Portable NIR Spectroscopy Combined with Machine Learning for Kiwi Ripeness Classification: An Approach to Precision Farming

Portable NIR Spectroscopy Combined with Machine Learning for Kiwi Ripeness Classification: An Approach to Precision Farming

This study aims to evaluate and classify the ripening stages of yellow-fleshed kiwifruit by integrating spectral and physicochemical data collected from the pre-harvest phase through 60 days of storage. A portable near-infrared (NIR) spectrometer (900–1700 nm) was used to develop predictive models f...

Full description

Saved in:
Bibliographic Details
Main Authors: Giuseppe Altieri, Sabina Laveglia, Mahdi Rashvand, Francesco Genovese, Attilio Matera, Alba Nicoletta Mininni, Maria Calabritto, Giovanni Carlo Di Renzo
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
portable near-infrared spectroscopy
harvest quality prediction
fruit ripening classification
machine learning model
Online Access:https://www.mdpi.com/2076-3417/15/11/6233
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study aims to evaluate and classify the ripening stages of yellow-fleshed kiwifruit by integrating spectral and physicochemical data collected from the pre-harvest phase through 60 days of storage. A portable near-infrared (NIR) spectrometer (900–1700 nm) was used to develop predictive models for soluble solids content (SSC) and firmness (FF), testing multiple preprocessing methods within a Partial Least Squares Regression (PLSR) framework. SNV preprocessing achieved the best predictions for FF (R<sup>2</sup>P = 0.74, RMSEP = 12.342 ± 0.274 N), while the Raw-PLS model showed optimal performance for SSC (R<sup>2</sup>P = 0.93, RMSEP = 1.142 ± 0.022°Brix). SSC was more robustly predicted than FF, as reflected by RPD values of 2.6 and 1.7, respectively. For ripening stage classification, an Artificial Neural Network (ANN) outperformed other models, correctly classifying 97.8% of samples (R<sup>2</sup> = 0.95, RMSE = 0.08, MAE = 0.03). These results demonstrate the potential of combining NIR spectroscopy with AI techniques for non-destructive quality assessment and accurate ripeness discrimination. The integration of regression and classification models further supports the development of intelligent decision-support systems to optimize harvest timing and postharvest handling.
ISSN:2076-3417

Similar Items