for the deep integration of artificial intelligence (AI) technology in luminescent materials research, aiming to provide a valuable reference for promoting the establishment of an “AI for Science” paradigm in the field of phosphor materials.

Key words: machine learning, phosphor, artificial intelligence, data-driven technique, luminescent material, AI for science, review

中图分类号:

O482

宋坤洁, 解荣军. 机器学习驱动新型发光材料的研究进展[J]. 无机材料学报, 2026, 41(6): 689-703.

SONG Kunjie, XIE Rongjun. Research Advances on Machine Learning-driven Development of Novel Luminescent Materials[J]. Journal of Inorganic Materials, 2026, 41(6): 689-703.

图/表 7

图1 荧光粉的关键性能指标

Fig. 1 Key properties for phosphors (a) Fluorescence spectrum (including excitation wavelength, emission wavelength, FWHM, Stokes shift); (b) Thermal stability of materials; (c) Quantum efficiency of phosphor; (d) Decay time; (e) Chemical stability; (f) Particle size distribution

图2 人工智能、机器学习与深度学习之间的关系示意图

Fig. 2 Conceptual framework of hierarchical relationship among artificial intelligence, machine learning, and deep learning

表1

Table 1 Major external libraries and databases[34-43]

Library	Website	Ref.	Database	Website	Ref.
Matminer	https://hackingmaterials.lbl.gov/matminer/	[34]	MP	https://materialsproject.org/	[39]
DScribe	https://singroup.github.io/dscribe/	[35]	AFLOW	https://www.aflowlib.org/	[40]
ChemTools	https://www.chemistrytools.org/	[36]	NOMAD	https://nomad-lab.eu/nomad-lab/	[41]
RDKit	https://www.rdkit.org/	[37]	ICSD	https://icsd.nist.gov/	[42]
Pymatgen	https://pymatgen.org/	[38]	COD	https://www.crystallography.net/cod/	[43]
……			……

图3 ML模型用于发射波长预测的应用[26,54,69,72,74]

Fig. 3 Application of ML models for emission wavelength prediction[26,54,69,72,74] (a) Emission spectra and A-X and A-A local structures for Ba2LiB5O10:Eu2+ and BaB8O13:Eu2+[69]; (b) Theoretically predicted and experimentally observed emission wavelengths of R1-xKxLSO:0.01Eu2+ (0≤x≤1) phosphors[54]; (c) Performance of the best model on the dataset[72]; (d) Comparison diagram between model predicted values and experimentally observed values[74]; (e) Comparative plots of the experimentally observed and model predicted values[26]

图4 ML模型用于发射FWHM预测的应用[80-81,83 -84]

Fig. 4 Application of ML models for emission FWHM prediction[80-81,83 -84] (a) Predicted emission wavelengths and FWHM of candidates[80]; (b) Relationship between emission bandwidth and Eu2+4f band levels. When there are multiple Eu2+4f levels within 0.1 eV from the highest band (left), overlapping emissions result in a broad bandwidth. Conversely, a large energy splitting between the two highest 4f bands (right) results in narrow-band emission[81]; (c) 2D t-SNE plots of the local structures, and enlarged image showing phosphors with similar local structures within the black region[83]; (d) 2D t-SNE plots of local structures[84]

图5 ML模型用于热稳定性预测的应用[11,25,89]

Fig. 5 Application of ML models for thermal stability prediction[11,25,89] (a) Schematic of thermally induced photoionization in phosphors that undergo 4fn-15d1→4fn5d0 transitions[11]; (b) Schematic of the crossover mechanism in which thermally induced non-radiative relaxation occurs at the intersection (crossover) point between the ground and excited state parabolas[11]; (c) Predicted T50 by model versus experimental results[89]; (d) Thermal quenching curves of normalized emission intensity for five candidate structures[89]; (e) Distribution of 2071 candidate structures with axes representing the model-predicted Deybe temperature and the DFT-calculated bandgap[25]

图6 ML模型用于其他性质预测的应用[24,97 -98]

Fig. 6 Application of ML models for other properties prediction[24,97 -98] (a) Experimental versus predicted fluorescence lifetime from ML model[24]; (b) Comparison of ML-predicted versus DFT-calculated dielectric constants for the validation set[97]; (c) Decision tree classification model for emission colors[98]

