Samenvatting
The thesis presents the application of machine learning techniques to solve a real world challenge related to pest and disease control in the agricultural sector.
The research is divided into three areas:
i). We developed algorithms to auto-diagnose diseases in crops using an image dataset captured with a mobile phone camera. The study looked into disease incidence and severity measurements from cassava leaf images. We applied computer vision techniques to extract visual features of color and shape combined with classification techniques.
(ii). We investigated on the diagnosis of disease in crops before they become symptomatic by use of spectrograms. The experiments of this study involved growing cassava plants in a screen house where they were inoculated with disease viruses and we monitored the plants over time collecting both spectral and plant tissue for wet chemistry analysis at each time step until the plants show disease. Our models in our case GMLVQ were able to detect cassava diseases one week after virus infection can be confirmed by wet lab chemistry, but several weeks before symptoms manifest on the plants.
(iii). We investigated on the development of a low-cost 3-D printed smartphone add-on spectrometer that can be used to diagnose crop diseases in the fields. Moving from a commercial spectrometer (1000 USD), the study presented a tool that should be cheap (less than 5 USD ) and usable by smallholder farmers, thus improving their livelihoods through increased crop yields and food security.
The research is divided into three areas:
i). We developed algorithms to auto-diagnose diseases in crops using an image dataset captured with a mobile phone camera. The study looked into disease incidence and severity measurements from cassava leaf images. We applied computer vision techniques to extract visual features of color and shape combined with classification techniques.
(ii). We investigated on the diagnosis of disease in crops before they become symptomatic by use of spectrograms. The experiments of this study involved growing cassava plants in a screen house where they were inoculated with disease viruses and we monitored the plants over time collecting both spectral and plant tissue for wet chemistry analysis at each time step until the plants show disease. Our models in our case GMLVQ were able to detect cassava diseases one week after virus infection can be confirmed by wet lab chemistry, but several weeks before symptoms manifest on the plants.
(iii). We investigated on the development of a low-cost 3-D printed smartphone add-on spectrometer that can be used to diagnose crop diseases in the fields. Moving from a commercial spectrometer (1000 USD), the study presented a tool that should be cheap (less than 5 USD ) and usable by smallholder farmers, thus improving their livelihoods through increased crop yields and food security.
| Originele taal-2 | English |
|---|---|
| Kwalificatie | Doctor of Philosophy |
| Toekennende instantie |
|
| Begeleider(s)/adviseur |
|
| Datum van toekenning | 28-aug.-2020 |
| Plaats van publicatie | [Groningen] |
| Uitgever | |
| Gedrukte ISBN's | 978-94-034-2637-2 |
| Elektronische ISBN's | 978-94-034-2636-5 |
| DOI's | |
| Status | Published - 2020 |