ISIS Neutron and Muon Source Data Journal

Coupling of deep learning with SANS for the development of sustainable polymer-surfactant formulations

Abstract: Polymers and surfactants are ubiquitously used in combination across a range of industrial applications including drug delivery, agrichemicals and detergents. In particular, cleaning formulations in the UK represent a market exceeding more than 1 billion annually, and thus their footprint leaves various implications related to water and energy consumption. This proposal forms part of an EPSRC iCASE PhD 2025-2029 project (Jared Seaton) in partnership with Procter \& Gamble. The project seeks to place these formulations within the context of sustainability, with the goal of developing high performance formulations using renewably derived polymers. These formulations are typically complex multicomponent systems which comprise various polymers, anionic, cationic, and amphoteric surfactants. In this SANS proposal, we will implement a well-established microfluidic cell setup within our group at Imperial College London that will provide us with molecular information related to the size, shape, and aggregation of surfactant micelles across the polymer backbone. Mapping of large parameter spaces is typically time consuming and tedious and thus generating a high data throughput via microfluidics will enable coupling of this data with a convolutional neural network (CNN) for developing predictive models that will provide key indications into the properties of these formulations.

Principal Investigator: Professor Joao Cabral
Experimenter: Mr Luis Miguel Ginja Torquato
Local Contact: Dr Lauren Matthews
Experimenter: Mr Jared Seaton
Experimenter: Dr Gunjan Tyagi
Experimenter: Ms Ariana Wanvig Dot

DOI: 10.5286/ISIS.E.RB2610574

ISIS Experiment Number: RB2610574

Publisher: STFC ISIS Neutron and Muon Source

Data format: RAW/Nexus
Select the data format above to find out more about it.

Data Citation

The recommended format for citing this dataset in a research publication is as:
[author], [date], [title], [publisher], [doi]

For Example:
Professor Joao Cabral et al; (2026): Coupling of deep learning with SANS for the development of sustainable polymer-surfactant formulations, STFC ISIS Neutron and Muon Source, https://doi.org/10.5286/ISIS.E.RB2610574

Data is released under the CC-BY-4.0 license.