参考文献 102

[1]	XIE R J, HIROSAKI N. Silicon-based oxynitride and nitride phosphors for white LEDs—a review. Science and Technology of Advanced Materials, 2007, 8(7/8): 588.
[2]	XIE R J, HIROSAKI N, SAKUMA K, et al. Eu²⁺-doped Ca-α-SiAlON: a yellow phosphor for white light-emitting diodes. Applied Physics Letters, 2004, 84(26): 5404.
[3]	WANG P, WANG Y, LI Z, et al. Enhanced stability and brightness through co-substitution: promoting plant growth with green-excited deep red phosphor Ca_1-_zSr_zLi_1-_xMg₂_xAl_3-_xN₄:yEu²⁺. Advanced Materials, 2025, 37(4): 2414578.
[4]	LIU S, LI L, QIN X, et al. Achieving ultra-broadband sunlight-like emission in single-phase phosphors: the interplay of structure and luminescence. Advanced Materials, 2024, 36(38): 2406164.
[5]	LIU S, YANG X, DU R, et al. Single-grain high-efficiency full- visible-spectrum white emitters. Angewandte Chemie International Edition, 2025, 64(19): e202502100.
[6]	LI S, XIA Y, AMACHRAA M, et al. Data-driven discovery of full-visible-spectrum phosphor. Chemistry of Materials, 2019, 31(16): 6286.
[7]	PUST P, WEILER V, HECHT C, et al. Narrow-band red-emitting Sr[LiAl₃N₄]:Eu²⁺ as a next-generation LED-phosphor material. Nature Materials, 2014, 13(9): 891.
[8]	PUST P, SCHMIDT P J, SCHNICK W. A revolution in lighting. Nature Materials, 2015, 14(5): 454.
[9]	GEORGE N C, DENAULT K A, SESHADRI R. Phosphors for solid-state white lighting. Annual Review of Materials Research, 2013, 43(1): 481.
[10]	MORGAN P, MONICA H, NORMAN B, et al. 2022 Solid-state lighting R&D opportunities. US Department of Energy Office of Scientific and Technical Information. (2022-02-02)[2025-11-26]. https://doi.org/10.2172/1862626.
[11]	HARIYANI S, SÓJKA M, SETLUR A, et al. A guide to comprehensive phosphor discovery for solid-state lighting. Nature Reviews Materials, 2023, 8(11): 759.
[12]	TAKEDA T, KOYAMA Y, IKENO H, et al. Exploring new useful phosphors by combining experiments with machine learning. Science and Technology of Advanced Materials, 2024, 25(1): 2421761.
[13]	WANG X J, WANG L, TAKEDA T, et al. Blue-emitting Sr₃Si_8-_xAl_xO₇₊_xN_8-_x:Eu²⁺ discovered by a single-particle-diagnosis approach: crystal structure, luminescence, scale-up synthesis, and its abnormal thermal quenching behavior. Chemistry of Materials, 2015, 27(22): 7689.
[14]	PARK W B, SINGH S P, KIM M, et al. Combinatorial screening of luminescent and structural properties in a Ce³⁺-doped Ln-Al-Si-O-N (Ln = Y, La, Gd, Lu) system: the discovery of a novel Gd₃Al₃₊_xSi_3-_xO₁₂₊_xN_2-_x:Ce³⁺ phosphor. Inorganic Chemistry, 2015, 54(4): 1829.
[15]	PARK W B, SINGH S P, SOHN K S. Discovery of a phosphor for light emitting diode applications and its structural determination, Ba(Si,Al)₅(O,N)₈:Eu²⁺. Journal of the American Chemical Society, 2014, 136(6): 2363.
[16]	ZHAO M, LIAO H, MOLOKEEV M S, et al. Emerging ultra-narrow-band cyan-emitting phosphor for white LEDs with enhanced color rendition. Light: Science & Applications, 2019, 8: 38.
[17]	WANG Z, HA J, KIM Y H, et al. Mining unexplored chemistries for phosphors for high-color-quality white-light-emitting diodes. Joule, 2018, 2(5): 914.
[18]	LI S, AMACHRAA M, CHEN C, et al. Efficient near-infrared phosphors discovered by parametrizing the Eu(II) 5d-to-4f energy gap. Matter, 2022, 5(6): 1924.
[19]	BUTLER K T, DAVIES D W, CARTWRIGHT H, et al. Machine learning for molecular and materials science. Nature, 2018, 559: 547.
[20]	XIE T, GROSSMAN J C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Physical Review Letters, 2018, 120(14): 145301.
[21]	AGRAWAL A, CHOUDHARY A. Perspective: materials informatics and big data: realization of the “fourth paradigm” of science in materials science. APL Materials, 2016, 4(5): 053208.
