Saved in:
Bibliographic Details
Main Authors: Motmans, Brent, Ghogare, Digvijay, van Wijk, Thijs G. I., Van Herck, Joren, De Meyer, Pieter, Smit, Berend, Hardy, An, Vanpoucke, Danny E. P.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.16545
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908821973106688
author Motmans, Brent
Ghogare, Digvijay
van Wijk, Thijs G. I.
Van Herck, Joren
De Meyer, Pieter
Smit, Berend
Hardy, An
Vanpoucke, Danny E. P.
author_facet Motmans, Brent
Ghogare, Digvijay
van Wijk, Thijs G. I.
Van Herck, Joren
De Meyer, Pieter
Smit, Berend
Hardy, An
Vanpoucke, Danny E. P.
contents Copper nanoparticles (Cu NPs) have a broad applicability, yet their synthesis is sensitive to subtle changes in reaction parameters. This sensitivity, combined with the time- and resource-intensive nature of experimental optimization, poses a major challenge in achieving reproducible and size-controlled synthesis. While Machine Learning (ML) shows promise in materials research, its application is often limited by scarcity of large high-quality experimental data sets. This study explores ML to predict the size of Cu NPs from microwave-assisted polyol synthesis using a small data set of 25 in-house performed syntheses. Latin Hypercube Sampling is used to efficiently cover the parameter space while creating the experimental data set. Ensemble regression models successfully predict particle sizes with high accuracy ($R^2 = 0.74$), outperforming classical statistical approaches ($R^2 = 0.60$). Additionally, classification models using both random forests and Large Language Models (LLMs) are evaluated to distinguish between large and small particles. While random forests show moderate performance, LLMs offer no significant advantages under data-scarce conditions. Overall, this study demonstrates that carefully curated small data sets, paired with robust classical ML, can effectively predict the synthesis of Cu NPs and highlights that for lab-scale studies, complex models like LLMs may offer limited benefit over simpler techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16545
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Predictive Inorganic Synthesis based on Machine Learning using Small Data sets: a case study of size-controlled Cu Nanoparticles
Motmans, Brent
Ghogare, Digvijay
van Wijk, Thijs G. I.
Van Herck, Joren
De Meyer, Pieter
Smit, Berend
Hardy, An
Vanpoucke, Danny E. P.
Materials Science
Machine Learning
Copper nanoparticles (Cu NPs) have a broad applicability, yet their synthesis is sensitive to subtle changes in reaction parameters. This sensitivity, combined with the time- and resource-intensive nature of experimental optimization, poses a major challenge in achieving reproducible and size-controlled synthesis. While Machine Learning (ML) shows promise in materials research, its application is often limited by scarcity of large high-quality experimental data sets. This study explores ML to predict the size of Cu NPs from microwave-assisted polyol synthesis using a small data set of 25 in-house performed syntheses. Latin Hypercube Sampling is used to efficiently cover the parameter space while creating the experimental data set. Ensemble regression models successfully predict particle sizes with high accuracy ($R^2 = 0.74$), outperforming classical statistical approaches ($R^2 = 0.60$). Additionally, classification models using both random forests and Large Language Models (LLMs) are evaluated to distinguish between large and small particles. While random forests show moderate performance, LLMs offer no significant advantages under data-scarce conditions. Overall, this study demonstrates that carefully curated small data sets, paired with robust classical ML, can effectively predict the synthesis of Cu NPs and highlights that for lab-scale studies, complex models like LLMs may offer limited benefit over simpler techniques.
title Predictive Inorganic Synthesis based on Machine Learning using Small Data sets: a case study of size-controlled Cu Nanoparticles
topic Materials Science
Machine Learning
url https://arxiv.org/abs/2512.16545