Banana Fusarium Wilt Disease Detection by Supervised and Unsupervised Methods from UAV-Based Multispectral Imagery

Validation and Application of a Molecular Detection System for Fusarium Wilt of Banana in China

Fusarium wilt of banana is a devastating disease caused by Fusarium oxysporum f. sp. cubense (Foc). It has restricted the development of the banana industry worldwide and is particularly serious in China because of the large planting areas and special planting patterns. However, there is no rapid and accurate approach to detect the Foc strains that specifically occur in China because of the rich genetic diversity observed in this pathosystem. In this study, we evaluated the performance of 10 previously published PCR primer pairs on 103 representative Foc strains in China and neighboring countries and screened out a set of primers (Foc-specific primer pair SIX9-Foc-F/R, Foc R1-specific primer pair SIX6b-210-F/R, Foc R4-specific primer pair Foc-1/2, and Foc TR4-specific primer pair W2987F/R) suitable for the detection of Foc strains in China and the surrounding Southeast Asian countries. Moreover, we developed a molecular detection system to accurately identify the different physiological races of Foc. The findings of this study provide technical support for preventing and controlling the spread of Fusarium wilt of banana in the field in China.

Image-Based High-Throughput Phenotyping in Horticultural Crops

Plant phenotyping is the primary task of any plant breeding program, and accurate measurement of plant traits is essential to select genotypes with better quality, high yield, and climate resilience. The majority of currently used phenotyping techniques are destructive and time-consuming. Recently, the development of various sensors and imaging platforms for rapid and efficient quantitative measurement of plant traits has become the mainstream approach in plant phenotyping studies. Here, we reviewed the trends of image-based high-throughput phenotyping methods applied to horticultural crops. High-throughput phenotyping is carried out using various types of imaging platforms developed for indoor or field conditions. We highlighted the applications of different imaging platforms in the horticulture sector with their advantages and limitations. Furthermore, the principles and applications of commonly used imaging techniques, visible light (RGB) imaging, thermal imaging, chlorophyll fluorescence, hyperspectral imaging, and tomographic imaging for high-throughput plant phenotyping, are discussed. High-throughput phenotyping has been widely used for phenotyping various horticultural traits, which can be morphological, physiological, biochemical, yield, biotic, and abiotic stress responses. Moreover, the ability of high-throughput phenotyping with the help of various optical sensors will lead to the discovery of new phenotypic traits which need to be explored in the future. We summarized the applications of image analysis for the quantitative evaluation of various traits with several examples of horticultural crops in the literature. Finally, we summarized the current trend of high-throughput phenotyping in horticultural crops and highlighted future perspectives.

The Advance of Fusarium Wilt Tropical Race 4 in Musaceae of Latin America and the Caribbean: Current Situation

The fungus Fusarium oxysporum f. sp. cubense tropical race 4 (syn. Fusarium odoratissimum) (Foc TR4) causes vascular wilt in Musaceae plants and is considered the most lethal for these crops. In Latin America and the Caribbean (LAC), it was reported for the first time in Colombia (2019), later in Peru (2021), and recently declared in Venezuela (2023). This work aimed to analyze the evolution of Foc TR4 in Musaceae in LAC between 2018 and 2022. This perspective contains a selection of topics related to Foc TR4 in LAC that address and describe (i) the threat of Foc TR4 in LAC, (ii) a bibliometric analysis of the scientific production of Foc TR4 in LAC, (iii) the current situation of Foc TR4 in Colombia, Peru, and Venezuela, (iv) medium-term prospects in LAC member countries, and (v) export trade and local food security. In this study, the presence of Foc TR4 in Venezuela and the possible consequences of the production of Musaceae in the long term were reported for the first time. In conclusion, TR4 is a major threat to banana production in Latin America and the world, and it is important to take measures to control the spread of the fungus and minimize its impact on the banana industry. It is important to keep working on the control of Foc TR4, which requires the participation of the local and international industry, researchers, and consumers, among others, to prevent the disappearance of bananas.

Evaluation of Diverse Convolutional Neural Networks and Training Strategies for Wheat Leaf Disease Identification with Field-Acquired Photographs

Tools for robust identification of crop diseases are crucial for timely intervention by farmers to minimize yield losses. Visual diagnosis of crop diseases is time-consuming and laborious, and has become increasingly unsuitable for the needs of modern agricultural production. Recently, deep convolutional neural networks (CNNs) have been used for crop disease diagnosis due to their rapidly improving accuracy in labeling images. However, previous CNN studies have mostly used images of single leaves photographed under controlled conditions, which limits operational field use. In addition, the wide variety of available CNNs and training options raises important questions regarding optimal methods of implementation of CNNs for disease diagnosis. Here, we present an assessment of seven typical CNNs (VGG-16, Inception-v3, ResNet-50, DenseNet-121, EfficentNet-B6, ShuffleNet-v2 and MobileNetV3) based on different training strategies for the identification of wheat main leaf diseases (powdery mildew, leaf rust and stripe rust) using field images. We developed a Field-based Wheat Diseases Images (FWDI) dataset of field-acquired images to supplement the public PlantVillage dataset of individual leaves imaged under controlled conditions. We found that a transfer-learning method employing retuning of all parameters produced the highest accuracy for all CNNs. Based on this training strategy, Inception-v3 achieved the highest identification accuracy of 92.5% on the test dataset. While lightweight CNN models (e.g., ShuffleNet-v2 and MobileNetV3) had shorter processing times (<0.007 s per image) and smaller memory requirements for the model parameters (<20 MB), their accuracy was relatively low (~87%). In addition to the role of CNN architecture in controlling overall accuracy, environmental effects (e.g., residual water stains on healthy leaves) were found to cause misclassifications in the field images. Moreover, the small size of some target symptoms and the similarity of symptoms between some different diseases further reduced the accuracy. Overall, the study provides insight into the collective effects of model architecture, training strategies and input datasets on the performance of CNNs, providing guidance for robust CNN design for timely and accurate crop disease diagnosis in a real-world environment.