用数据驱动框架解决辐射接枝法中因基底形态差异导致的重复性难题。
Hierarchical Stacking Optimization Using Dirichlet's Process (SoDip): Towards Accelerated Design for Graft Polymerization
- 基于狄利克雷过程构建分层优化框架，融合文本与多模态数据
- 相比传统方法提升33%预测性能，准确识别低重复性实验条件
- 适合材料设计、高通量合成及工艺可重复性研究者使用
辐射诱导接枝（RIG）可通过在稳定基底上生成自由基，精确功能化聚合物薄膜，应用于离子交换膜、二氧化碳分离膜和电池电解质。然而，由于基底形态（如结晶度、晶粒取向、自由体积）的未报告变异，导致单体扩散、自由基分布及Trommsdorff效应差异，产生空间接枝梯度与性能不一致，限制了可重复性。本文提出一种基于狄利克雷过程的分层堆叠优化框架（SoDip），整合：(1) 解码器仅变压器（DeepSeek-R1）编码文本工艺描述（辐照源、接枝类型、基材厂商）；(2) TabNet与XGBoost建模多模态特征交互；(3) 带狄利克雷过程混合模型（DPMM）的高斯过程回归（GPR）实现不确定性量化与异方差性建模；(4) 贝叶斯优化高效探索高维合成空间。通过ChemDataExtractor 2.0和WebPlotDigitizer收集数百项RIG研究的数值与文本变量，构建多样化数据集。交叉验证显示，SoDip相较GPR提升约33%，并提供校准置信区间，可识别低重复性区域。其堆叠结构能融合质量参差的稀疏文本与数值输入，优于已有模型，为可重复、形态感知的接枝聚合物设计奠定基础。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。