Machine Learning-Optimized Laser Ablation for Gold Nanoparticle Synthesis

A 3.4-fold increase in investment-specific productivity for synthesizing 5 nm gold nanoparticles was achieved via machine learning-optimized laser ablation in liquid. The dataset, created by Runpeng Miao and published on figshare in April 2026, details the experimental parameters and outcomes of this green synthesis method. It compares the results to conventional chemical synthesis, showing the optimized process is four times cheaper for gram-scale production.

Use Cases

• Predict nanoparticle yield or productivity from laser ablation parameters like pulse energy and duration.
• Analyze correlations between synthesis conditions and nanoparticle properties such as size (5 nm), plasmon absorption intensity, and catalytic activity.
• Compare the cytocompatibility and surface thiol coverage of laser-synthesized nanoparticles against commercial counterparts.
• Model the cost and environmental impact trade-offs between laser ablation and the Turkevich–Frens chemical method.

Strengths

• Documents a specific 3.4-fold productivity increase over a previous benchmark for laser ablation synthesis.
• Provides a direct comparison of key nanoparticle properties (catalytic activity, plasmon absorption, cytocompatibility) against a commercial standard.
• Results are validated across multiple application domains: biomedicine, catalysis, and surface-enhanced spectroscopy (MALDI).

Limitations

• The dataset is very small at 43.4 KB, indicating limited scope and likely a small number of experimental runs.
• Specific experimental data columns, row counts, and raw measurements are not detailed in the available metadata.
• The temporal and geographic context of the data collection is not specified.

Provenance

Source

Runpeng Miao via figshare.

Collection Method

Data generated from machine learning-optimized laser ablation in liquid (LAL) experiments for gold nanoparticle synthesis.

Freshness

Last updated in April 2026, indicating recent publication.