Search

In this study hyperspectral imaging (380–1020 nm) and machine learning were utilised to develop a technique for detecting different disease development stages (asymptomatic, early, intermediate, and late disease stage) of powdery mildew (PM) in squash. Data were collected in the laboratory as well as in the field using an unmanned aerial vehicle (UAV). Radial basis function (RBF) was used to discriminate between healthy and diseased plants, and to classify the severity level (disease stage) of a plant; the most significant bands to differentiate between healthy and different stages of disease development were selected (388 nm, 591 nm, 646 nm, 975 nm, and 1012 nm). Furthermore, 29 spectral vegetation indices (VIs) were tested and evaluated for their ability to detect and classify healthy and PM-infected plants; the M value was used to evaluate the VIs. The water index (WI) and the photochemical reflectance index (PRI) were able to accurately detect and classify PM in asymptomatic, early, and late development stages under laboratory conditions. Under field conditions (UAV-based), the spectral ratio of 761 (SR761) accurately detected PM in early stages, and the chlorophyll index green (CI green), the normalised difference of 750/705 (ND 750/705), the green normalised difference vegetation index (GNDVI), and the spectral ratio of 850 (SR850) in late stages. The classification results, by using RBF, in laboratory conditions for the asymptomatic and late stage was 82% and 99% respectively, while in field conditions it was 89% and 96% in early and late disease development stages, respectively. • A lab- and UAV-based powdery mildew (PM) disease detection system was developed. • Spectral reflectance analysis of PM-infected squash leaves was performed. • The most significant wavelengths and vegetation indices were selected. • The technique was able to detect different stages of PM progress in squash. [ABSTRACT FROM AUTHOR]

Highlights • A remote sensing technique for Laurel Wilt detection in avocado was developed. • This low-cost technique can distinguish Laurel Wilt disease from other stressors. • Neural networks were utilizing for disease detection and classification. • Early disease detection was achieved utilizing multispectral imaging. Abstract Early and accurate disease detection is essential for implementing timely disease management practices. Current disease detection tactics, like visual detection through scouting, are labor intensive, expensive, requires a level of expertise in pest identification, and, may result in subjective disease identification. Diagnosis based on visual symptoms is often compromised by the inability to differentiate between similar symptoms caused by different biotic and abiotic factors. In this paper, an automated early disease detection technique for avocado trees is presented and evaluated. This remote sensing technique can detect an important avocado disease, the laurel wilt (Lw) disease, and differentiate it from healthy trees (H), trees infected by phytophthora root rot (Prr), and trees with iron (Fe) and nitrogen (N) deficiencies. Detection of Lw disease in avocado trees, in early stage, is very difficult, because it has similar symptoms with other stress factors such as nutrient deficiency, salt damage, phytophthora root rot, etc. The proposed disease detection procedure contains several steps including image acquisition, image pre-processing, image segmentation, feature extraction and classification. For image acquisition, two cameras were utilized and evaluated: (i) a Tetracamera (6 bands Tetracam) and (ii) a modified Canon camera (3 bands); and two classification methods were studied: (a) neural network multilayer perceptron (MLP), and (ii) K- nearest neighbors, to detect Lw in asymptomatic stage and in late (symptomatic) stage. Additionally, two segmentation methods, region of interest (OVROI) and polygon region of interest (PROI), were utilized. The MLP classification method with the Tetracam was able to successfully detect Lw with an accuracy of 99% in asymptomatic (early) stage. Hence, low-cost remote technique can be utilized to differentiate healthy and unhealthy plants. [ABSTRACT FROM AUTHOR]

Highlights • A Laurel Wilt detection disease system was developed. • It can distinguish Laurel Wilt disease from other disorders with similar symptoms. • Early disease detection was achieved utilizing hyperspectral data. • Spectral signature reflectance and vegetation indices were used for disease detection. Abstract Laurel wilt (Lw) disease is an exotic and lethal disease that can kill laurel family trees very fast. It is vectored by the redbay ambrosia beetle that prefers to live and lay eggs inside avocado trees (among other plants). Lw disease continues to expand in Florida posing a major threat to the avocado industry. Early and accurate disease detection is very critical in this case to remove infected trees and distinguish Lw disease from other diseases or disorders with similar symptoms. Herein, we present a nondestructive remote sensing method to detect Lw-infected avocado trees (in early and late stage) and discriminate them from healthy and other factors that cause similar symptoms, such as iron and nitrogen deficiencies, by using a portable spectral data collection system (visible – near infrared; 400–970 nm). Two data sets were collected in 10 nm and 40 nm spectral resolution, and 23 vegetation indices (VIs) were calculated to detect Lw-affected trees by using two classification methods: decision tree (DT) and multilayer perceptron (MLP) neural networks. Additionally, the optimal wavelengths and VIs to discriminate healthy, Lw-infected and avocado trees with iron and nitrogen deficiencies were identified. The results showed that it was possible to detect Lw-infected trees at early stage and distinguish them from other biotic and abiotic factors with high accuracy (around 100%) using the MLP method. Poorer results were achieved with DTs. The optimum 10 nm wide bands and VIs selected for the Lw-detection were found in the red, red-edge and NIR bands. [ABSTRACT FROM AUTHOR]

