Generative Machine Learning Models for the Deconvolution of Charge Carrier Dynamics in Organic Photovoltaic Cells

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Raymond, Li, Flora, Salim, Sijin, Wang, Brendan, Wright
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917055262883840
author Raymond, Li
Flora, Salim
Sijin, Wang
Brendan, Wright
author_facet Raymond, Li
Flora, Salim
Sijin, Wang
Brendan, Wright
contents Charge carrier dynamics critically affect the efficiency and stability of organic photovoltaic devices, but they are challenging to model with traditional analytical methods. We introduce \b{eta}-Linearly Decoded Latent Ordinary Differential Equations (\b{eta}-LLODE), a machine learning framework that disentangles and reconstructs extraction dynamics from time-resolved charge extraction measurements of P3HT:PCBM cells. This model enables the isolated analysis of the underlying charge carrier behaviour, which was found to be well described by a compressed exponential decay. Furthermore, the learnt interpretable latent space enables simulation, including both interpolation and extrapolation of experimental measurement conditions, offering a predictive tool for solar cell research to support device study and optimisation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01118
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Machine Learning Models for the Deconvolution of Charge Carrier Dynamics in Organic Photovoltaic Cells
Raymond, Li
Flora, Salim
Sijin, Wang
Brendan, Wright
Materials Science
Machine Learning
82D20, 62H25, 37M05
I.2.6; I.5.3; I.6.5; G.3
Charge carrier dynamics critically affect the efficiency and stability of organic photovoltaic devices, but they are challenging to model with traditional analytical methods. We introduce \b{eta}-Linearly Decoded Latent Ordinary Differential Equations (\b{eta}-LLODE), a machine learning framework that disentangles and reconstructs extraction dynamics from time-resolved charge extraction measurements of P3HT:PCBM cells. This model enables the isolated analysis of the underlying charge carrier behaviour, which was found to be well described by a compressed exponential decay. Furthermore, the learnt interpretable latent space enables simulation, including both interpolation and extrapolation of experimental measurement conditions, offering a predictive tool for solar cell research to support device study and optimisation.
title Generative Machine Learning Models for the Deconvolution of Charge Carrier Dynamics in Organic Photovoltaic Cells
topic Materials Science
Machine Learning
82D20, 62H25, 37M05
I.2.6; I.5.3; I.6.5; G.3
url https://arxiv.org/abs/2511.01118