[22]	PARK C, LEE J W, KIM M, et al. A data-driven approach to predicting band gap, excitation, and emission energies for Eu²⁺-activated phosphors. Inorganic Chemistry Frontiers, 2021, 8(21): 4610.
[23]	MOLOKEEV M S, SU B, ALEKSANDROVSKY A S, et al. Machine learning analysis and discovery of zero-dimensional ns² metal halides toward enhanced photoluminescence quantum yield. Chemistry of Materials, 2022, 34(2): 537.
[24]	MING H, ZHOU Y, MOLOKEEV M S, et al. Machine- learning-driven discovery of Mn⁴⁺-doped red-emitting fluorides with short excited-state lifetime and high efficiency for mini light- emitting diode displays. ACS Materials Letters, 2024, 6(5): 1790.
[25]	ZHUO Y, TEHRANI A, OLIYNYK A, et al. Identifying an efficient, thermally robust inorganic phosphor host via machine learning. Nature Communications, 2018, 9: 4377.
[26]	WANG Y, TANG W, ZHANG C, et al. Structure-based machine learning enables discovery of Mn⁴⁺-activated red-light fluorides for ultrawide-gamut mini-light-emitting diodes. Advanced Functional Materials, 2024, 34(14): 2313490.
[27]	BI H, JIANG J, CHEN J, et al. Machine learning prediction of quantum yields and wavelengths of aggregation-induced emission molecules. Materials, 2024, 17(7): 1664.
[28]	PILANIA G, GUBERNATIS J E, LOOKMAN T. Multi-fidelity machine learning models for accurate bandgap predictions of solids. Computational Materials Science, 2017, 129: 156.
[29]	YUAN H, QI L, PARIS M, et al. Machine learning guided design of single-phase hybrid lead halide white phosphors. Advanced Science, 2021, 8(19): 2101407.
[30]	LI H, ZHENG H, YUE T, et al. Machine learning-accelerated discovery of heat-resistant polysulfates for electrostatic energy storage. Nature Energy, 2025, 10: 90.
[31]	YANG S, ZANG B, XIANG M, et al. Designing Fe-based amorphous alloys with both ultra-high magnetization and ultra-low coercivity through artificial intelligence. Advanced Functional Materials, 2025, 35(30): 2425588.
[32]	JIA X, DENG Y, BAO X, et al. Unsupervised machine learning for discovery of promising half-Heusler thermoelectric materials. npj Computational Materials, 2022, 8: 34.
[33]	ISAYEV O, OSES C, TOHER C, et al. Universal fragment descriptors for predicting properties of inorganic crystals. Nature Communications, 2017, 8: 15679.
[34]	WARD L, DUNN A, FAGHANINIA A, et al. Matminer: an open source toolkit for materials data mining. Computational Materials Science, 2018, 152: 60.
[35]	HIMANEN L, JÄGER M O J, MOROOKA E V, et al. DScribe: library of descriptors for machine learning in materials science. Computer Physics Communications, 2020, 247: 106949.
[36]	HEIDAR-ZADEH F, RICHER M, FIAS S, et al. An explicit approach to conceptual density functional theory descriptors of arbitrary order. Chemical Physics Letters, 2016, 660: 307.
[37]	BENTO A P, HERSEY A, FÉLIX E, et al. An open source chemical structure curation pipeline using RDKit. Journal of Cheminformatics, 2020, 12: 51.
[38]	ONG S P, RICHARDS W D, JAIN A, et al. Python Materials Genomics (pymatgen): a robust, open-source Python library for materials analysis. Computational Materials Science, 2013, 68: 314.
[39]	JAIN A, ONG S P, HAUTIER G, et al. Commentary: the materials project: a materials genome approach to accelerating materials innovation. APL Materials, 2013, 1: 011002.
[40]	CURTAROLO S, SETYAWAN W, HART G L W, et al. AFLOW: an automatic framework for high-throughput materials discovery. Computational Materials Science, 2012, 58: 218.
[41]	DRAXL C, SCHEFFLER M. The NOMAD laboratory: from data sharing to artificial intelligence. Journal of Physics: Materials, 2019, 2(3): 036001.
