Differentiable Hybrid Modelling for Learning and Optimising Chemical Transport Processes from Experimental Data
Abstract
Transport models underpin the design and optimisation of chemical processes, yet their constitutive laws are typically hand-picked, their experimental initial conditions are assumed exact, and their computational cost restricts optimisation to a handful of process variables. Here we introduce a differentiable hybrid modelling framework that embeds neural networks within a GPU-accelerated population balance equation solver to discover constitutive laws and assimilate initial conditions directly from experimental crystallisation data. Using thirteen real experiments with multi-dimensional size and shape measurements, we show that treating measured initial conditions as exact yields a physically inconsistent rate law despite improved predictive accuracy, whereas assimilating them recovers a physically consistent, non-linear law and reduces trajectory error sevenfold relative to conventional modelling. End-to-end differentiability further enables gradient-based optimisation of high-dimensional operating profiles, identifying a 300-variable temperature profile that reduces crystal aspect ratio by 25% at constant mass, facilitating superior product attributes. Our framework augments, rather than replaces, mechanistic modelling, offering a general route to learning transport models from data and optimising processes with them.
Related
- Enhancing Equity in Multimodal Public Transport: Optimising Electric-Bus Transfer Stations
- Training Non-Differentiable Networks via Optimal Transport
- Equation free data-driven modelling of chaotic processes
- Kriging and Gaussian processes: interconnected frameworks for spatial modelling and prediction
- New Modelling and Solution Frameworks for Multiple Objectives, Decomposability and Impulsivity in Continuous-time Markov Decision Processes
BibTeX
@misc{jessop2026differentiable,
title = {{Differentiable Hybrid Modelling for Learning and Optimising Chemical Transport Processes from Experimental Data}},
author = {Arthur Jessop and Mohammed Alsubeihi and Ben Moseley and Ashwin Kumar Rajagopalan},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.04011},
eprint = {2609.04011},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.04011},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Differentiable Hybrid Modelling for Learning and Optimising Chemical Transport Processes from Experimental Data
AU - Arthur Jessop
AU - Mohammed Alsubeihi
AU - Ben Moseley
AU - Ashwin Kumar Rajagopalan
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2609.04011
UR - https://arxiv.org/abs/2609.04011
AB - Transport models underpin the design and optimisation of chemical processes, yet their constitutive laws are typically hand-picked, their experimental initial conditions are assumed exact, and their computational cost restricts optimisation to a handful of process variables. Here we introduce a differentiable hybrid modelling framework that embeds neural networks within a GPU-accelerated population balance equation solver to discover constitutive laws and assimilate initial conditions directly from experimental crystallisation data. Using thirteen real experiments with multi-dimensional size and shape measurements, we show that treating measured initial conditions as exact yields a physically inconsistent rate law despite improved predictive accuracy, whereas assimilating them recovers a physically consistent, non-linear law and reduces trajectory error sevenfold relative to conventional modelling. End-to-end differentiability further enables gradient-based optimisation of high-dimensional operating profiles, identifying a 300-variable temperature profile that reduces crystal aspect ratio by 25% at constant mass, facilitating superior product attributes. Our framework augments, rather than replaces, mechanistic modelling, offering a general route to learning transport models from data and optimising processes with them.
ER -