A Hybrid Machine Learning Model to Study UV-Vis Spectra of Gold Nanospheres

Abstract

Here, we have employed principal component analysis (PCA) and linear discriminant analysis (LDA) to analyze the Miecalculated UV-Vis spectra of gold nanospheres (GNS). Eigen spectra of PCA perform the Fano-type resonances. PCA vector spectra determine the 3D vector fields which reveal the homoclinic orbit strange attractor. Quantum confinement effects are observed by the 3D representation of LDA. Standing wave patterns resulting from oscillations of ion-acoustic phonon and electron waves are illustrated through the eigen spectra of LDA. Such capabilities of GNPs have brought high attention to the high energy density physics applications. Furthermore, accurate prediction of gold nanoparticle (GNP) sizes using machine learning could provide rapid analysis without the need for expensive analysis. Two hybrid algorithms consist of unsupervised PCA and two different supervised ANN have been used to estimate the diameters of GNPs. PCA-based artificial neural networks(ANN) were found to estimate the diameters with a high accuracy.

Instantaneous Property Prediction and Inverse Design of Plasmonic Nanostructures Using Machine Learning: Current Applications and Future Directions

“…Unsupervised training is expected to attract more research interest and application opportunities as the AI field progresses, as it requires less effort in data collection and learns at a high level of autonomy. An unsupervised approach is not commonly seen in plasmonics research, but it is found useful in the analysis of spectroscopic data and time-domain electromagnetic simulations [69][70][71]. Reinforcement learning (RL) is a reward-based training method that stochastically improves the candidate's performance while being guided by environmental feedback [72].…”

“…Fano resonance of the surface plasmon polariton can be interpreted from the PCA processed dataset, and the LDA results implied electron oscillation and quantum confinement effects. The PCA coordinates were further fed into the MLP network for gold nanosphere diameter prediction [69]. Ensemble ML is another method that assembles a few different models, together called an "ensemble".…”

Machine Learning-Based Interpretation of Optical Properties of Colloidal Gold with Convolutional Neural Networks

“…25−33 This has been done, for example, to find a suitable nanoparticle design that gives desired optical properties, 27,29−31 or to determine nanoparticle shape or size directly from their spectra or from descriptors such as λ SPR and FWHM. 25,28,29,32,33 One machine learning algorithm that is of particular interest for array-like data such as spectra or images, is convolutional neural network (CNN) architectures. CNNs can handle complex datatypes such as images or spectra as input, which often minimizes the need for dimensionality reduction and preprocessing.…”

Machine learning activation energies of chemical reactions

“…Outside of chemistry, ML has been applied in many circumstances including: natural language processing 36–39 ; driverless vehicles 40–44 speech recognition 45–48 ; handwriting analysis 49–51 ; enhancing image resolution 52–55 ; robotics 56–60 ; and, famously, beating the human champions of the games chess 61 and Go 62 . Within chemistry, an incomplete list of applications include: evaluating potential energy surfaces of ground 63–66 and excited states 67,68 ; forming solutions to the Schrödinger equation 69,70 ; modeling molecular wavefunctions 71,72 ; accelerating TS optimization 73,74 ; finding exchange‐correlation functionals for DFT 75,76 ; predicting reaction rate constants 77,78 ; predicting the outcomes of organic reactions 79–84 ; X‐ray, 85–87 UV–Vis, 88 IR, 89–92 and NMR 93–95 spectroscopies; sequence‐based biomolecular function prediction 96,97 and predictions of protein structures 98–101 . Another very recent and exciting application of ML in chemistry is the prediction of activation energies.…”