[42]	HELLENBRANDT M. The inorganic crystal structure database (ICSD)—present and future. Crystallography Reviews, 2004, 10(1): 17.
[43]	GRAŽULIS S, DAŠKEVIČ A, MERKYS A, et al. Crystallography open database (COD): an open-access collection of crystal structures and platform for world-wide collaboration. Nucleic Acids Research, 2012, 40(D1): D420.
[44]	MORGAN D, JACOBS R. Opportunities and challenges for machine learning in materials science. Annual Review of Materials Research, 2020, 50(1): 71.
[45]	LIU Y, YANG Z, ZOU X, et al. Data quantity governance for machine learning in materials science. National Science Review, 2023, 10(7): nwad125.
[46]	HAGHIGHATLARI M, LI J, HEIDAR-ZADEH F, et al. Learning to make chemical predictions: the interplay of feature representation, data, and machine learning methods. Chem, 2020, 6(7): 1527.
[47]	GHIRINGHELLI L M, VYBIRAL J, LEVCHENKO S V, et al. Big data of materials science: critical role of the descriptor. Physical Review Letters, 2015, 114(10): 105503.
[48]	HE J, LI J, LIU C, et al. Machine learning identified materials descriptors for ferroelectricity. Acta Materialia, 2021, 209: 116815.
[49]	YILMAZ B, YILDIRIM R. Critical review of machine learning applications in perovskite solar research. Nano Energy, 2021, 80: 105546.
[50]	JO B, CHEN W, JUNG H S. Comprehensive review of advances in machine-learning-driven optimization and characterization of perovskite materials for photovoltaic devices. Journal of Energy Chemistry, 2025, 101: 298.
[51]	PEARSON K. Mathematical contributions to the theory of evolution: on a form of spurious correlation which may arise when indices are used in the measurement of organs. Proceedings of the Royal Society, 1897, 60: 489.
[52]	WANG A Y T, MURDOCK R J, KAUWE S K, et al. Machine learning for materials scientists: an introductory guide toward best practices. Chemistry of Materials, 2020, 32(12): 4954.
[53]	LI C, HAO H, XU B, et al. Improved physics-based structural descriptors of perovskite materials enable higher accuracy of machine learning. Computational Materials Science, 2021, 198: 110714.
[54]	LAI S, ZHAO M, QIAO J, et al. Data-driven photoluminescence tuning in Eu²⁺-doped phosphors. The Journal of Physical Chemistry Letters, 2020, 11(14): 5680.
[55]	KARPOVICH C, PAN E, OLIVETTI E A. Deep reinforcement learning for inverse inorganic materials design. npj Computational Materials, 2024, 10: 287.
[56]	HE Z, THÜRER M, ZHOU W. The use of reinforcement learning for material flow control: an assessment by simulation. International Journal of Production Economics, 2024, 274: 109312.
[57]	SHEN Z H, LIU H X, SHEN Y, et al. Machine learning in energy storage materials. Interdisciplinary Materials, 2022, 1(2): 175.
[58]	JIANG X, FU H, BAI Y, et al. Interpretable machine learning applications: a promising prospect of AI for materials. Advanced Functional Materials, 2025, 35(41): 2507734.
[59]	SHI Y, ZHANG Y, WEN J, et al. Interpretable machine learning for stability and electronic structure prediction of Janus III-VI van der Waals heterostructures. Materials Genome Engineering Advances, 2024, 2(4): e76.
[60]	YAO Y, HAN D, SPOONER K B, et al. Adapting explainable machine learning to study mechanical properties of 2D hybrid halide perovskites. Advanced Functional Materials, 2025, 35(1): 2411652.
[61]	DUAN X, LI Y, ZHAO J, et al. Machine learning accelerated discovery of entropy-stabilized oxide catalysts for catalytic oxidation. Journal of the American Chemical Society, 2025, 147(1): 651.
