Detection of Apple Proliferation Disease Using Hyperspectral Imaging and Machine Learning Techniques

Apple proliferation is among the most important diseases in European fruit production. Early and reliable detection enables farmers to respond appropriately and to prevent further spreading of the disease. Traditional phenotyping approaches by human observers consider multiple symptoms, but these ar...

Full description

Saved in:
Bibliographic Details
Main Authors: Uwe Knauer, Sebastian Warnemünde, Patrick Menz, Bonito Thielert, Lauritz Klein, Katharina Holstein, Miriam Runne, Wolfgang Jarausch
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7774
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849220391972634624
author Uwe Knauer
Sebastian Warnemünde
Patrick Menz
Bonito Thielert
Lauritz Klein
Katharina Holstein
Miriam Runne
Wolfgang Jarausch
author_facet Uwe Knauer
Sebastian Warnemünde
Patrick Menz
Bonito Thielert
Lauritz Klein
Katharina Holstein
Miriam Runne
Wolfgang Jarausch
author_sort Uwe Knauer
collection DOAJ
description Apple proliferation is among the most important diseases in European fruit production. Early and reliable detection enables farmers to respond appropriately and to prevent further spreading of the disease. Traditional phenotyping approaches by human observers consider multiple symptoms, but these are difficult to measure automatically in the field. Therefore, the potential of hyperspectral imaging in combination with data analysis by machine learning algorithms was investigated to detect the symptoms solely based on the spectral signature of collected leaf samples. In the growing seasons 2019 and 2020, a total of 1160 leaf samples were collected. Hyperspectral imaging with a dual camera setup in spectral bands from 400 nm to 2500 nm was accompanied with subsequent PCR analysis of the samples to provide reference data for the machine learning approaches. Data processing consists of preprocessing for segmentation of the leaf area, feature extraction, classification and subsequent analysis of relevance of spectral bands. The results show that imaging multiple leaves of a tree enhances detection results, that spectral indices are a robust means to detect the diseased trees, and that the potentials of the full spectral range can be exploited using machine learning approaches. Classification models like rRBF achieved an accuracy of 0.971 in a controlled environment with stratified data for a single variety. Combined models for multiple varieties from field test samples achieved classification accuracies of 0.731. Including spatial distribution of spectral data further improves the results to 0.751. Prediction of qPCR results by regression based on spectral data achieved RMSE of 14.491 phytoplasma per plant cell.
format Article
id doaj-art-9d41a9e49dce43b5bc936eb2bcec5402
institution Kabale University
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-9d41a9e49dce43b5bc936eb2bcec54022024-12-13T16:32:44ZengMDPI AGSensors1424-82202024-12-012423777410.3390/s24237774Detection of Apple Proliferation Disease Using Hyperspectral Imaging and Machine Learning TechniquesUwe Knauer0Sebastian Warnemünde1Patrick Menz2Bonito Thielert3Lauritz Klein4Katharina Holstein5Miriam Runne6Wolfgang Jarausch7Department of Agriculture, Ecotrophology and Landscape Development, Anhalt University of Applied Sciences, 06406 Bernburg, GermanyCognitive Processes and Systems, Fraunhofer Institute for Factory Operation and Automation IFF, 39106 Magdeburg, GermanyCognitive Processes and Systems, Fraunhofer Institute for Factory Operation and Automation IFF, 39106 Magdeburg, GermanyCognitive Processes and Systems, Fraunhofer Institute for Factory Operation and Automation IFF, 39106 Magdeburg, GermanyCognitive Processes and Systems, Fraunhofer Institute for Factory Operation and Automation IFF, 39106 Magdeburg, GermanyDepartment of Computer Science and Languages, Anhalt University of Applied Sciences, 06366 Köthen, GermanyRLP AgroScience, 67435 Neustadt an der Weinstrasse, GermanyRLP AgroScience, 67435 Neustadt an der Weinstrasse, GermanyApple proliferation is among the most important diseases in European fruit production. Early and reliable detection enables farmers to respond appropriately and to prevent further spreading of the disease. Traditional phenotyping approaches by human observers consider multiple symptoms, but these are difficult to measure automatically in the field. Therefore, the potential of hyperspectral imaging in combination with data analysis by machine learning algorithms was investigated to detect the symptoms solely based on the spectral signature of collected leaf samples. In the growing seasons 2019 and 2020, a total of 1160 leaf samples were collected. Hyperspectral imaging with a dual camera setup in spectral bands from 400 nm to 2500 nm was accompanied with subsequent PCR analysis of the samples to provide reference data for the machine learning approaches. Data processing consists of preprocessing for segmentation of the leaf area, feature extraction, classification and subsequent analysis of relevance of spectral bands. The results show that imaging multiple leaves of a tree enhances detection results, that spectral indices are a robust means to detect the diseased trees, and that the potentials of the full spectral range can be exploited using machine learning approaches. Classification models like rRBF achieved an accuracy of 0.971 in a controlled environment with stratified data for a single variety. Combined models for multiple varieties from field test samples achieved classification accuracies of 0.731. Including spatial distribution of spectral data further improves the results to 0.751. Prediction of qPCR results by regression based on spectral data achieved RMSE of 14.491 phytoplasma per plant cell.https://www.mdpi.com/1424-8220/24/23/7774hyperspectralrandom forestmachine learningapple‘<i>Candidatus</i> Phytoplasma mali’disease monitoring
spellingShingle Uwe Knauer
Sebastian Warnemünde
Patrick Menz
Bonito Thielert
Lauritz Klein
Katharina Holstein
Miriam Runne
Wolfgang Jarausch
Detection of Apple Proliferation Disease Using Hyperspectral Imaging and Machine Learning Techniques
Sensors
hyperspectral
random forest
machine learning
apple
‘<i>Candidatus</i> Phytoplasma mali’
disease monitoring
title Detection of Apple Proliferation Disease Using Hyperspectral Imaging and Machine Learning Techniques
title_full Detection of Apple Proliferation Disease Using Hyperspectral Imaging and Machine Learning Techniques
title_fullStr Detection of Apple Proliferation Disease Using Hyperspectral Imaging and Machine Learning Techniques
title_full_unstemmed Detection of Apple Proliferation Disease Using Hyperspectral Imaging and Machine Learning Techniques
title_short Detection of Apple Proliferation Disease Using Hyperspectral Imaging and Machine Learning Techniques
title_sort detection of apple proliferation disease using hyperspectral imaging and machine learning techniques
topic hyperspectral
random forest
machine learning
apple
‘<i>Candidatus</i> Phytoplasma mali’
disease monitoring
url https://www.mdpi.com/1424-8220/24/23/7774
work_keys_str_mv AT uweknauer detectionofappleproliferationdiseaseusinghyperspectralimagingandmachinelearningtechniques
AT sebastianwarnemunde detectionofappleproliferationdiseaseusinghyperspectralimagingandmachinelearningtechniques
AT patrickmenz detectionofappleproliferationdiseaseusinghyperspectralimagingandmachinelearningtechniques
AT bonitothielert detectionofappleproliferationdiseaseusinghyperspectralimagingandmachinelearningtechniques
AT lauritzklein detectionofappleproliferationdiseaseusinghyperspectralimagingandmachinelearningtechniques
AT katharinaholstein detectionofappleproliferationdiseaseusinghyperspectralimagingandmachinelearningtechniques
AT miriamrunne detectionofappleproliferationdiseaseusinghyperspectralimagingandmachinelearningtechniques
AT wolfgangjarausch detectionofappleproliferationdiseaseusinghyperspectralimagingandmachinelearningtechniques