Early Detection of Coffee Leaf Rust Caused by <i>Hemileia vastatrix</i> Using Multispectral Images
Conventional methodology in the field for the sampling of coffee leaf rust, caused by <i>Hemileia vastatrix</i>, has proven to be impractical. This paper proposes a method for the early detection of this disease, which is the most significant pathogen of coffee plants worldwide, using mu...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/12/12/2911 |
| _version_ | 1797461892465164288 |
|---|---|
| author | Analis da Silva Soares Bruno Sérgio Vieira Thalita Almeida Bezerra George Deroco Martins Ana Carolina Silva Siquieroli |
| author_facet | Analis da Silva Soares Bruno Sérgio Vieira Thalita Almeida Bezerra George Deroco Martins Ana Carolina Silva Siquieroli |
| author_sort | Analis da Silva Soares |
| collection | DOAJ |
| description | Conventional methodology in the field for the sampling of coffee leaf rust, caused by <i>Hemileia vastatrix</i>, has proven to be impractical. This paper proposes a method for the early detection of this disease, which is the most significant pathogen of coffee plants worldwide, using multispectral images acquired using a Mapir Survey3W camera and an unmanned aerial vehicle (UAV). For this purpose, 160 coffee seedlings of the coffee cultivar ‘Mundo Novo’ were inoculated with urediniospores of <i>H. vastatrix</i> and compared with 160 control (non-inoculated) seedlings to determine the most favorable interval for distinguishing healthy and infected plants. The 320 seedlings were placed on a dark surface to perform the imaging flights. In vitro analyses of the physiological parameters of 20 specimens were then performed for each condition (inoculated/non-inoculated) to obtain the hyperspectral curves, and this process was repeated three times at 15, 30, and 45 days after inoculation (DAI). Based on the simulated hyperspectral curves, a discrepancy between the red and near-infrared (NIR) bands was identified at 15 DAI, with the inoculated plants showing greater absorption in the red band and a greater spectral response in the NIR band. Thus, multispectral images were able to distinguish <i>H. vastatrix</i> infection in coffee seedlings at an asymptomatic stage (15 DAI) using a support vector machines (SVM) algorithm. Detection accuracy was 80% and the Kappa index of agreement was moderate (0.6). The early detection of this pathogen in the field using low-cost technology can be an important tool for the monitoring of coffee leaf rust and, consequently, a more sustainable management of the pathogen, causing farmers to make applications of chemical fungicides only when necessary. |
| first_indexed | 2024-03-09T17:25:52Z |
| format | Article |
| id | doaj.art-4893a5d6d7a0451cb856167719b5ad1b |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-09T17:25:52Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-4893a5d6d7a0451cb856167719b5ad1b2023-11-24T12:43:10ZengMDPI AGAgronomy2073-43952022-11-011212291110.3390/agronomy12122911Early Detection of Coffee Leaf Rust Caused by <i>Hemileia vastatrix</i> Using Multispectral ImagesAnalis da Silva Soares0Bruno Sérgio Vieira1Thalita Almeida Bezerra2George Deroco Martins3Ana Carolina Silva Siquieroli4Graduate Program in Agriculture and Geospatial Information, Institute of Agrarian Sciences, (Universidade Federal de Uberlândia), Monte Carmelo 38500-000, BrazilInstitute of Agrarian Sciences (Universidade Federal de Uberlândia), Monte Carmelo 38500-000, BrazilInstitute of Agrarian Sciences (Universidade Federal de Uberlândia), Monte Carmelo 38500-000, BrazilInstitute of Geography (Universidade Federal de Uberlândia), Monte Carmelo 38500-000, BrazilInstitute of Biotechnology (Universidade Federal de Uberlândia), Monte Carmelo 38500-000, BrazilConventional methodology in the field for the sampling of coffee leaf rust, caused by <i>Hemileia vastatrix</i>, has proven to be impractical. This paper proposes a method for the early detection of this disease, which is the most significant pathogen of coffee plants worldwide, using multispectral images acquired using a Mapir Survey3W camera and an unmanned aerial vehicle (UAV). For this purpose, 160 coffee seedlings of the coffee cultivar ‘Mundo Novo’ were inoculated with urediniospores of <i>H. vastatrix</i> and compared with 160 control (non-inoculated) seedlings to determine the most favorable interval for distinguishing healthy and infected plants. The 320 seedlings were placed on a dark surface to perform the imaging flights. In vitro analyses of the physiological parameters of 20 specimens were then performed for each condition (inoculated/non-inoculated) to obtain the hyperspectral curves, and this process was repeated three times at 15, 30, and 45 days after inoculation (DAI). Based on the simulated hyperspectral curves, a discrepancy between the red and near-infrared (NIR) bands was identified at 15 DAI, with the inoculated plants showing greater absorption in the red band and a greater spectral response in the NIR band. Thus, multispectral images were able to distinguish <i>H. vastatrix</i> infection in coffee seedlings at an asymptomatic stage (15 DAI) using a support vector machines (SVM) algorithm. Detection accuracy was 80% and the Kappa index of agreement was moderate (0.6). The early detection of this pathogen in the field using low-cost technology can be an important tool for the monitoring of coffee leaf rust and, consequently, a more sustainable management of the pathogen, causing farmers to make applications of chemical fungicides only when necessary.https://www.mdpi.com/2073-4395/12/12/2911algorithmscoffee cultivationdiagnosismachine learningphytopathology |
| spellingShingle | Analis da Silva Soares Bruno Sérgio Vieira Thalita Almeida Bezerra George Deroco Martins Ana Carolina Silva Siquieroli Early Detection of Coffee Leaf Rust Caused by <i>Hemileia vastatrix</i> Using Multispectral Images Agronomy algorithms coffee cultivation diagnosis machine learning phytopathology |
| title | Early Detection of Coffee Leaf Rust Caused by <i>Hemileia vastatrix</i> Using Multispectral Images |
| title_full | Early Detection of Coffee Leaf Rust Caused by <i>Hemileia vastatrix</i> Using Multispectral Images |
| title_fullStr | Early Detection of Coffee Leaf Rust Caused by <i>Hemileia vastatrix</i> Using Multispectral Images |
| title_full_unstemmed | Early Detection of Coffee Leaf Rust Caused by <i>Hemileia vastatrix</i> Using Multispectral Images |
| title_short | Early Detection of Coffee Leaf Rust Caused by <i>Hemileia vastatrix</i> Using Multispectral Images |
| title_sort | early detection of coffee leaf rust caused by i hemileia vastatrix i using multispectral images |
| topic | algorithms coffee cultivation diagnosis machine learning phytopathology |
| url | https://www.mdpi.com/2073-4395/12/12/2911 |
| work_keys_str_mv | AT analisdasilvasoares earlydetectionofcoffeeleafrustcausedbyihemileiavastatrixiusingmultispectralimages AT brunosergiovieira earlydetectionofcoffeeleafrustcausedbyihemileiavastatrixiusingmultispectralimages AT thalitaalmeidabezerra earlydetectionofcoffeeleafrustcausedbyihemileiavastatrixiusingmultispectralimages AT georgederocomartins earlydetectionofcoffeeleafrustcausedbyihemileiavastatrixiusingmultispectralimages AT anacarolinasilvasiquieroli earlydetectionofcoffeeleafrustcausedbyihemileiavastatrixiusingmultispectralimages |