Tomato crops are susceptible to multiple diseases, several of which may be present during the same season. Therefore, rapid disease identification could enhance crop management consequently increasing the yield. In this study, nondestructive methods were developed to detect diseases that affect tomato crops, such as bacterial spot (BS), target spot (TS), and tomato yellow leaf curl (TYLC) for two varieties of tomato (susceptible and tolerant to TYLC only) by using hyperspectral sensing in two conditions: a) laboratory (benchtop scanning), and b) in field using an unmanned aerial vehicle (UAV-based). The stepwise discriminant analysis (STDA) and the radial basis function were applied to classify the infected plants and distinguish them from noninfected or healthy (H) plants. Multiple vegetation indices (VIs) and the M statistic method were utilized to distinguish and classify the diseased plants. In general, the classification results between healthy and diseased plants were highly accurate for all diseases; for instance, when comparing H vs. BS, TS, and TYLC in the asymptomatic stage and laboratory conditions, the classification rates were 94%, 95%, and 100%, respectively. Similarly, in the symptomatic stage, the classification rates between healthy and infected plants were 98% for BS, and 99–100% for TS and TYLC diseases. The classification results in the field conditions also showed high values of 98%, 96%, and 100%, for BS, TS, and TYLC, respectively. The VIs that could best identify these diseases were the renormalized difference vegetation index (RDVI), and the modified triangular vegetation index 1 (MTVI 1) in both laboratory and field. The results were promising and suggest the possibility to identify these diseases using remote sensing. [ABSTRACT FROM AUTHOR]

Laurel wilt (Lw) is a very destructive disease and poses a serious threat to the commercial production of avocado in Florida, USA. External symptoms of Lw are similar to those that are caused by other diseases and disorders. A rapid technique to distinguish Lw infected avocado from healthy trees and trees with other abiotic stressors is presented in this paper. A novel method was developed to analyze data from hyperspectral data using finite difference approximation (FDA) and bivariate correlation (BC) to discriminate Lw, Nitrogen (N), and Iron (Fe) deficiencies from healthy avocado plants. Several combinatorial methods were used in preprocessing the data, such as standard normal transformation of data, smoothing of the data, and polynomial fit. The FDA technique was derived using a Taylor Polynomial finite difference approximation. This FDA accentuates inflection points in the spectrum. These, in turn, reveal variance in the data that can be used to identify spectral signature associated with healthy and diseased states. By statistical correlation using the bivariate correlation coefficient of these enhanced spectral patterns, an algorithm (FDA-BC) for distinguishing Lw avocado leaves from all other categories of healthy or mineral deficient avocado leaves is achieved with an overall accuracy of 100%. [ABSTRACT FROM AUTHOR]

A remote sensing technique was developed to detect citrus canker in laboratory conditions and was verified in the grove by utilizing an unmanned aerial vehicle (UAV). In the laboratory, a hyperspectral (400–1000 nm) imaging system was utilized for the detection of citrus canker in several disease development stages (i.e., asymptomatic, early, and late symptoms) on Sugar Belle leaves and immature (green) fruit by using two classification methods: (i) radial basis function (RBF) and (ii) K nearest neighbor (KNN). The same imaging system mounted on an UAV was used to detect citrus canker on tree canopies in the orchard. The overall classification accuracy of the RBF was higher (94%, 96%, and 100%) than the KNN method (94%, 95%, and 96%) for detecting canker in leaves. Among the 31 studied vegetation indices, the water index (WI) and the Modified Chlorophyll Absorption in Reflectance Index (ARI and TCARI 1) more accurately detected canker in laboratory and in orchard conditions, respectively. Immature fruit was not a reliable tissue for early detection of canker. However, the proposed technique successfully distinguished the late stage canker-infected fruit with 92% classification accuracy. The UAV-based technique achieved 100% classification accuracy for identifying healthy and canker-infected trees. [ABSTRACT FROM AUTHOR]

Anthracnose crown rot (ACR) is one of the major diseases affecting strawberry crops grown in warm climates and causes huge yield losses each year. ACR is caused by the fungus Colletotrichum. Since this airborne disease spreads rapidly, detection at the early stage of infection is critical. The objective of this study was to investigate the feasibility of detecting ACR in strawberry at its early stage under field conditions using spectroscopy technology. Hyperspectral data were collected in-field using a mobile platform on three categories of strawberry plants: infected but asymptomatic, infected and symptomatic, and healthy. As a comparison, indoor data were also collected from the same three categories of strawberry plants under a controlled laboratory setup . Three classification models, stepwise discriminant analysis (SDA), Fisher discriminant analysis (FDA), and the k-Nearest Neighbor (kNN) algorithms, were investigated for their potential to differentiate the three infestation categories. Thirty-three spectral vegetation indices (SVIs) were calculated as inputs using selected spectral bands in the visible (VIS) and near infrared (NIR) regions to train classification models. The mean classification accuracies of in-field tests for the three infestation categories were 71.3%, 70.5%, and 73.6% for SDA, FDA, and kNN, respectively. These accuracies were approximately 15–20% lower than those of the indoor tests. The low accuracy (15.4%) of classifying healthy leaves in-field using the kNN model was possibly due to the training datasets being unbalanced. After the adjustment of sample sizes of each category, the accuracies of kNN improved greatly, especially for the healthy and symptomatic categories. Overall, SDA was the optimal classifier for both indoor and in-field tests for detection strawberry ACR. However, kNN performed better for asymptomatic leaves in the field in the case of balanced sample sizes of each category. [ABSTRACT FROM AUTHOR]