• The Journal of Engineering Geology
• /
• v.32 no.4
• /
• pp.697-723
• /
• 2022

Data-driven models to predict groundwater levels 30 days in advance were developed for 12 groundwater monitoring stations in the middle-Jeju watershed, Jeju Island. Stacked long short-term memory (stacked-LSTM), a deep learning technique suitable for time series forecasting, was used for model development. Daily time series data from 2001 to 2022 for precipitation, groundwater usage amount, and groundwater level were considered. Various models were proposed that used different combinations of the input data types and varying lengths of previous time series data for each input variable. A general procedure for deep-learning-based model development is suggested based on consideration of the comparative validation results of the tested models. A model using precipitation, groundwater usage amount, and previous groundwater level data as input variables outperformed any model neglecting one or more of these data categories. Using extended sequences of these past data improved the predictions, possibly owing to the long delay time between precipitation and groundwater recharge, which results from the deep groundwater level in Jeju Island. However, limiting the range of considered groundwater usage data that significantly affected the groundwater level fluctuation (rather than using all the groundwater usage data) improved the performance of the predictive model. The developed models can predict the future groundwater level based on the current amount of precipitation and groundwater use. Therefore, the models provide information on the soundness of the aquifer system, which will help to prepare management plans to maintain appropriate groundwater quantities.

• Journal of Korea Water Resources Association
• /
• v.55 no.11
• /
• pp.931-939
• /
• 2022

In Korea, about two-thirds of the precipitation is concentrated in the summer season, so the problem of turbidity in the summer flood season varies from year to year. Concentrated rainfall due to abnormal rainfall and extreme weather is on the rise. The inflow of turbidity caused a sudden increase in turbidity in the water, causing a problem of turbidity in the dam reservoir. In particular, in Korea, where rivers and dam reservoirs are used for most of the annual average water consumption, if turbidity problems are prolonged, social and environmental problems such as agriculture, industry, and aquatic ecosystems in downstream areas will occur. In order to cope with such turbidity prediction, research on turbidity modeling is being actively conducted. Flow rate, water temperature, and SS data are required to model turbid water. To this end, the national measurement network measures turbidity by measuring SS in rivers and dam reservoirs, but there is a limitation in that the data resolution is low due to insufficient facilities. However, there is an unmeasured period depending on each dam and weather conditions. As a sensor for measuring turbidity, there are Optical Backscatter Sensor (OBS) and YSI, and a sensor for measuring SS uses equipment such as Laser In-Situ Scattering and Transmissometry (LISST). However, in the case of such a high-tech sensor, there is a limit due to the stability of the equipment. Therefore, there is an unmeasured period through analysis based on the acquired flow rate, water temperature, SS, and turbidity data, so it is necessary to develop a relational expression to calculate the SS used for the input data. In this study, the AEM3D model used in the Water Resources Corporation SURIAN system was used to improve the accuracy of prediction of turbidity through the turbidity-SS relationship developed based on the measurement data near the dam outlet.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.4
• /
• pp.1-15
• /
• 2023

This research intended to reveal the special characteristics of the vegetation structure and the tendency of change of -landfill slope districts, which are reclaimed land, through an investigationsinto the presently existent vegetation and plant community structure of the World Cup Park landfill slope district. For the analysis of changes in vegetation, this study compared the results of field surveys in 1999, 2003, 2005, 2007, 2008, 2012, 2016, and 2021. For the investigation into the plant community structure, a field investigation was carried out in 2021 with six fixed investigation districts designated in 1999 as subjects. To analyze the change in the plant community structure, the past data on the population, the number of the species, and the species diversity by the layer in 2021 were compared and analyzed in the landfill slope district, which is reclaimed land. The changes of the vegetation distribution and the power had been affected by typhoons (Kompasu). Above the plantation foundation, which had been dry and poor, Salix koreensis, marsh woody plants that had formed the community, decreased greatly. The Robinia pseudoacacia community, after the typhoon in 2010, decreased in the number of species and population. Afterward, it showed a tendency to rebound. Regarding the Ailanthus altissima-Robinia pseudoacacia-Paulownia tomentosa community, the number of the species and the population had shown a change similar to the Robinia pseudoacacia community. The Paulownia tomentosa and the Ailanthus altissima have been culled. The slope was predicted as a Future Robinia pseudoacacia forest. The Salix pseudolasiogyne community has been transitioning to a Robinia pseudoacacia forest. Only some enumeration districts, the Robinia pseudoacacia forests and the Salix pseudolasiogyne, had been growing. However, most had been in been declining. It was predicted that this community will be maintained as a Robinia pseudoacacia forest in the future. As these vegetation communities are the representative vegetation of the landfill slope districts, which is reclaimed land, there is a need to understand the ecosystem changes of the community through continuous monitoring. The results of this research can be utilized as a basic material for the vegetation restoration of reclaimed land.

