Radiation-induced grafting (RIG) enables precise functionalization of polymer films for ion-exchange membranes, CO2-separation membranes, and battery electrolytes by generating radicals on robust substrates to graft desired monomers. However, reproducibility remains limited due to unreported variability in base-film morphology (crystallinity, grain orientation, free volume), which governs monomer diffusion, radical distribution, and the Trommsdorff effect, leading to spatial graft gradients and performance inconsistencies. We present a hierarchical stacking optimization framework with a Dirichlet's Process (SoDip), a hierarchical data-driven framework integrating: (1) a decoder-only Transformer (DeepSeek-R1) to encode textual process descriptors (irradiation source, grafting type, substrate manufacturer); (2) TabNet and XGBoost for modelling multimodal feature interactions; (3) Gaussian Process Regression (GPR) with Dirichlet Process Mixture Models (DPMM) for uncertainty quantification and heteroscedasticity; and (4) Bayesian Optimization for efficient exploration of high-dimensional synthesis space. A diverse dataset was curated using ChemDataExtractor 2.0 and WebPlotDigitizer, incorporating numerical and textual variables across hundreds of RIG studies. In cross-validation, SoDip achieved ~33% improvement over GPR while providing calibrated confidence intervals that identify low-reproducibility regimes. Its stacked architecture integrates sparse textual and numerical inputs of varying quality, outperforming prior models and establishing a foundation for reproducible, morphology-aware design in graft polymerization research.

翻译：辐射诱导接枝（RIG）通过在坚固的基底上产生自由基来接枝所需单体，能够实现聚合物薄膜的精确功能化，用于制备离子交换膜、CO2分离膜和电池电解质。然而，由于基底薄膜形态（结晶度、晶粒取向、自由体积）中未报告的变异性——这些因素控制着单体扩散、自由基分布和特罗姆斯多夫效应，导致空间接枝梯度和性能不一致——可重复性仍然有限。我们提出了一种基于狄利克雷过程的分层堆叠优化框架（SoDip），这是一个分层的数据驱动框架，整合了：（1）仅解码器Transformer（DeepSeek-R1）用于编码文本过程描述符（辐照源、接枝类型、基底制造商）；（2）TabNet和XGBoost用于建模多模态特征交互；（3）结合狄利克雷过程混合模型（DPMM）的高斯过程回归（GPR）用于不确定性量化和异方差性处理；（4）贝叶斯优化用于高效探索高维合成空间。我们使用ChemDataExtractor 2.0和WebPlotDigitizer整理了一个多样化数据集，整合了数百项RIG研究中的数值和文本变量。在交叉验证中，SoDip相比GPR实现了约33%的性能提升，同时提供了经过校准的置信区间，能够识别低可重复性区域。其堆叠架构整合了不同质量的稀疏文本和数值输入，优于现有模型，并为接枝聚合研究中可重复的、形态感知的设计奠定了基础。