1. ABOUT THE DATASET -------------------- Title: Supporting data for "Universal prediction of molecular weight distribution for entangled linear polymers from linear rheology using neural networks" Creator(s): Robert J. Elliott[1,2] Luisa Cutillo[1], Johan Mattsson[3], and Daniel J. Read[1] Organisation(s): 1. School of Mathematics, University of Leeds, Leeds LS2 9JT, UK. 2. DPI, P.O. Box 902, 5600 AX Eindhoven, the Netherlands. 3. School of Physics and Astronomy, University of Leeds, Leeds LS2 9JT, UK Rights-holder(s):Unless otherwise stated, Copyright 2025 University of Leeds Publication Year: 2026 Supporting data for the associated article (Macromolecules 2026). This dataset, along with GUI software found at https://github.com/py19rje/MWD-Inference-GUI, enables the reproduction of the results from the related publication. The goal of the work is the universal prediction of the molecular weight distribution from the linear melt rheology of molten linear polymers. This dataset includes testing data which can be loaded into the GUI software to make MWD predictions as seen in the manuscript. Cite as: Robert J. Elliott, Luisa Cutillo, Luisa, Johan Mattsson, Daniel J. Read. (2026) Supporting data for "Universal prediction of molecular weight distribution for entangled linear polymers from linear rheology using neural networks". University of Leeds. [Dataset] https://doi.org/10.5518/1799 Related publication: Title: Universal prediction of molecular weight distribution for entangled linear polymers from linear rheology using neural networks; Authors: Robert J. Elliott, Luisa Cutillo, Johan Mattsson, and Daniel J. Read; Journal: Macromolecules; Year: 2026; Status: Accepted. Contact: Robert J. Elliott: py19rje@leeds.ac.uk 2. TERMS OF USE --------------- [A standard copyright notice and licence statement with URL can be used, e.g. Copyright [publication year] [University of Leeds, name of other rights-holder(s)]. Unless otherwise stated, this dataset is licensed under a Creative Commons Attribution 4.0 International Licence: https://creativecommons.org/licenses/by/4.0/.] 3. PROJECT AND FUNDING INFORMATION ---------------------------------- Title: Closing the Loop via Molecular Polymer Rheology Dates: 01/10/2023 - 30/09/2027 Funding organisation: DPI (Dutch Polymer Institute) Grant no.: 861 4. CONTENTS ----------- File listing Data folders: MWD_Data: -Contains GPC and MWD statistics for all polymer samples included in the associated article. - File names in the folder are in the format [sample name]_GPC.dat or [sample name]_MWD.dat. - Files with the GPC suffix have full MWD curves, and those with MWD are either monodisperse or bidisperse (these classes are discussed in the manuscript). - Monodisperse sample files each have one row with two tab-delimited data entries. The first is the weight-average mean molecular weight of the sample M_W, and the second is the PDI of the sample. -Bidisperse sample files have two rows, and each row has an additional entry in the first column for the volume fraction of the MWD component represented by that row. The following two entries in each row follows the monodisperse format (M_W \t PDI). Rheology_Data: - Contains the corresponding rheology data for all samples. - All file names are in the format [sample_name]_rheo.dat - The first row of each tab delimited data file has three entries: the rheology measurement temperature, the material of the sample e.g. PS for polystyrene, and a signifier of the class of the sample's MWD. 0 signifies that the sample is polydisperse, with 1 and 2 signifying monodisperse and bidisperse respectively. - The following rows also all contain three entries, which are firstly the frequency of the SAOS rheology measurement in radians per second, followed by the storage modulus G' and the the loss modulus G'' at the respective frequency. Other files: - Data_Sources.xlsx: Contains the source of the data for all samples. Many are from research papers and are cited accordingly, and others were provided by industrial partners of the funding organisation of this work, the DPI. 5. METHODS ---------- Data was sourced from academic papers in many cases, and are cited in Data_Sources.xlsx. Rheology experiments were all SAOS and details can be found via the relevant citation for each sample, other than for those provided by industrial partners, in which case experimental techniques are confidential. Details on GPC experiments and experimental determination of MWDs to produce the GPC and MWD files can also be found this way.