• Korean Journal of Environment and Ecology
• /
• v.37 no.4
• /
• pp.259-272
• /
• 2023

This study set up 49 survey areas with an area of about 400 square meters in Abies koreana natural habitat to identify the species composition and vegetation structure of the A. koreana forest in the Mt. Jiri Nation Park, conducted field surveys using phytosociological methods, and performed the cluster analysis using the Two-Way Indicator Species Analysis (TWINSPAN) and Table manipulation. Subsequently, species composition analysis using the importance value, species diversity analysis, DBH analysis, sapling analysis, and similarity analysis was conducted by each cluster type. The cluster analysis classified the A. koreana forest in Mt. Jiri into five clusters, A, B, C, D, and E. The forest was divided into two clusters, Magnolia sieboldii-Dryopteris crassirhizoma-Sasa borealis and Betula ermanii-Solidago virgaurea-Calamagrostis arundinacea. The former was classified as type A and B by Cornus controversa-Hydrangea macrophylla, and the latter was classified as type E, a typical community, and a Sorbus commixta-Rhododendron mucronulatum cluster. And the S. commixta-R. mucronulatum cluster was divided into C type and D type by Picea jezoensis-Ligularia fischeri and Ainsliaea acerifolia. Through vegetation analysis, the importance value of A. koreana, Quercus mongolica, Acer pseudosieboldianum, Fraxinus sieboldiana, and B. ermanii was highly expressed in the A. koreana forest in Mt. Jiri. Regarding species diversity, the results were similar to those reported in other studies of A. koreana forests in Mt. Jiri. The analysis of diameter at breast height (DBH) showed that A. koreana dominated all layers, and the growth of saplings was also good, indicating that the dominance of A. koreana is expected to continue for a while. However, when considering the value of biodiversity that is expected to increase and threats caused by climate change, systematic preservation and management are required to respond to various threats based on continuous monitoring.

• (The) Research of the performance art and culture
• /
• no.43
• /
• pp.79-120
• /
• 2021

