• The Plant Pathology Journal
• /
• v.38 no.1
• /
• pp.46-51
• /
• 2022

Rice blast is the most destructive disease threatening stable rice production in rice-growing areas. Cultivation of disease-resistant rice cultivars is the most effective way to control rice blast disease. However, the rice blast resistance is easy to breakdown within years by blast fungus that continually changes to adapt to new cultivars. Therefore, it is important to continuously monitor the incidence of rice blast disease and race differentiation of rice blast fungus in fields. In 2020, a severe rice blast disease occurred nationwide in Korea. We evaluated the incidence of rice blast disease in Yeoju and compared the weather conditions at the periods of rice blast disease in 2019 and 2020. We investigated the races and avirulence genes of rice blast isolates in Yeoju to identify race diversity and genetic characteristics of the isolates. This study will provide empirical support for rice blast control and the breeding of blast-resistant rice cultivars.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.285-292
• /
• 2023

With the wide spread of smart farms and the advancements in IoT technology, it is easy to obtain additional data in addition to crop images. Consequently, deep learning-based crop disease diagnosis research utilizing multimodal data has become important. This study proposes a crop disease diagnosis method using multimodal supervised contrastive learning by expanding upon the multimodal self-supervised learning. RandAugment method was used to augment crop image and time series of environment data. These augmented data passed through encoder and projection head for each modality, yielding low-dimensional features. Subsequently, the proposed multimodal supervised contrastive loss helped features from the same class get closer while pushing apart those from different classes. Following this, the pretrained model was fine-tuned for crop disease diagnosis. The visualization of t-SNE result and comparative assessments of crop disease diagnosis performance substantiate that the proposed method has superior performance than multimodal self-supervised learning.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1653-1671
• /
• 2022

Crop diseases affect crop production, more than 30 billion USD globally. We proposed a classification study of crop species and diseases using deep learning algorithms for corn, cucumber, pepper, and strawberry. Our study has three steps of species classification, disease detection, and disease classification, which is noteworthy for using captured images without additional processes. We designed deep learning approach of deep learning convolutional neural networks based on Mask R-CNN model to classify crop species. Inception and Resnet models were presented for disease detection and classification sequentially. For classification, we trained Mask R-CNN network and achieved loss value of 0.72 for crop species classification and segmentation. For disease detection, InceptionV3 and ResNet101-V2 models were trained for nodes of crop species on 1,500 images of normal and diseased labels, resulting in the accuracies of 0.984, 0.969, 0.956, and 0.962 for corn, cucumber, pepper, and strawberry by InceptionV3 model with higher accuracy and AUC. For disease classification, InceptionV3 and ResNet 101-V2 models were trained for nodes of crop species on 1,500 images of diseased label, resulting in the accuracies of 0.995 and 0.992 for corn and cucumber by ResNet101 with higher accuracy and AUC whereas 0.940 and 0.988 for pepper and strawberry by Inception.

• Journal of Korea Multimedia Society
• /
• v.23 no.10
• /
• pp.1250-1257
• /
• 2020

The early detection of diseases is important in agriculture because diseases are major threats of reducing crop yield for farmers. The shape and color of plant leaf are changed differently according to the disease. So we can detect and estimate the disease by inspecting the visual feature in leaf. This study presents a vision-based leaf classification method for detecting the diseases of tomato crop. ResNet-50 model was used to extract the visual feature in leaf and classify the disease of tomato crop, since the model showed the higher accuracy than the other ResNet models with different depths. We propose a new ensemble approach using several DCNN classifiers that have the same structure but have been trained at different ranges in the DCNN layers. Experimental result achieved accuracy of 97.19% for PlantVillage dataset. It validates that the proposed method effectively classify the disease of tomato crop.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2020.12a
• /
• pp.64-64
• /
• 2020

Bakanae disease, caused by several Fusarium species, imposes serious limitations to the productivity of rice across the globe. The incidence of this disease has been shown to increase, particularly in major rice-growing countries. Thus, the use of high resistant rice cultivars offers a comparative advantage, such as being cost effective, and could be preferred to the use of fungicides. In this research, we used a tropical japonica rice variety, Zenith, a bakanae disease resistant line selected as donor parent. A RIL population (F_8:9) composed of 180 lines generated from a cross between Ilpum and Zenith was used. In primary mapping, a QTL was detected on the short arm of chromosome 1, covering about 3.5 Mb region flanked by RM1331 and RM3530 markers. The resistance QTL, qBK1^Z, explained about 30.93% of the total phenotype variation (PVE, logarith of the odds (LOD) of 13.43). Location of qBK1^Z was further narrowed down to 730 kb through fine mapping using additional RM markers, including those previously reported and developed by Sid markers. Furthermore, there is a growing need to improving resistance to bakanae disease and promoting breeding efficiency using MAS from qBK1^Z region. The new QTL, qBK1^Z, developed by the current study is expected to be used as foundation to promoting breeding efficiency with an enhanced resistance against bakanae disease. Moreover, this study provides useful information for developing resistant rice lines carrying single or multiple major QTLs using gene pyramiding approach and marker-assisted breeding.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.92-92
• /
• 2017

