Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Using Machine Learning to Detect Grapevine Disease in Wine Production

Vänglund, Ivar LU (2021) In Master’s Theses in Mathematical Sciences FMAM05 20211
Mathematics (Faculty of Engineering)
Abstract
When growing grapevines there are common risks for disease outbreaks when the pathogen has remained from earlier growing cycles and the weather and soil conditions work in the diseases' favour. The diseases may spread a lot before being highly noticeable. This means that the harvests of grapes for wine production are in jeopardy. This thesis concerns a branch of a, from the Swedish Board of Agriculture funded, project "IoT and AI to increase the competiveness in Swedish fruit and wine production" with the special focus for the thesis to use machine learning tools such as convolutional neural networks to detect the most common grapevine diseases downy mildew and powdery mildew. By using an image inventory from the project staff the purpose... (More)
When growing grapevines there are common risks for disease outbreaks when the pathogen has remained from earlier growing cycles and the weather and soil conditions work in the diseases' favour. The diseases may spread a lot before being highly noticeable. This means that the harvests of grapes for wine production are in jeopardy. This thesis concerns a branch of a, from the Swedish Board of Agriculture funded, project "IoT and AI to increase the competiveness in Swedish fruit and wine production" with the special focus for the thesis to use machine learning tools such as convolutional neural networks to detect the most common grapevine diseases downy mildew and powdery mildew. By using an image inventory from the project staff the purpose is to give decision support regarding the mentioned diseases of an input image using neural networks and image analysis. As being able to notice different types and stages of the grapevine diseases is desired, the network was sought to have 5 class outputs but also testing to have fewer (3 and 2). The resulting model, after training to reach a good validation accuracy, reached an accuracy of ∼65 % when predicting to 5 labels, but with lower recall on the infected classes with fewer image samples. Training for predicting 3 and 2 different outputs gave higher results of ∼70 % and ∼75 % respectively and better tendencies of finding non-healthy leaves. It is believed that a larger amount of training images could improve the performance of the network. (Less)
Please use this url to cite or link to this publication:
author
Vänglund, Ivar LU
supervisor
organization
course
FMAM05 20211
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Grapevine disease, Downy mildew, Powdery mildew, Image analysis, Deep learning, Convolutional neural network, Data augmentation
publication/series
Master’s Theses in Mathematical Sciences
report number
LUTFMA-3440-2021
ISSN
1404-6342
other publication id
2021:E13
language
English
id
9046108
date added to LUP
2021-06-03 14:39:01
date last changed
2021-06-03 14:39:01
@misc{9046108,
  abstract     = {{When growing grapevines there are common risks for disease outbreaks when the pathogen has remained from earlier growing cycles and the weather and soil conditions work in the diseases' favour. The diseases may spread a lot before being highly noticeable. This means that the harvests of grapes for wine production are in jeopardy. This thesis concerns a branch of a, from the Swedish Board of Agriculture funded, project "IoT and AI to increase the competiveness in Swedish fruit and wine production" with the special focus for the thesis to use machine learning tools such as convolutional neural networks to detect the most common grapevine diseases downy mildew and powdery mildew. By using an image inventory from the project staff the purpose is to give decision support regarding the mentioned diseases of an input image using neural networks and image analysis. As being able to notice different types and stages of the grapevine diseases is desired, the network was sought to have 5 class outputs but also testing to have fewer (3 and 2). The resulting model, after training to reach a good validation accuracy, reached an accuracy of ∼65 % when predicting to 5 labels, but with lower recall on the infected classes with fewer image samples. Training for predicting 3 and 2 different outputs gave higher results of ∼70 % and ∼75 % respectively and better tendencies of finding non-healthy leaves. It is believed that a larger amount of training images could improve the performance of the network.}},
  author       = {{Vänglund, Ivar}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master’s Theses in Mathematical Sciences}},
  title        = {{Using Machine Learning to Detect Grapevine Disease in Wine Production}},
  year         = {{2021}},
}