[62]	HAN Z, XIA S, CHEN Z, et al. Facilitated the discovery of new γ/γ′ Co-based superalloys by combining first-principles and machine learning. npj Computational Materials, 2024, 10: 259.
[63]	WU J, TORRESI L, HU M, et al. Inverse design workflow discovers hole-transport materials tailored for perovskite solar cells. Science, 2024, 386(6727): 1256.
[64]	CUI C X, SHEN Y, HE J R, et al. Quantitative insight into the electric field effect on CO₂ electrocatalysis via machine learning spectroscopy. Journal of the American Chemical Society, 2024, 146(50): 34551.
[65]	WANG L, XIE R J, SUEHIRO T, et al. Down-conversion nitride materials for solid state lighting: recent advances and perspectives. Chemical Reviews, 2018, 118(4): 1951.
[66]	XIE R J, HINTZEN H T. Optical properties of (oxy)nitride materials: a review. Journal of the American Ceramic Society, 2013, 96(3): 665.
[67]	XIE R J, HIROSAKI N, SUEHIRO T, et al. A simple, efficient synthetic route to Sr₂Si₅N₈:Eu²⁺-based red phosphors for white light-emitting diodes. Chemistry of Materials, 2006, 18(23): 5578.
[68]	LI Y, HIROSAKI N, XIE R J, et al. Yellow-orange-emitting CaAlSiN₃:Ce³⁺ phosphor: structure, photoluminescence, and application in white LEDs. Chemistry of Materials, 2008, 20(21): 6704.
[69]	PARK W B, SINGH S P, KIM M, et al. Phosphor informatics based on confirmatory factor analysis. ACS Combinatorial Science, 2015, 17(5): 317.
[70]	QIAO J, AMACHRAA M, MOLOKEEV M, et al. Engineering of K₃YSi₂O₇ to tune photoluminescence with selected activators and site occupancy. Chemistry of Materials, 2019, 31(18): 7770.
[71]	QIAO J, ZHOU G, ZHOU Y, et al. Divalent europium-doped near-infrared-emitting phosphor for light-emitting diodes. Nature Communications, 2019, 10: 5267.
[72]	KOYAMA Y, IKENO H, HARADA M, et al. Rapid discovery of new Eu²⁺-activated phosphors with a designed luminescence color using a data-driven approach. Materials Advances, 2023, 4(1): 231.
[73]	XU Y, YAMAZAKI M, VILLARS P. Inorganic materials database for exploring the nature of material. Japanese Journal of Applied Physics, 2011, 50(11S): 11RH02.
[74]	NAKANO H, TANAKA K, MIYAO T, et al. Practical models for predicting the emission peak wavelengths of inorganic phosphors based on stoichiometric information. Chemistry Letters, 2017, 46(10): 1482.
[75]	DING C, LI Z F, ZHANG W J, et al. Machine learning the peak emission wavelength of Mn⁴⁺-activated inorganic phosphors. New Journal of Chemistry, 2023, 47(22): 10875.
[76]	TIAN R, ZHOU T, XIE R J. Spectrally tunable dual-phosphor ceramics for laser lighting. Laser & Photonics Reviews, 2025, 19(13): 2402144.
[77]	HIROSAKI N, XIE R, KIMOTO K, et al. Characterization and properties of green-emitting β-SiAlON:Eu²⁺ powder phosphors for white light-emitting diodes. Applied Physics Letters, 2005, 86(21): 211905.
[78]	ZHAO M, YANG Z, NING L, et al. Tailoring of white luminescence in a NaLi₃SiO₄:Eu²⁺ phosphor containing broad-band defect-induced charge-transfer emission. Advanced Materials, 2021, 33(29): 2101428.
[79]	ZHAO M, LIAO H, NING L, et al. Next-generation narrow-band green-emitting RbLi(Li₃SiO₄)₂:Eu²⁺ phosphor for backlight display application. Advanced Materials, 2018, 30(38): 1802489.
[80]	LIU S, SONG K, LI S, et al. Machine learning-driven discovery of efficient narrow-band green phosphor for wide-color-gamut backlight displays. Chemical Engineering Journal, 2025, 520: 165719.
[81]	WANG Z, CHU I H, ZHOU F, et al. Electronic structure descriptor for the discovery of narrow-band red-emitting phosphors. Chemistry of Materials, 2016, 28(11): 4024.
[82]	KIM M, SINGH S P, LEE J W, et al. Identification of a narrow band red light-emitting phosphor using computational screening of ICSD: its synthesis and optical characterization. Journal of Alloys and Compounds, 2019, 774: 338.
