Polymeric soft materials - including thermoplastics, thermosets, elastomers, hydrogels, and composite systems -display intricate, multiscale behaviors resulting from their unique structural organization, history of processing, and dynamic responses to external stimuli. Gaining a comprehensive understanding of these behaviors is frequently constrained by the complexity of connecting experimental observations, theoretical models, and process variables across scales. This issue is particularly pronounced in polymer science, where features such as porosity, fiber orientation, crystallinity, and phase morphology, alongside diverse manufacturing methods (such as extrusion, additive manufacturing, injection and reaction injection molding, and curing), critically influence material performance. Effectively bridging these scales necessitates approaches that integrate physics, data, and design principles to deliver accurate and interpretable predictions of viscoelasticity, durability, and function. Recent advances in artificial intelligence (AI), machine learning (ML), and data-centric analyses provide promising pathways to more rapidly and precisely link polymer processing, microstructure, and properties.

This Research Topic seeks to gather pioneering research that leverages AI, ML, and data-driven techniques to model, characterize, and design polymeric soft materials, with a firm focus on elucidating structure–processing–property relationships. By unifying experiments, simulations, and advanced data analysis, the topic aims to establish a robust foundation for predictive modeling, microstructural discovery, and digital design tailored to polymer systems. We especially welcome studies that integrate physics-informed learning with expert knowledge in polymer processing (such as extrusion, additive manufacturing, injection/reaction injection molding, and curing) for minimizing defects, reducing cycle times, and boosting performance, as well as research automating the quantification of microstructural attributes—such as porosity, fiber orientation, and phase distribution—to strengthen the connection between process parameters and resulting properties. Emphasis on interpretability, uncertainty quantification, and broad applicability across different processing regimes is encouraged. Through these efforts, the Topic aspires to enable faster innovation and greater reliability in polymer and polymer-composite applications across research and industry.

To gather further insights in this area, we welcome submissions on, but not limited to, the following themes:

- Machine learning and data analytics for predicting viscoelastic, mechanical, and functional properties of polymeric materials and composites
- Automated image analysis for quantification of microstructural features such as porosity, fiber orientation, crystallinity, and phase morphology
- Generative and inverse design frameworks for architected polymers and polymer-based composites aimed at targeted performance characteristics
- Digital twins and physics-informed AI for optimizing polymer processing methods, including extrusion, additive manufacturing, injection molding, and reaction injection molding
- Integration of multiscale experimental and computational data to establish links between processing parameters, microstructure, and material performance
- Uncertainty quantification and interpretability in AI and ML models applied to polymer science
- Benchmark datasets, reproducibility protocols, and best practices for data-centric research in polymers

Contributions should focus on soft-matter phenomena within polymer systems and address the structure–processing–property paradigm. Submissions focused on fundamental biology, biotechnology, food technology, or organic synthesis are not within the scope of this Research Topic. Interdisciplinary contributions and cross-listing with the Gels and Self-Assembly and Self-Organisation sections are encouraged where relevant.

Are you interested in contributing a manuscript to this Research Topic?

Data-Driven Approach for Digital Design and Characterization in Polymeric Soft Matter