Imaging and Deep Learning Based Approach to Leaf Wetness Detection in Strawberry
The Strawberry Advisory System (SAS) is a tool developed to help Florida strawberry growers determine the risk of common fungal diseases and the need for fungicide applications. Leaf wetness duration (LWD) is one of the important parameters in SAS disease risk modeling. By accurately measuring the L...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/21/8558 |
| _version_ | 1797466444459409408 |
|---|---|
| author | Arth M. Patel Won Suk Lee Natalia A. Peres |
| author_facet | Arth M. Patel Won Suk Lee Natalia A. Peres |
| author_sort | Arth M. Patel |
| collection | DOAJ |
| description | The Strawberry Advisory System (SAS) is a tool developed to help Florida strawberry growers determine the risk of common fungal diseases and the need for fungicide applications. Leaf wetness duration (LWD) is one of the important parameters in SAS disease risk modeling. By accurately measuring the LWD, disease risk can be better assessed, leading to less fungicide use and more economic benefits to the farmers. This research aimed to develop and test a more accurate leaf wetness detection system than traditional leaf wetness sensors. In this research, a leaf wetness detection system was developed and tested using color imaging of a reference surface and a convolutional neural network (CNN), which is one of the artificial-intelligence-based learning methods. The system was placed at two separate field locations during the 2021–2022 strawberry-growing season. The results from the developed system were compared against manual observation to determine the accuracy of the system. It was found that the AI- and imaging-based system had high accuracy in detecting wetness on a reference surface. The developed system can be used in SAS for determining accurate disease risks and fungicide recommendations for strawberry production and allows the expansion of the system to multiple locations. |
| first_indexed | 2024-03-09T18:38:56Z |
| format | Article |
| id | doaj.art-41000ab2630448238c0d15e41d25d12b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:38:56Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-41000ab2630448238c0d15e41d25d12b2023-11-24T06:49:58ZengMDPI AGSensors1424-82202022-11-012221855810.3390/s22218558Imaging and Deep Learning Based Approach to Leaf Wetness Detection in StrawberryArth M. Patel0Won Suk Lee1Natalia A. Peres2Department of Electrical & Computer Engineering, University of Florida, Gainesville, FL 32611, USADepartment of Agricultural and Biological Engineering, University of Florida, Rogers Hall, 1741 Museum Road, Gainesville, FL 32611, USADepartment of Plant Pathology, Gulf Coast Research and Education Center, University of Florida, Wimauma, FL 33598, USAThe Strawberry Advisory System (SAS) is a tool developed to help Florida strawberry growers determine the risk of common fungal diseases and the need for fungicide applications. Leaf wetness duration (LWD) is one of the important parameters in SAS disease risk modeling. By accurately measuring the LWD, disease risk can be better assessed, leading to less fungicide use and more economic benefits to the farmers. This research aimed to develop and test a more accurate leaf wetness detection system than traditional leaf wetness sensors. In this research, a leaf wetness detection system was developed and tested using color imaging of a reference surface and a convolutional neural network (CNN), which is one of the artificial-intelligence-based learning methods. The system was placed at two separate field locations during the 2021–2022 strawberry-growing season. The results from the developed system were compared against manual observation to determine the accuracy of the system. It was found that the AI- and imaging-based system had high accuracy in detecting wetness on a reference surface. The developed system can be used in SAS for determining accurate disease risks and fungicide recommendations for strawberry production and allows the expansion of the system to multiple locations.https://www.mdpi.com/1424-8220/22/21/8558artificial intelligencecolor imagingleaf wetnessStrawberry Advisory Systemstrawberry diseases |
| spellingShingle | Arth M. Patel Won Suk Lee Natalia A. Peres Imaging and Deep Learning Based Approach to Leaf Wetness Detection in Strawberry Sensors artificial intelligence color imaging leaf wetness Strawberry Advisory System strawberry diseases |
| title | Imaging and Deep Learning Based Approach to Leaf Wetness Detection in Strawberry |
| title_full | Imaging and Deep Learning Based Approach to Leaf Wetness Detection in Strawberry |
| title_fullStr | Imaging and Deep Learning Based Approach to Leaf Wetness Detection in Strawberry |
| title_full_unstemmed | Imaging and Deep Learning Based Approach to Leaf Wetness Detection in Strawberry |
| title_short | Imaging and Deep Learning Based Approach to Leaf Wetness Detection in Strawberry |
| title_sort | imaging and deep learning based approach to leaf wetness detection in strawberry |
| topic | artificial intelligence color imaging leaf wetness Strawberry Advisory System strawberry diseases |
| url | https://www.mdpi.com/1424-8220/22/21/8558 |
| work_keys_str_mv | AT arthmpatel imaginganddeeplearningbasedapproachtoleafwetnessdetectioninstrawberry AT wonsuklee imaginganddeeplearningbasedapproachtoleafwetnessdetectioninstrawberry AT nataliaaperes imaginganddeeplearningbasedapproachtoleafwetnessdetectioninstrawberry |