[83]	TAKEMURA S, KOYAMA Y, NAKANISHI T, et al. Narrow-band phosphor K₂ZnP₂O₇:Eu²⁺ discovered using local structure similarity. Scripta Materialia, 2022, 215(1): 114686.
[84]	TAKEMURA S, KOYAMA Y, NAKANISHI T, et al. Narrow-band emitting phosphor Na₂Cs₂Sr(B₉O₁₅)₂:Eu²⁺ discovered from local structure similarity with sulfate phosphor. The Journal of Physical Chemistry Letters, 2022, 13(51): 11878.
[85]	AMACHRAA M, WANG Z, CHEN C, et al. Predicting thermal quenching in inorganic phosphors. Chemistry of Materials, 2020, 32(14): 6256.
[86]	KIM Y H, ARUNKUMAR P, KIM B Y, et al. A zero-thermal- quenching phosphor. Nature Materials, 2017, 16(5): 543.
[87]	ZHENG P, LI S, WANG L, et al. Unique color converter architecture enabling phosphor-in-glass (PiG) films suitable for high-power and high-luminance laser-driven white lighting. ACS Applied Materials & Interfaces, 2018, 10(17): 14930.
[88]	JIANG L, JIANG X, ZHANG Y, et al. Multiobjective machine learning-assisted discovery of a novel cyan-green garnet: Ce phosphors with excellent thermal stability. ACS Applied Materials & Interfaces, 2022, 14(13): 15426.
[89]	ZHUO Y, HARIYANI S, ARMIJO E, et al. Evaluating thermal quenching temperature in Eu³⁺-substituted oxide phosphors via machine learning. ACS Applied Materials & Interfaces, 2020, 12(5): 5244.
[90]	ZHANG S, LV Y, LI Z, et al. Explainable machine learning- enabled discovery for high-efficiency red-emitting phosphor under data constraints. Chemical Engineering Journal, 2025, 522: 167046.
[91]	JIANG L, JIANG X, YANG M, et al. Developing and optimizing novel Cr³⁺-activated inorganic NIR phosphors by combining triple-objective optimization and crystal field engineering. Inorganic Chemistry Frontiers, 2024, 11(2): 487.
[92]	HUANG L, LOU S, CAO L, et al. Surfactant- and HF-free cation exchange synthesis of highly-efficient nanoscale K₂SiF₆:Mn⁴⁺ and potential usage for high-resolution micro-LED display. ACS Materials Letters, 2022, 4(9): 1716.
[93]	DORENBOS P. 5d-level energies of Ce³⁺ and the crystalline environment. I. Fluoride compounds. Physical Review B, 2000, 62(23): 15640.
[94]	DORENBOS P. 5d-level energies of Ce³⁺ and the crystalline environment. II. Chloride, bromide, and iodide compounds. Physical Review B, 2000, 62(23): 15650.
[95]	DORENBOS P. 5d-level energies of Ce³⁺ and the crystalline environment. III. Oxides containing ionic complexes. Physical Review B, 2001, 64(12): 125117.
[96]	DORENBOS P. Relation between Eu²⁺ and Ce³⁺ f ↔ d-transition energies in inorganic compounds. Journal of Physics: Condensed Matter, 2003, 15(27): 4797.
[97]	ZHUO Y, HARIYANI S, YOU S, et al. Machine learning 5d-level centroid shift of Ce³⁺ inorganic phosphors. Journal of Applied Physics, 2020, 128: 013104.
[98]	YUAN H, GÉNOIS R, GLAIS E, et al. Machine learning identification of experimental conditions for the synthesis of single-phase white phosphors. Matter, 2021, 4(12): 3967.
[99]	YUAN W, CHEN G, WANG Z, et al. Empowering generalist material intelligence with large language models. Advanced Materials, 2025, 37(32): 2502771.
[100]	XU P, MA Y, LU W, et al. Multi-objective optimization in machine learning assisted materials design and discovery. Journal of Materials Informatics, 2025, 5(2): 26.
[101]	ZHU Q, ZHANG F, HUANG Y, et al. An all-round AI-Chemist with a scientific mind. National Science Review, 2022, 9(10): nwac190.
[102]	MALYI O I, SOPIHA K V, PERSSON C, et al. Energy, phonon, and dynamic stability criteria of two-dimensional materials. ACS Applied Materials & Interfaces, 2019, 11(28): 24876.