Rapid Assessment of Anthocyanins Content of Onion Waste through Visible-Near-Short-Wave and Mid-Infrared Spectroscopy Combined with Machine Learning Techniques

Abstract

A sustainable process for valorization of onion waste would need to entail preliminary sorting out of exhausted or suboptimal material as part of decision-making. In the present study, an approach for monitoring red onion skin (OS) phenolic composition was investigated through Visible Near-Short-Wave infrared (VNIR-SWIR) (350–2500 nm) and Fourier-Transform-Mid-Infrared (FT-MIR) (4000–600 cm−1) spectral analyses and Machine-Learning (ML) methods. Our stepwise approach consisted of: (i) chemical analyses to obtain reference values for Total Phenolic Content (TPC) and Total Monomeric Anthocyanin Content (TAC); (ii) spectroscopic analysis and creation of OS spectral libraries; (iii) generation of calibration and validation datasets; (iv) spectral exploratory analysis and regression modeling via several ML algorithms; and (v) model performance evaluation. Among all, the k-nearest neighbors model from 1st derivative VNIR-SWIR spectra at 350–2500 nm resulted promising for the prediction of TAC (R2 = 0.82, RMSE = 0.52 and RPIQ = 3.56). The 2nd derivative FT-MIR spectral fingerprint among 600–900 and 1500–1600 cm−1 proved more informative about the inherent phenolic composition of OS. Overall, the diagnostic value and predictive accuracy of our spectral data support the perspective of employing non-destructive spectroscopic tools in real-time quality control of onion waste.

Machine learning prediction of organic moieties from the IR spectra, enhanced by additionally using the derivative IR data

“…One such prominent example is the machine-learning assisted identification of functional groups from the IR spectrum [12][13][14][15][16]. Additionally, machine learning has also been employed in: the determination of the secondary protein structures [17], classification of food powders in continuous process, prediction of pellet quality, characterization of mixed plastic wastes, classification of chromoblastomycosis agents, rapid identification of pit mud, characterization of surface microstructure of complex materials, prediction of quality-related parameters of instant tea, biodiesel analysis and rapid determination of anthocyanins content in onion waste [18][19][20][21][22][23][24][25][26]. Machine learning models were also successfully applied in combination with other spectroscopic techniques [27][28][29][30][31].…”