我的研究主要围绕同步辐射X射线散射技术与人工智能/机器学习、高分子的深度融合开展研究，以下是具体的研究方向和成果：
1. 同步辐射散射技术及原位/工况研究方法
致力于同步辐射共振相干散射线站设计与建设，以及发展基于同步辐射硬X射线散射的原位表征装置与方法，以实现高分子材料在接近真实加工（拉伸、温度场等）条件下的结构演化实时追踪。代表性成果如下：
合肥光源共振软X射线散射（金华）线站：https://www.nsrl.ustc.edu.cn/gzrXsxssxz/list.htm
Li, W.#; Yu, W.#; Zhu, J.; Qiao, M.; Guo, H.; Li, X. Cui, K.*; Li, L.* Synchrotron Radiation X-ray Scattering Approaching Real Industrial Processing of Polymer. Polymer Science & Technology 2025, 1, 155-170.
Min, X.; Wu, T.; Han, X.; An, M.; Yu, W.*; Li, L.* Zero-Zero Birefringence Cellulose Acetate-based Optical Films by Benzoylation. ACS Appl. Polym. Mater. 2022, 4 (8), 6255-6264.
Wu, T.; Han, X.; Min, X.; An, M.; Zhao, J.; Yu, W.*; Li, L.* Regulation of orientation birefringence for cellulose acetate film: The role of crystallization and orientation. Carbohydrate Polymers 2022, 296, 119915.
Chen, J.; Zhang, W.; Chen, Y.; Zhang, H.; Ye, B.; Yu, W.*; Li, L.* Structural evolutions of the amorphous fraction of polyethylene terephthalate during the secondary crystallization. Polymer 2022, 253, 124987.
Wu, T.; Min, X.; Han, X.; An, M.; Zhao, J.; Yu, W.*; Li, L.* Orientation Birefringence Regulation for the Binary Blend Film of Cellulose Triacetate and Rigid-Rod-Like 5CB Molecules. ACS Appl. Polym. Mater. 2021, 3, 6642-6652.
Zhao, J.; Feng, S.; Zhang, W.; Chen, W.; Sheng, J.; Yu, W.*; Li, L.* Strain Rate Dependence of Stretch-Induced Crystallization and Crystal Transition of Poly(dimethylsiloxane). Macromolecules 2021, 54(19), 9204-9216.
Zhao, J.; Yu, W.*; Chen, W.; Chen, X.; Sheng, J.; Li, L.*Characterization of Polymer Materials by Synchrotron Radiation Hard X-ray Scattering Technology: The Development and Application of in-situ Instruments. Acta Polym. Sin. 2021, 52 (12), 1632-1646.
Iqbal, O.; Habumugisha, J. C.; Feng, S.; Lin, Y.; Chen, W.; Yu, W.*; Li, L.* Microstructural Origin of the Double Yield Points of the Metallocene Linear Low-Density Polyethylene (mLLDPE) Precursor Film under Uniaxial Tensile Deformation. Polymers 2021, 13, 126.
2. 同步辐射散射等大科学数据AI/ML分析方法
面向同步辐射小角X射线散射（SAXS）与固态核磁共振（NMR）谱学等大科学装置产生的高维、海量数据，开发了一系列融入物理先验的机器学习与深度学习方法。在小角散射数据分析方面，建立了基于机器学习的SAXS数据集可视化与聚丙烯薄膜加工-结构映射方法，提出物理感知神经网络从二维SAXS谱直接重构材料形态，以及利用图神经网络加速预测球形纳米颗粒尺寸分布。在多维谱学分析方面，发展了机器学习辅助解析二维固态NMR谱的方法。代表性成果如下：
Guo, Q. #; Xie, F.#; Sun, Z.; Jiao, X.*; Yu, W.* Machine Learning for Accelerated Prediction of Size Distributions of Spherical Nanoparticles from Small-Angle X-ray Scattering. Phys. Chem. Chem. Phys. 2026, 28, 9659-9667.
Zhao, C.; Sun, S.; Han, X.; Zhu, J.; Yu, W.*; Li, L. Morphology reconstruction from experimental small-angle x-ray scattering patterns by physics-aware neural network. APL Mach. Learn. 2025, 3, 016109.
Tao, W.#; Yu, W.#; Zou, X.; Chen, W.* Machine Learning Assisted Interpretation of 2D Solid-state Nuclear Magnetic Resonance Spectra. Journal of Magnetic Resonance 2023, 353, 107492.
Zhao, C.; Yu, W.*; Li, L.* Visualization of small-angle X-ray scattering datasets and processing-structure mapping of isotactic polypropylene films by machine learning. Materials & Design 2023, 228, 111828.
3. AI/ML与高分子交叉研究
利用AI/ML方法开展高分子链构象性质，高分子材料性质预测和逆向设计等研究。代表性成果如下：
Sun, S.; Tian, F.; Zhao, C.; Xie, M.; Li, W.; Yu, W.*; Cui, K.; Li, L.* Directed message passing neural networks enhanced graph convolutional learning for accurate polymer density prediction J. Chem. Phys. 2025, 163, 104903.
Yu, W.#; Liu, Y.#; Chen, Y; Jiang, Y.*; Chen, J. Z. Y.* Generating the conformational properties of a polymer by the restricted Boltzmann machine. J. Chem. Phys. 2019, 151 (3), 031101.