Intelligent control of nanoparticle synthesis through machine learning

Lv, Honglin; Chen, Xueye

doi:10.1039/d2nr00124a

Cited by 36 publications

(25 citation statements)

References 148 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite its increasing popularity, MLguided design of inorganic NPs has just emerged and only a handful of publications are available on ML-mediated Au NP synthesis. 49,50 We foresee that improved knowledge from a complete characterization of the NPs and their ligand shells (in 3D and in solution) can be used to train ML routines, which in turn will predict synthetic routes for NPs with the desired composition, surface chemistry, and properties.…”

Section: Discussionmentioning

confidence: 99%

Surfactant Layers on Gold Nanorods

et al. 2023

View full text Add to dashboard Cite

Conspectus Gold nanorods (Au NRs) are an exceptionally promising tool in nanotechnology due to three key factors: (i) their strong interaction with electromagnetic radiation, stemming from their plasmonic nature, (ii) the ease with which the resonance frequency of their longitudinal plasmon mode can be tuned from the visible to the near-infrared region of the electromagnetic spectrum based on their aspect ratio, and (iii) their simple and cost-effective preparation through seed-mediated chemical growth. In this synthetic method, surfactants play a critical role in controlling the size, shape, and colloidal stability of Au NRs. For example, surfactants can stabilize specific crystallographic facets during the formation of Au NRs, leading to the formation of NRs with specific morphologies. The process of surfactant adsorption onto the NR surface may result in various assemblies of surfactant molecules, such as spherical micelles, elongated micelles, or bilayers. Again, the assembly mode is critical toward determining the further availability of the Au NR surface to the surrounding medium. Despite its importance and a great deal of research effort, the interaction between Au NPs and surfactants remains insufficiently understood, because the assembly process is influenced by numerous factors, including the chemical nature of the surfactant, the surface morphology of Au NPs, and solution parameters. Therefore, gaining a more comprehensive understanding of these interactions is essential to unlock the full potential of the seed-mediated growth method and the applications of plasmonic NPs. A plethora of characterization techniques have been applied to reach such an understanding, but many open questions remain. In this Account, we review the current knowledge on the interactions between surfactants and Au NRs. We briefly introduce the state-of-the-art methods for synthesizing Au NRs and highlight the crucial role of cationic surfactants during this process. The self-assembly and organization of surfactants on the Au NR surface is then discussed to better understand their role in seed-mediated growth. Subsequently, we provide examples and elucidate how chemical additives can be used to modulate micellar assemblies, in turn allowing for a finer control over the growth of Au NRs, including chiral NRs. Next, we review the main experimental characterization and computational modeling techniques that have been applied to shed light on the arrangement of surfactants on Au NRs and summarize the advantages and disadvantages for each technique. The Account ends with a “Conclusions and Outlook” section, outlining promising future research directions and developments that we consider are still required, mostly related to the application of electron microscopy in liquid and in 3D. Finally, we remark on the potential of exploiting machine learning techniques to predict synthetic routes for NPs with predefined structures and properties.

show abstract

Section: Discussionmentioning

confidence: 99%

Surfactant Layers on Gold Nanorods

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Interested readers can find more information on these algorithms in some excellent published reviews. 36,69,[85][86][87][88][89][90][91][92] In summary, the major thrust of the ML approach here is to reduce time to discovery, and to expedite the transition of impactful discoveries from the lab and into the real world. In the context of QD devices, and our pressing need to bring energyefficient products to market, we can see the attraction of bringing AI into the fold.…”

Section: Automation Algorithms and Artificial Intelligencementioning

confidence: 99%

“…Interested readers can find more information on these algorithms in some excellent published reviews. 36,69,85–92…”

Section: How Can We Approach Data-driven Discovery?mentioning

confidence: 99%

Accelerating colloidal quantum dot innovation with algorithms and automation

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Recurrent (RNN) and function fitting (ANN-FF) networks are frequently used. [31][32][33][34][35][36][37][38][39] In this present work, ANN-FF procedure has been employed due to the static nature of our system and because of its ability to understand and forecast complex systems. Although ANN is quite competent in grasping the data but not so competent to understand the meaning of every neuron and its load.…”

Section: Introductionmentioning

confidence: 99%