Deep Learning Approach for Raman Spectroscopy

Abstract

Raman spectroscopy is a widely used technique for organic and inorganic chemical material identification. Throughout the last century, major improvements in lasers, spectrometers, detectors, and holographic optical components have uplifted Raman spectroscopy as an effective device for a variety of different applications including fundamental chemical and material research, medical diagnostics, bio-science, in-situ process monitoring and planetary investigations. Undoubtedly, mathematical data analysis has been playing a vital role to speed up the migration of Raman spectroscopy to explore different applications. It supports researchers to customize spectral interpretation and overcome the limitations of the physical components in the Raman instrument. However, large, and complex datasets, interferences from instrumentation noise and sample properties which mask the true features of samples still make Raman spectroscopy as a challenging tool. Deep learning is a powerful machine learning strategy to build exploratory and predictive models from large raw datasets and has gained more attention in chemical research over recent years. This chapter demonstrates the application of deep learning techniques for Raman signal-extraction, feature-learning and modelling complex relationships as a support to researchers to overcome the challenges in Raman based chemical analysis.

A new approach to Fourier transform Raman: Identification of haploids in maize (Zea mays)

“…During this period, the molecule is temporarily elevated to a higher energy level, called the “virtual state or excited state.” Subsequently, the molecule returns to a lower energy state after the light is scattered (Knorr et al, 2010). The difference in energy between the incident light and the scattered light is what is measured in Raman spectroscopy (Jinadasa et al, 2021; Kafle, 2020).…”

“…Raman spectroscopy is a well‐known technique in studies related to the physical characteristics of objects, including work showing the quantification of DNA (Kafle, 2020; Liland et al, 2016). This technique investigates the molecular and structural constituents of the samples and allows the detection of physical, biochemical and molecular changes and may be an option in the differentiation of diploid and haploid kernels (Colthup & Daly, 1975; Compton, 1923;Jinadasa et al, 2021; Kafle, 2020).…”

From Characterization to Discovery: Artificial Intelligence, Machine Learning and High-Throughput Experiments for Heterogeneous Catalyst Design

“…As for the actual processing of the spectra, Lussier et al (2020) provide a guide for multiple ML algorithms (LDA, NN, SVM, kNN, and RF) in Raman Spectroscopy that have been applied to many areas in chemistry not necessarily related to catalysis such as food analysis and health sciences . Wathshala N. Jinadasa et al (2022) provide a thorough guide on deep learning algorithms coupled with Raman for material identification and discovery …”