• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.3
• /
• pp.33-38
• /
• 2021

Recently, transfer learning techniques with a base convolutional neural network (CNN) model have widely gained acceptance in early detection and classification of crop diseases to increase agricultural productivity with reducing disease spread. The transfer learning techniques based classifiers generally achieve over 90% of classification accuracy for crop diseases using dataset of crop leaf images (e.g., PlantVillage dataset), but they have ability to classify only the pre-trained diseases. This paper provides with an evaluation scheme on selecting an effective base CNN model for crop disease transfer learning with regard to the accuracy of trained target crops as well as of untrained target crops. First, we present transfer learning models called CDC (crop disease classification) architecture including widely used base (pre-trained) CNN models. We evaluate each performance of seven base CNN models for four untrained crops. The results of performance evaluation show that the DenseNet201 is one of the best base CNN models.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.58-58
• /
• 2022

With the development of advanced technology, automation of agricultural work is spreading. In association with the 4th industrial revolution-based technology, research on field smart farm technology is being actively conducted. A state-of-the-art unmanned automated agricultural production demonstration complex was established in Naju-si, Jeollanam-do. For the operation of the demonstration area platform, it is necessary to build a sophisticated, advanced, and intelligent field smart farming model. For the operation of the unmanned automated agricultural production demonstration area platform, we are building data on the growth of soybean for smart cultivated crops and conducting research to determine the optimal time for agricultural work. In order to operate an unmanned automation platform, data is collected to discover digital factors for water management immediately after planting, water management during the growing season, and determination of harvest time. A subsurface drip irrigation system was established for smart water management. Irrigation was carried out when the soil moisture was less than 20%. For effective water management, soil moisture was measured at the surface, 15cm, and 30cm depth. Vegetation indices were collected using drones to find key factors in soybean production prediction. In addition, major growth characteristics such as stem length, number of branches, number of nodes on the main stem, leaf area index, and dry weight were investigated. By discovering digital factors for effective decision-making through data construction, it is expected to greatly enhance the efficiency of the operation of the unmanned automated agricultural production demonstration area.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.59 no.3
• /
• pp.299-306
• /
• 2014

Fresh edible sweet corns demand relatively short period to harvest fresh ears, which can allow farmers to make a choice sweet corns for various cropping systems. For this reason, we were to find the optimum planting date of late-planted sweet corns to sell fresh ears in the autumn linked to cropping system with winter crops, investigating yield and properties of marketable fresh ears and growth traits of sweet corns (cv. 'Godangok' and cv. 'Guseulok') depending on planting dates such as 10 July, 20 July, and 30 July in Suwon 2012 and 2013, respectively. The 20 July-planted sweet corns showed the most fresh ear yield. However, the 10 July-planted and the 30 July-planted had 32% less yield caused by consecutive rainfall from 10 July through 20 July, and 15% less yield due to low air temperature during ripening than the 20 July-planted, respectively. The 10 and 20 July-planted sweet corns had average 140g of a fresh ear weight and 15% heavier ear than the 30 July-planted. For the July-planted sweet corns, silking days after planting ($r=-0.80^{**}$), and harvesting days after silking ($r=-0.97^{**}$) and planting ($r=-0.91^{**}$) were highly negatively correlated with daily mean air temperature during the period, resulting in it takes 1,100 growing degree days (GDD) to harvest fresh ears from the July-planted sweet corns. The fresh ears of the 20 July-planted sweet corns are able to be harvested by early October. Therefore it will be a good choice for the cropping system based on winter vegetable cash crops such as temperate garlic and onion with medium or late maturity. Among three planting dates 20 July-planted sweet corns had the best field performance in every year considering fresh ear yield, ear size, and stability to grow.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.267-267
• /
• 2017