Bakanae disease is one of the most serious and oldest problems of rice production, which was first described in 1828 in Japan. This disease has also been identified in Asia, Africa, North America, and Italy. Germinating rice seeds in seed boxes for mechanical transplantation has caused many problems associated with diseases, including bakanae disease. Bakanae disease has become a serious problem in the breeding of hybrid rice, which involves the increased use of raising plants in seed beds. The indica rice variety Shingwang was selected as resistant donor to bakanae disease. One hundred sixty nine NILs, YR28297 ($BC_6F_4$) generated by five backcrosses of Shingwang with the genetic background of susceptible japonica variety, Ilpum were used for QTL analysis. Rice bakanae disease pathogen, CF283, was mainly used in this study and inoculation and evaluation of bakanae disease was performed with the method of the large-scale screening method developed by Kim et al. (2014). SSR markers evenly distributed in the entire rice chromosomes were selected from the Gramene database (http://www.gramene.org), and the polymorphic markers were used for frame mapping of a $BC_5F_5$ resistant line. Here, we developed 168 near-isogenic rice lines (NILs, $BC_6F_4$) to locate a QTL for resistance against bakanae disease. The lines were derived from a cross between Shingwang, a highly resistant variety (indica), and Ilpum, a highly susceptible variety (japonica). The 24 markers representing the Shingwang allele in a bakanae disease-resistant NIL, YR24982-9-1 (parental line of the $BC_6F_4$ NILs), were located on chromosome 1, 2, 7, 8, 10, 11, and 12. Single marker analysis using an SSR marker, RM9, showed that a major QTL was located on chromosome 1. The QTL explained 65 % of the total phenotype variation in $BC_6F_4$ NILs. The major QTL designated qBK1 was mapped in 91 kb region between InDel15 and InDel21. The identification of qBK1 and the closely linked SSR marker, InDel18, could be useful for improving rice bakanae disease resistance in marker-assisted breeding.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.149-158
• /
• 2024

Traditional manual identification of crop leaf diseases is challenging. Owing to the limitations in manpower and resources, it is challenging to explore crop diseases on a large scale. The emergence of artificial intelligence technologies, particularly the extensive application of deep learning technologies, is expected to overcome these challenges and greatly improve the accuracy and efficiency of crop disease identification. Crop leaf disease identification models have been designed and trained using large-scale training data, enabling them to predict different categories of diseases from unlabeled crop leaves. However, these models, which possess strong feature representation capabilities, require substantial training data, and there is often a shortage of such datasets in practical farming scenarios. To address this issue and improve the feature learning abilities of models, this study proposes a deep transfer learning adaptation strategy. The novel proposed method aims to transfer the weights and parameters from pre-trained models in similar large-scale training datasets, such as ImageNet. ImageNet pre-trained weights are adopted and fine-tuned with the features of crop leaf diseases to improve prediction ability. In this study, we collected 16,060 crop leaf disease images, spanning 12 categories, for training. The experimental results demonstrate that an impressive accuracy of 98% is achieved using the proposed method on the transferred ResNet-50 model, thereby confirming the effectiveness of our transfer learning approach.

• The Korean Journal of Mycology
• /
• v.47 no.4
• /
• pp.407-416
• /
• 2019

A common post-harvest disease of sweetpotato tuber is root rot caused by Fusarium solani in Korea as well as the other countries. Storage root rot disease was monitored earlier on sweetpotato (Ipomoea batatas) in storehouses of different locations in Korea. In the present study, an isolate SPL16124 was choosen and collected from Sweetpotato Research Lab., Bioenergy Crop Research Institute, NICS, Muan, Korea, and confirmed the identification as Fusarium solani by conidial and molecular phylogenetic analysis (internal transcribed spacer ITS and translation elongation factor EF 1-α gene sequences). The isolate was cultured on potato dextrose agar, and conidiation was induced. The fungus was screened for Fusarium root rot on tuber of 14 different varieties. Among the tested variety, Yenjami, Singeonmi, Daeyumi, and Sinjami showed resistant to root rot disease. Additionally, the pathogen was tested for pathogenicity on stalks of these varieties. No symptom was observed on the stalk, and it was confirmed that the disease is tissue specific.

• The Plant Pathology Journal
• /
• v.32 no.6
• /
• pp.580-583
• /
• 2016

The cotton leafroll dwarf virus (CLRDV) is one of the most devastating pathogens of cotton. This malady, known as cotton blue disease, is widespread in South America where it causes huge crop losses. Recently the disease has been reported from India. We noticed occurrence of cotton blue disease and chickpea stunt disease in adjoining cotton and chickpea fields and got interested in knowing if these two viral diseases have some association. By genetic studies, we have shown here that CLRDV is very close to chickpea stunt disease associated virus (CpSDaV). We were successful in transmitting the CLRDV from cotton to chickpea. Our studies indicate that CpSDaV and CLRDV in India are possibly two different strains of the same virus. These findings would be helpful in managing these serious diseases by altering the cropping patterns.

• Mycobiology
• /
• v.45 no.3
• /
• pp.129-138
• /
• 2017

In this study, we aimed to characterize fungal samples from necrotic lesions on collar regions observed in different sweetpotato growing regions during 2015 and 2016 in Korea. Sclerotia appeared on the root zone soil surface, and white dense mycelia were observed. At the later stages of infection, mother roots quickly rotted, and large areas of the plants were destroyed. The disease occurrence was monitored at 45 and 84 farms, and 11.8% and 6.8% of the land areas were found to be infected in 2015 and 2016, respectively. Fungi were isolated from disease samples, and 36 strains were preserved. Based on the cultural and morphological characteristics of colonies, the isolates resembled the reference strain of Sclerotium rolfsii. Representative strains were identified as S. rolfsii (teleomorph: Athelia rolfsii) based on phylogenetic analysis of the internal transcribed spacer and large subunit genes along with morphological observations. To test the pathogenicity, sweetpotato storage roots were inoculated with different S. rolfsii strains. 'Yulmi' variety displayed the highest disease incidence, whereas 'Pungwonmi' resulted in the least. These findings suggested that morphological characteristics and molecular phylogenetic analysis were useful for identification of S. rolfsii.