A large-scale nanocrystal database with aligned synthesis and properties enabling generative inverse design

TL;DR

This paper introduces a large-scale aligned nanocrystal database and a generative AI model for inverse synthesis design, enabling efficient discovery of nanocrystal synthesis routes with validated experimental results.

Contribution

It presents the creation of the NSP database and NanoExtractor, a language model for extracting synthesis data, and demonstrates NanoDesigner’s ability to generate viable, novel synthesis routes.

Findings

NanoExtractor achieves 88% accuracy, outperforming existing models.

NanoDesigner successfully designs synthesis routes for various nanocrystals.

Counter-intuitive precursor ratios are experimentally validated.

Abstract

The synthesis of nanocrystals has been highly dependent on trial-and-error, due to the complex correlation between synthesis parameters and physicochemical properties. Although deep learning offers a potential methodology to achieve generative inverse design, it is still hindered by the scarcity of high-quality datasets that align nanocrystal synthesis routes with their properties. Here, we present the construction of a large-scale, aligned Nanocrystal Synthesis-Property (NSP) database and demonstrate its capability for generative inverse design. To extract structured synthesis routes and their corresponding product properties from literature, we develop NanoExtractor, a large language model (LLM) enhanced by well-designed augmentation strategies. NanoExtractor is validated against human experts, achieving a weighted average score of 88% on the test set, significantly outperforming chemistry-specialized (3%) and general-purpose LLMs (38%). The resulting NSP database contains nearly 160,000 aligned entries and serves as training data for our NanoDesigner, an LLM for inverse synthesis design. The generative capability of NanoDesigner is validated through the successful design of viable synthesis routes for both well-established PbSe nanocrystals and rarely reported MgF2 nanocrystals. Notably, the model recommends a counter-intuitive, non-stoichiometric precursor ratio (1:1) for MgF2 nanocrystals, which is experimentally confirmed as critical for suppressing byproducts. Our work bridges the gap between unstructured literature and data-driven synthesis, and also establishes a powerful human-AI collaborative paradigm for accelerating nanocrystal discovery.