In Korea, the average air temperature has been elevated twice faster than the average global warming. And the climate warming is characterized by the smaller rise of air temperature in summer and the greater rise of air temperature in spring and winter. Therefore, the number of frost-free days to determine the cultivation ability of crops has increased by more than 15 days in 10 years according to climate warming. This climate warming trend has extended and is projected to extend not only the sweet potato growing season but also the sweet potato early cultivating area to higher altitude and latitude region. This study was carried out to evaluate the possibility of sweet potato double cropping in the southern island area of Korea by assessing the growth and yield performance of sweet potato cultivated at extremely-early and -late time. We had performed at Yokji Island Yokji Island($E128^{\circ}$ 18' $N34^{\circ}$ 36'), a representative specified complex area of sweet potato cultivation in southern Korea. As the test varieties, the major cultivars of the this region, Shinyulmi and early hypertrophic cultivars, Dahomi were used. The prior cropping were planted with PE film mulching on March 30 and April 10, and harvested after 110 days. So the succeeding cropping were planted without PE film mulching on July 25 and August 5 according to the harvesting time of the prior sweet potato and harvested after 120 days. As a control, it was harvested on September 15, 120 days after planted on May 15. Each experimental plot had an area of 12 square meters consisting of 4 beds, and was planted one at a time at intervals of 25cm. We had investigated growth characteristics - main vine length, node number, branch number, total vine yield, and tuberous root characteristics - tuberous root number, average weight, starch value, and etc. After harvesting, we analyzed the economic effects by examining the postharvest quantity, the input labor, the management cost, and the income. The total yield of marketable products in prior and succeeding cropping was 46~70% higher than that of control. The average unit price of sweet potato was 36% higher than the conventional culture, and the gross income increased by 98%, but the operating cost increased by 83%, and the farm income increased by 103%. There are considerations such as the difficulty of enlargement of cultivation area due to lack of labor in limited space and the need for watering measures due to spring drought. However, if the area of application for sweet potatoes double system is increased by 10%, it can be used as a new cropping system.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.280-280
• /
• 2017

In Korea, the average air temperature has been elevated twice faster than the average global warming. And the climate warming is characterized by the smaller rise of air temperature in summer and the greater rise of air temperature in spring and winter. Therefore, the number of frost-free days to determine the cultivation ability of crops has increased by more than 15 days in 10 years according to climate warming. This climate warming trend has extended and is projected to extend not only the sweet potato growing season but also the sweet potato early cultivating area to higher altitude and latitude region. This study was carried out to evaluate the possibility of sweet potato double cropping in the southern island area of Korea by assessing the growth and yield performance of sweet potato cultivated at extremely-early and -late time. We had performed at Yokji Island Yokji Island($E128^{\circ}$ 18' $N34^{\circ}$ 36'), a representative specified complex area of sweet potato cultivation in southern Korea. As the test varieties, the major cultivars of the this region, Shinyulmi and early hypertrophic cultivars, Dahomi were used. The prior cropping were planted with PE film mulching on March 30 and April 10, and harvested after 110 days. So the succeeding cropping were planted without PE film mulching on July 25 and August 5 according to the harvesting time of the prior sweet potato and harvested after 120 days. As a control, it was harvested on September 15, 120 days after planted on May 15. Each experimental plot had an area of 12 square meters consisting of 4 beds, and was planted one at a time at intervals of 25cm. We had investigated growth characteristics - main vine length, node number, branch number, total vine yield, and tuberous root characteristics - tuberous root number, average weight, starch value, and etc. After harvesting, we analyzed the economic effects by examining the postharvest quantity, the input labor, the management cost, and the income. The total yield of marketable products in prior and succeeding cropping was 46~70% higher than that of control. The average unit price of sweet potato was 36% higher than the conventional culture, and the gross income increased by 98%, but the operating cost increased by 83%, and the farm income increased by 103%. There are considerations such as the difficulty of enlargement of cultivation area due to lack of labor in limited space and the need for watering measures due to spring drought. However, if the area of application for sweet potatoes double system is increased by 10%, it can be used as a new cropping system.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.68 no.4
• /
• pp.304-312
• /
• 2023

