| 1. |
- Araujo Sandroni, Murilo, et al.
(författare)
-
In-field classification of the asymptomatic biotrophic phase of potato late blight based on deep learning and proximal hyperspectral imaging
- 2023
-
Ingår i: Computers and Electronics in Agriculture. - : Elsevier BV. - 0168-1699 .- 1872-7107. ; 205
-
Tidskriftsartikel (refereegranskat)abstract
- Effective detection of potato late blight (PLB) is an essential aspect of potato cultivation. However, it is a challenge to detect late blight in asymptomatic biotrophic phase in fields with conventional imaging approaches because of the lack of visual symptoms in the canopy. Hyperspectral imaging can capture spectral signals from a wide range of wavelengths also outside the visual wavelengths. Here, we propose a deep learning classification architecture for hyperspectral images by combining 2D convolutional neural network (2D-CNN) and 3D-CNN with deep cooperative attention networks (PLB-2D-3D-A). First, 2D-CNN and 3D-CNN are used to extract rich spectral space features, and then the attention mechanism AttentionBlock and SE-ResNet are used to emphasize the salient features in the feature maps and increase the generalization ability of the model. The dataset is built with 15,360 images (64x64x204), cropped from 240 raw images captured in an experimental field with over 20 potato genotypes. The accuracy in the test dataset of 2000 images reached 0.739 in the full band and 0.790 in the specific bands (492 nm, 519 nm, 560 nm, 592 nm, 717 nm and 765 nm). This study shows an encouraging result for classification of the asymptomatic biotrophic phase of PLB disease with deep learning and proximal hyperspectral imaging.
|
|
| 2. |
- Araujo Sandroni, Murilo, et al.
(författare)
-
Plant resistance inducers (PRIs): perspectives for future disease management in the field
- 2020
-
Ingår i: Cab Reviews: Perspectives In Agriculture, Veterinary Science, Nutrition And Natural Resources. - 1749-8848. ; 15, s. 10-
-
Forskningsöversikt (refereegranskat)abstract
- Plants are confronted with numerous biotic stresses that may affect productivity. Besides their constitutive defence, plants can activate specific metabolic processes to enhance resistance upon stress detection. These defence mechanisms can also be activated through the recognition of plant resistance inducers (PRIs). This review highlights some of the current challenges that prevent the adoption of PRIs in agriculture, and explore research topics and knowledge gaps to be addressed for bringing PRIs closer to practice. First, we present studies on the variance of induced defence responses and examine the possibility of employing inducibility in breeding strategies as well as the possible role of epigenetics. We also discuss the efficiency of PRIs in future climate and knowledge gaps on this subject. Remote sensing, high-throughput phenotyping and modelling in combination with PRIs as part of decision support systems and integrated pest management are further possibilities to advance the use of PRIs. Finally, we discuss the challenges which need to be addressed to make PRIs available for small-scale farmers in low-income countries. Although PRIs have successfully presented significant rates of disease prevention under controlled conditions, converting these findings into field application still depends on more studies, e.g. on how they can be integrated into disease management programmes. Better mechanistic understanding of IR together with the coupling of PRIs to new disease monitoring and protection strategies can give PRIs a stronger role in future agricultural practice.
|
|
| 3. |
- Zahid, Muhammad Awais, et al.
(författare)
-
A fast, nondestructive method for the detection of disease-related lesions and wounded leaves
- 2021
-
Ingår i: Biotechniques. - : Future Science Ltd. - 0736-6205 .- 1940-9818. ; 71
-
Tidskriftsartikel (refereegranskat)abstract
- Trypan blue staining is a classic way of visualizing leaf disease and wound responses in plants, but it involves working with toxic chemicals and is time-consuming (2-3 days). Here, the investigators established near-infrared scanning with standard lab equipment as a fast and nondestructive method for the analysis of leaf injuries compared with trypan blue staining. Pathogen-inoculated and wounded leaves from potato, tomato, spinach, strawberry, and arabidopsis plants were used for proof of concept. The results showed that this newly developed protocol with near-infrared scanning gave the same results as trypan blue staining. Furthermore, a macro in FIJI was made to quantify the leaf damage. The new protocol was time-efficient, nondestructive, chemical-free and may be used for high-throughput studies.
|
|
