@article{MotmansBrent:ChemMater2026,
    author = {Motmans, Brent and Ghogare, Digvijay and van Wijk, Thijs G. I. and Van Herck, Joren 
             and Heidarian, Saba and De Meyer, Pieter and Smit, Berend and Hardy, An 
             and Vanpoucke, Danny E. P.},
    title = {{Predictive Inorganic Synthesis Based on Machine Learning Using Small Data Sets: 
             A Case Study of Hydrodynamic Diameter-Controlled Copper Nanoparticles}},
    journal = {Chem. Mater.},
    volume = {38},
    number = {21},
    pages = {10981--10993},
    year = {2026},
    month = {11},
    issn = {0897-4756},
    doi = {10.1021/acs.chemmater.6c01699},
    url = {https://doi.org/10.1021/acs.chemmater.6c01699},
    abstract = {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 DLS-derived hydrodynamic diameter
		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 hydrodynamic
		diameters with good predictive performance given the limited data
		set. Since quantitative regression requires a unique DLS-derived hydrodynamic
		diameter, the regression model is restricted to monomodal DLS distributions,
		while a complementary classification model identifies synthesis conditions
		for which quantitative prediction is applicable. Using equivalent
		out-of-sample validation (OOB and LOOCV), the ML and DoE models showed
		comparable generalization (MAE = 40.92 and 40.46 nm, respectively).
		The final ensemble model achieved an R2 of 0.74, an MAE of 23.81 nm, 
		compared to an R2 of 0.60, an MAE of 33.54 nm for the DoE model, while retaining
		the complete synthesis parameter space, making it better suited for
		synthesis guidance. Additionally, classification models using both
		random forests and large language models (LLMs) are evaluated to distinguish
		between large and small particles. These classification models exhibited
		only modest predictive performance, indicating that this small data
		set is insufficient to fully exploit the capabilities of complex LLMs.
		Overall, this study demonstrates that carefully curated small data
		sets, paired with robust classical ML, can effectively support the
		synthesis of Cu NPs and highlights that for lab-scale studies, complex
		models like LLMs may offer limited benefits. The validation experiments
		further indicate the potential of ML guided synthesis to improve the
		efficiency of experimental optimization and reduce resource consumption.},
}
