The digitalization of the agrifood market is increasingly demanding for new technologies to support its transition towards smart agriculture, a sustainable food industry, and efficient management of greenhouses and crop breeding. In this work, we aim to exploit two emerging and promising technologies with application to the early detection of stressful conditions in plants. Two high-resolution near-infrared spectrometers, spanning the range from 1350 nm to 2150 nm, were used to acquire the reflectance spectra from a pothos (Epipremnum aureum) in two different hydration conditions, i.e., normal and anomalous. Then, we trained a machine learning model, i.e., a β-variational autoencoder (β-VAE), to identify the anomalies in the hydration of the plant over three months of acquisition. We are able to show the feasibility of our proposed combination of near-infrared spectrometry and the β-VAE to accurately identify anomalies, i.e., to detect stressful conditions in plants. This contributes to the recent and promising advancements in smart agriculture, by exploiting a new generation of high-resolution, portable, and non-destructive near-infrared sensing technology and powerful machine learning data analytics.

Zancanaro, A., Cisotto, G., Tegegn, D., Manzoni, S., Reguzzoni, I., Lotti, E., et al. (2022). Variational Autoencoder for Early Stress Detection in Smart Agriculture: A Pilot Study. In 2022 IEEE Workshop on Metrology for Agriculture and Forestry, MetroAgriFor 2022 - Proceedings (pp.126-130). Institute of Electrical and Electronics Engineers Inc. [10.1109/MetroAgriFor55389.2022.9964641].

Variational Autoencoder for Early Stress Detection in Smart Agriculture: A Pilot Study

Cisotto G.
Secondo
;
Tegegn D. D.;Manzoni S. L.;Zoppis I.
2022

Abstract

The digitalization of the agrifood market is increasingly demanding for new technologies to support its transition towards smart agriculture, a sustainable food industry, and efficient management of greenhouses and crop breeding. In this work, we aim to exploit two emerging and promising technologies with application to the early detection of stressful conditions in plants. Two high-resolution near-infrared spectrometers, spanning the range from 1350 nm to 2150 nm, were used to acquire the reflectance spectra from a pothos (Epipremnum aureum) in two different hydration conditions, i.e., normal and anomalous. Then, we trained a machine learning model, i.e., a β-variational autoencoder (β-VAE), to identify the anomalies in the hydration of the plant over three months of acquisition. We are able to show the feasibility of our proposed combination of near-infrared spectrometry and the β-VAE to accurately identify anomalies, i.e., to detect stressful conditions in plants. This contributes to the recent and promising advancements in smart agriculture, by exploiting a new generation of high-resolution, portable, and non-destructive near-infrared sensing technology and powerful machine learning data analytics.
slide + paper
anomaly detection; deep learning; near-infrared spectrometry; smart agriculture; Variational autoencoder;
English
2022 IEEE Workshop on Metrology for Agriculture and Forestry, MetroAgriFor 2022 - 3 November 2022 through 5 November 2022
2022
2022 IEEE Workshop on Metrology for Agriculture and Forestry, MetroAgriFor 2022 - Proceedings
978-1-6654-6998-2
2022
126
130
reserved
Zancanaro, A., Cisotto, G., Tegegn, D., Manzoni, S., Reguzzoni, I., Lotti, E., et al. (2022). Variational Autoencoder for Early Stress Detection in Smart Agriculture: A Pilot Study. In 2022 IEEE Workshop on Metrology for Agriculture and Forestry, MetroAgriFor 2022 - Proceedings (pp.126-130). Institute of Electrical and Electronics Engineers Inc. [10.1109/MetroAgriFor55389.2022.9964641].
File in questo prodotto:
File Dimensione Formato  
Zancanaro-2022-MetroAgriFor-VoR.pdf

Solo gestori archivio

Descrizione: Intervento a convegno
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Tutti i diritti riservati
Dimensione 5.51 MB
Formato Adobe PDF
5.51 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/400839
Citazioni
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
Social impact