Plant breeding is a time-consuming process, mainly due to the limited annual generational advancement. A speed breeding system, using LED light sources, has been applied to accelerate generational progression in various crops. However, detailed protocols applicable to soybeans are still insufficient. In this study, we report the optimized protocols for a speed breeding system comprising 12 soybean varieties with various maturity ecotypes. We investigated the effects of two light qualities (RGB ratio), three levels of light intensity (PPFD), and two soil conditions on the flowering time and development of soybeans. Our results showed that an increase in the red wavelength of the light spectrum led to a delay in flowering time. Furthermore, as light intensity increased, flowering time, average internode length, and plant height decreased, while the number of nodes, branches, and pods increased. When compared to agronomic soil, horticultural soil resulted in an increase of more than 50% in the number of nodes, branches, and pods. Consequently, the optimal conditions were determined as follows: a 10-hour short-day photoperiod, an equal RGB ratio (1:1:1), light intensity exceeding 1,300 PPFD, and the use of horticultural soil. Under these conditions, the average flowering time was found to be 27.3±2.48 days, with an average seed yield of 7.9±2.67. Thus, the speed breeding systems reduced the flowering time by more than 40 days, compared to the average flowering time of Korean soybean resources (approximately 70 days). By using a controlled growth chamber that is unaffected by external environmental conditions, up to 6 generations can be achieved per year. The use of LED illumination and streamlined facilities further contributes to cost savings. This study highlights the substantial potential of integrating modern crop breeding techniques, such as digital breeding and genetic editing, with generational shortening systems to accelerate crop improvement.

• Korean Journal of Remote Sensing
• /
• v.31 no.5
• /
• pp.491-499
• /
• 2015

In developed countries such as USA and Europe, agricultural monitoring system is developed and utilized in various fields in order to predict crop yield, observe weather conditions and anomaly, categorize crop fields, and calculate areas for each crop. These system is Web Map Service(WMS) which utilizes open source and commercial softwares, and various information collected from remote sensing data are provided. This study will utilize tools such as GeoServer, ArcGIS Server, which are widely used to monitor agricultural production, to publish Map Server and Web Application Server. This enables performance test study for future agricultural production monitoring system by making use of response time and data transfer test. When tested in identical condition GeoServer showed a better result in response time and data transfer for performance test.

• Korean Journal of Soil Science and Fertilizer
• /
• v.51 no.2
• /
• pp.79-89
• /
• 2018

Subsurface drip irrigation (SDI) system is considered one of the most effective methods for water application. A 2-year field study was conducted to investigate the effect of SDI systems with various dripline spacing (0.7 or 1.4 m) and position (under furrow or ridge) on soybean (Glycine max L.) production at a sandy-loam soil in Miryang, South Korea. For 2016-2017, average grain yield in SDI irrigated plots, $3.16Mg\;ha^{-1}$, was statistically greater than rainfed irrigated plot ($2.63Mg\;ha^{-1}$). Soybean grain yield averaged $3.25Mg\;ha^{-1}$ for the 0.7 m dripline spacing and $3.07Mg\;ha^{-1}$ for the 1.4 m spacing for the two-year period compared to a rainfed irrigated average of $2.63Mg\;ha^{-1}$ for the same period. Soybean treated with SDI system had significantly greater values of normalized difference vegetation index and stomatal conductance, indicating that soybean plants in SDI plots had greater photosynthetic and stomatal activity due to the higher water availability in soil. Irrigation water use efficiency (IWUE) was greatest in the plot of 0.7 m spacing installed under ridge position than any other plot across growing season. Average soil water content in plots with 0.7 m dripline spacing was $0.21m^3\;m^{-3}$ at 5 cm depth layer, which was 45% greater compared to the plots with 1.4 m spacing, even though the gross irrigation amounts were greater in 1.4 m spacing plots. It is concluded that wide dripline spacing (1.4 m) is probably the more economical installation design for SDI system compared to 0.7 m spacing in this study soil because the initial cost for dripline may be reduced with wide spacing design, even though the IWUE is greater in the plot of 0.7 m dripline spacing.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.34 no.s01
• /
• pp.33-39
• /
• 1989

Ethylene gas classified as one of five major plant hormones plays an important role in various plant metabolism. The precise analysis of ethylene production of plants or plant parts is a valuable research procedure because knowledge of ethylene production facilitates measures of the physiological activity within the tissue. This paper describes procedures for analyzing ethylene from plant tissues by gas chromatography and discusses problems associated with extracting gas samples either by introducing a vacuum to plant samples or by using a hypodermic syringe. Introduced are a continuous flow system for efficient analysis and an automated system for sampling, analyzing, calculating and recording ethylene production data.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2000.11a
• /
• pp.225-226
• /
• 2000