, "Deep convolutional neural network for classifying Fusarium wilt of radish from unmanned aerial vehicles," J. Appl. Remote Sens. 11(4), 042621 (2017), doi: 10.1117/1.JRS.11.042621. Abstract. Recently, unmanned aerial vehicles (UAVs) have gained much attention. In particular, there is a growing interest in utilizing UAVs for agricultural applications such as crop monitoring and management. We propose a computerized system that is capable of detecting Fusarium wilt of radish with high accuracy. The system adopts computer vision and machine learning techniques, including deep learning, to process the images captured by UAVs at low altitudes and to identify the infected radish. The whole radish field is first segmented into three distinctive regions (radish, bare ground, and mulching film) via a softmax classifier and K-means clustering. Then, the identified radish regions are further classified into healthy radish and Fusarium wilt of radish using a deep convolutional neural network (CNN). In identifying radish, bare ground, and mulching film from a radish field, we achieved an accuracy of ≥97.4%. In detecting Fusarium wilt of radish, the CNN obtained an accuracy of 93.3%. It also outperformed the standard machine learning algorithm, obtaining 82.9% accuracy. Therefore, UAVs equipped with computational techniques are promising tools for improving the quality and efficiency of agriculture today.

No abstract

Fusarium wilt (FW) is a fungal disease that causes severe yield losses in radish production. The most effective method to control the FW is the development and use of resistant varieties in cultivation. The identification of marker loci linked to FW resistance are expected to facilitate the breeding of disease-resistant radishes. In the present study, we applied an integrated framework of genome-wide association studies (GWAS) using genotyping-by-sequencing (GBS) to identify FW resistance loci among a panel of 225 radish accessions, including 58 elite breeding lines. Phenotyping was conducted by manual inoculation of seedlings with the FW pathogen, and scoring for the disease index was conducted three weeks after inoculation during two constitutive years. The GWAS analysis identified 44 single nucleotide polymorphisms (SNPs) and twenty putative candidate genes that were significantly associated with FW resistance. In addition, a total of four QTLs were identified from F2 population derived from a FW resistant line and a susceptible line, one of which was co-located with the SNPs on chromosome 7, detected in GWAS study. These markers will be valuable for molecular breeding programs and marker-assisted selection to develop FW resistant varieties of R. sativus.

No abstract

Kimchi made from small-type (Altari) radishes grown in late spring is more pungent than that made from autumn-grown Altari radishes, which poses a major challenge in the kimchi industry. The mechanism through which the pungency of Altari radish changes seasonally has not been intensively investigated. In this study, three small-type radish cultivars with different pungency levels were cultivated in spring and autumn to identify the factors affecting the seasonal-dependent pungency of small-type radishes. The contents of pungency-related metabolite glucoraphasatin and other polar metabolites were analyzed. Although a previous study reported that the glucoraphasatin concentration affects the pungency of radish, in the current study, the concentration of neither glucoraphasatin nor its hydrolysis product (raphasatin) could fully explain the change in the pungency associated with radish cultivars grown in the two seasons. The change in the pungency of radish by season may be explained by the ratio of raphasatin content to total sweetness of sugars. In addition, the polar metabolites that differ with season were analyzed to identify seasonal biomarkers and understand the seasonal changed physio-biochemistry.