Impact of Dataset Diversity on Machine Learning Prediction of Reorganisation Energies in Organic Semiconductors

Malin Zollner; Tahereh Nematiaram; Yashar Moshfeghi

Impact of Dataset Diversity on Machine Learning Prediction of Reorganisation Energies in Organic Semiconductors

Malin Zollner
, Tahereh Nematiaram^*
, Yashar Moshfeghi

^*Corresponding author for this work

Research output: Contribution to conference › Poster

3 Downloads (Pure)

Abstract

This work investigates how input characteristics, particularly dataset diversity, affect the performance of machine learning algorithms in predicting hole and electron reorganisation energies, ultimately aiding the identification of promising organic semiconductors candidates.

Original language	English
Number of pages	1
Publication status	Published - 19 Jun 2025
Event	Scottish Computational Chemistry Symposium 2025 - University of Strathclyde, Glasgow, United Kingdom Duration: 19 Jun 2025 → 19 Jun 2025 https://www.scotch-research.com/sccs

Conference

Conference	Scottish Computational Chemistry Symposium 2025
Abbreviated title	ScotChem
Country/Territory	United Kingdom
City	Glasgow
Period	19/06/25 → 19/06/25
Internet address	https://www.scotch-research.com/sccs

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy
SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities
SDG 13 Climate Action

Keywords

organic semiconductors
machine learning
artificial intelligence
reorganisation energy

Access to Document

Zollner-etal-SCCS-2025-Impact-of-Dataset-Diversity-on-Machine-Learning-PredictionAccepted author manuscript, 1.23 MBLicence: CC BY 4.0

1 Active

Functional Materials Discovery Using Artificial Intelligence
Zollner, M. (Researcher), Nematiaram, T. (Principal Investigator) & Moshfeghi, Y. (Principal Investigator)
1/10/24 → 30/09/27
Project: Research - Studentship

ARCHIE-WeSt (UOSHPC)
Martin, R. (Manager)
University Of Strathclyde
Facility/equipment: Facility

1 Article

Learning the limits: how data, diversity, and representation control machine-learning predictions of reorganisation energy
Zollner, M., Moshfeghi, Y. & Nematiaram, T., 16 Apr 2026, In: Journal of Materials Chemistry. C . 14, 14, p. 5999-6011 13 p.
Research output: Contribution to journal › Article › peer-review

Open Access
File
1 Link opens in a new tab Citation (Scopus)

5 Downloads (Pure)

People's Choice Poster Prize
Zollner, M. (Recipient), Moshfeghi, Y. (Recipient) & Nematiaram, T. (Recipient), 19 Jun 2025
Prize: Prize (including medals and awards)

Cite this

@conference{a3182b0d2b744b2d86b4838289ce7b46,

title = "Impact of Dataset Diversity on Machine Learning Prediction of Reorganisation Energies in Organic Semiconductors",

abstract = "This work investigates how input characteristics, particularly dataset diversity, affect the performance of machine learning algorithms in predicting hole and electron reorganisation energies, ultimately aiding the identification of promising organic semiconductors candidates.",

keywords = "organic semiconductors, machine learning, artificial intelligence, reorganisation energy",

author = "Malin Zollner and Tahereh Nematiaram and Yashar Moshfeghi",

year = "2025",

month = jun,

day = "19",

language = "English",

note = "Scottish Computational Chemistry Symposium 2025, ScotChem ; Conference date: 19-06-2025 Through 19-06-2025",

url = "https://www.scotch-research.com/sccs",

}

TY - CONF

T1 - Impact of Dataset Diversity on Machine Learning Prediction of Reorganisation Energies in Organic Semiconductors

AU - Zollner, Malin

AU - Nematiaram, Tahereh

AU - Moshfeghi, Yashar

PY - 2025/6/19

Y1 - 2025/6/19

N2 - This work investigates how input characteristics, particularly dataset diversity, affect the performance of machine learning algorithms in predicting hole and electron reorganisation energies, ultimately aiding the identification of promising organic semiconductors candidates.

AB - This work investigates how input characteristics, particularly dataset diversity, affect the performance of machine learning algorithms in predicting hole and electron reorganisation energies, ultimately aiding the identification of promising organic semiconductors candidates.

KW - organic semiconductors

KW - machine learning

KW - artificial intelligence

KW - reorganisation energy

M3 - Poster

T2 - Scottish Computational Chemistry Symposium 2025

Y2 - 19 June 2025 through 19 June 2025

ER -

Impact of Dataset Diversity on Machine Learning Prediction of Reorganisation Energies in Organic Semiconductors

Abstract

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Projects

Functional Materials Discovery Using Artificial Intelligence

Equipment

ARCHIE-WeSt (UOSHPC)

Research output

Learning the limits: how data, diversity, and representation control machine-learning predictions of reorganisation energy

Prizes

People's Choice Poster Prize

Cite this