‘Saebom’ is a new vegetable perilla (Perilla frutescens (L.) Britton) variety developed at the National Institute of Crop Science, Rural Development Administration, in 2020, following a cross made in 2011 between YPL54-2B-36-1-1-1-2-2 and YPL83-2B-5-2-5. It was developed using a pedigree breeding method. YPL156-2B-9-2-1-3-2 was selected and named ‘Milyang 83.’ Subsequently, summer and winter productivity tests were conducted. ‘Saebom’ has small, round-shaped leaves and its maximum leaf length is 13.1 cm, which allows for the distribution of leaf harvesting labor. In addition, the leaves are thick, which is beneficial for storage, and the ratio of the apical leaf length/leaf length is 55.8% (‘Namcheon’ 37.2%). This value is considered high and makes ‘Saebom’ highly marketable. Its leaf yield and leaf number were 10% and 8% higher than those of ‘Namcheon,’ respectively, and its antioxidant activity was also higher. In December 2020, the variety was named ‘Saebom’ by the new variety selection committee for its excellence, and its variety protection rights were registered in 2023 (Registration No. 9305).

Deep learning has gained considerable interest in agricultural breeding research. While advances in sequencing technologies have made genotypic data collection easier in genomic breeding, phenotypic data collection remains labor intensive and time consuming. Furthermore, as traditional phenotypic data collection relies heavily on manual processes, the results may vary based on the researcher’s skill and criteria. Thus, automated phenotypic data collection is essential for addressing these challenges. In this study, we aimed to develop a deep learning model using the YOLOv8 framework to measure the lengths of hypocotyls and roots in sprout vegetables such as mung bean, cowpea, and soybean. Our model automates the measurement process, accurately identifies the hypocotyl and root using Roboflow, and subsequently measures their lengths with high precision in various legume species. This approach addresses the challenges of extensive phenotypic data collection, which is essential for genetic breeding and agricultural improvement. Our deep learning model facilitates consistent and accurate data collection in large-scale studies by controlling variables influenced by the researcher’s skills and criteria. This reduces errors and enhances data reliability and accuracy, which are crucial for successful breeding practices and agricultural research.

‘Gowon1’ is a large-sized and high-yielding peanut (Arachis hypogaea L. ssp. hypogaea var. hypogaea), which was developed at the Department of Southern Area Crop Science, National Institute of Crop Science (NICS), Miryang, and approved for release in 2019. For the harvest of vegetable peanuts, a large-sized pod and comparatively early maturation with high fresh-pod yield are required. ‘Gowon1’ was developed through pedigree selection from a single cross between the large-grain, short-stem variety ‘Pungsan’ and ‘Miryang47’, the early-maturing elite line. ‘Gowon1’ has 11 branches with the main stem and branch lengths of 43 cm and 49 cm, respectively. Each pod contains two seeds with a brown testa and a long ellipse-shape. ‘Gowon1’ exhibits 42 pods per plant, a 100-seed weight of 98 g and 80% mature pod ratio. Seed composition includes 30.2% protein, 47.0% crude fat, and 45% oleic acid, among other fatty acids. In regional yield trials conducted at four locations (2016-2018), ‘Gowon1’ demonstrated enhanced productivity, with an average fresh pod yield of 12.25 MT per hectare, which was 28% higher than the reference variety, ‘Palkwang’. It also exhibited higher resistance to early and late leaf spot and lodging compared to the reference variety in trials (Registration No. 9196).

In order to select sweetpotato varieties with excellent tip characteristics, we investigated the appearance, yield, and functional compounds in 32 domestic sweetpotato varieties. During the cultivation period, the total production of sweetpotato tips among the different variety ranged from 1,780 to 9,923 g/m², with that of the Gogeonmi variety being the highest. The lutein content among varieties ranged from 21.7 to 47.0 mg/100 g and was highest in the Juhwangmi variety, whereas the ß-carotene content ranged from 25.5 to 183.4 mg/100 g and was highest in the Hayanmi variety. The total polyphenol content ranged from 30.7 to 74.4 mg CAE/g, and it was high in the Pungwonmi, Daeyumi, and Dahomi varieties at 74.4, 73.8, and 72.9 mg CAE/g, respectively, whereas the DPPH radical scavenging activity of tips ranged from 88.6% to 91.6%, with Gogeonmi and Healthymi showing the highest value of 91.6%. ABTS radical scavenging activity was found to be lowest in the Yeonjami variety at 86%, whereas the remaining 31 varieties showed values in excess of 96%. ABTS radical scavenging activity showed a high positive correlation with total polyphenol content. On the basis of these analyses, we identified Juhwangmi with high lutein content, Hayanmi with high beta-carotene content and high yield, and Gogeonmi with high DPPH radical scavenging activity and high yield, as being suitable varieties for tip cultivation. We anticipate that these sweetpotato varieties with excellent tip characteristics will be used as parents for the breeding of varieties for vegetable use.

Nowadays most parts of vegetable breeding in Korea have been conducted by private seed companies. However, in the beginning stages of breeding research, Horticulture Experiment Station played a crucial role. Major vegetable varieties that are distributed from Korea are produced as F₁ hybrids. Korea has developed leading techniques and human infrastructure for vegetable breeding. Such brilliant developments have resulted from three major factors: changes in the composition of varieties, the establishment of year-round vegetable production, and the development of the seed export market. First, an F₁ hybrid system increased seed performance more than traditional open pollinated (OP) varieties with respect to productivity, uniformity and disease resistance. Moreover, an F₁ hybrid system required repetitive seed production and provision, which increased the economic growth of seed companies. Second, vegetables tend to be consumed fresh instead of dried or processed. Finally, vegetable seed exports have continuously increased with the aid of R&D projects such as the Golden Seed Project (GSP). Therefore, for further progress of the vegetable industry, new varieties that can meet consumers’ demands, as well as the stable provision of fresh vegetables, are required. Contrary to the past, the future focus must be concerned with productivity and cultivation stability, the development of high value, functional, eco-friendly vegetables, and high quality vegetables. To cope with this, every breeding subject, including industry, universities, and institutes, have to collaborate with the aim of advancing vegetable breeding in Korea.