Nagyangchun is a Dangak that has been handed down to the present time with Boheoja as a Saak of the Song Dynasty which was introduced in the Goryeo Dynasty. The title and lyrics of Nagyangchun are conveyed in the Dangakjo of Goryeosa-akji and the Jeungbomunheonbigo. The remaining scores containing Nagyangchun include Akjangyoram, Sogagwonbo Vol.4 and Vol.6 of the Joseon Dynasty and Aakbu-akbo, the 6th Aaksaeng-gyogwacheol, Leewangjikaakbu-oseonakbo during the Japanese colonial period. Besides, the current melody of Nagyangchun is based on Hangugeumak and Gugakjeonjib published by the National Gugak Center. This paper aims to examine how Nagyangchun, which is currently being performed at the National Gugak Center, went through the process of change to have the same structure and form as it is now using these scores as a research subject. The study results are summarized as follows. First, the song of Nagyangchun, which was originally Saak but transmitted as an instrumental piece without lyrics, first appeared in the Hangugeumak Vol.16 and Gugakjeonjib Vol.7 published by the National Gugak Center in 1978 and 1979. In this process, the Janggu added by Kim Ki-soo is now disappearing and is replaced by Jwago. Second, though the five notes of 黃, 太, 仲, 林, and 南 have been maintained unchanged since the Akjangyoram, the pitch of 無/應 and 夾/姑, which appear once each, gradually rises and is unified into 應 and 姑 during the period of Aaksaeng-gyogwacheol or at the latest Leewangjikaakbu-oseonakbo, and reached the present. Third, the current melody of Nagyangchun consists of a structure in which the tones and range of each phrase rises within the form of Mijeonsa (a·b·c·d) and Mihusa (e·b'·c'·d'). Particularly, except for the a-type and e-type melodies, which are the introduction for the Mijeonsa and Mihusa, the remaining melodic types show a gradually descending structure within the corresponding phrase, so the structure of ascending and descending is generally in harmony. Forth, the Ganeum that appeared from Aakbu-akbo are currently classified into seven types, and they appear in ascending pitches of 2nd, 3rd, 4th, and 5th and play a role in smoothly or fluently connecting melodic progression. Fifth, after Akjangyoram, Nagyangchun, which had been handed down as an instrumental piece without lyrics, was restored in 1960 by Lee Hye-gu, and is being passed down as the form of male and female vocals added to the instrumental accompaniment. As a result of examining the current Nagyangchun, which was formed through the process of change after Akjangyoram, it was found that there were tasks that required reconsideration of the current Nagyangchun, which is being played at the National Gugak Center, such as the arrangement of Janggu, the identification of the key, and the investigation of the lyrics. When follow-up studies are continued in the future, it will be able to contribute to the cultural transmission of Nagyangchun.

• Korean Journal of Environmental Biology
• /
• v.40 no.4
• /
• pp.363-373
• /
• 2022

On April 29, 2021 (1st), June 2 (2nd), and August 17 (3rd), we surveyed benthic macroinvertebrates fauna at Muljangori-oreum wetland in Bonggae-dong, Jeju Island, Korea. Muljangori-oreum wetland was divided into four areas. The survey was conducted in three accessible areas (areas 1-3). As a result of habitat environment analysis, the average monthly temperature from 2017 to 2021 was the highest in July and August and the lowest in December and February. This pattern was repeated. As a result of analyzing changes in vegetation and water surface area through satellite images, normalized difference vegetation index (NDVI) increased from February to July and decreased after July. Normalized difference water index (NDWI) was analyzed to show an inverse relationship. A total of 21 species from 13 families were identified in the qualitative survey and a total of 412 individuals of 24 species from 15 families were identified in the quantitative survey. A total of 26 species from 17 families, 8 orders, 3 classes, and 2 phyla of benthic macroinvertebrates were identified. The dominant species was Chronomidae spp. with 132 individuals (32.04%). Noterus japonicus was a subdominant species with 71 individuals (17.23%). As a result of comparative analysis of species identified in this study and the literature, it was confirmed that species diversity was high for Coleoptera and Odonata. Main functional feeding groups (FFGs) were found to be predators. Habitat orientation groups (HOGs) were found to be swimmers. In OHC (Odonata, Hemiptera, and Coleoptera) group, 17 species (73.91%) in 2021, 23 species (79.31%) in 2016, 26 species (86.67%) in 2018, and 19 species (79.17%) in 2019 were identified. Cybister japonicus, an endangered species II, was confirmed to inhabit Muljangori-oreum wetland in the literature. Ten individuals (2.43%) were also confirmed to inhabit Muljangori-oreum wetland in 2021. Therefore, continuous management and habitat protection are required to maintain the habitat environment of C. japonicus in Muljangori-oreum wetland.

• Korean Journal of Animal Reproduction
• /
• v.25 no.1
• /
• pp.71-77
• /
• 2001

This experiment was designed to improve the production efficiency of germ-line chimeric mice from phospholipase C (PLC)-$\beta$3 or peroxiredoxin (Prx) E -targeted ($\Delta$) ES cells by the investigating the manipulation conditions and characteristics of Jl ES cells. Four targeting clones were isolated to investigate the karyotypical and morphological stability prior to injection. All clones ($\Delta$PLC$\beta$-3 C3, $\Delta$Prx II C3, C10 and I5) showed more than 80% euploidism, however, most of $\Delta$PLC$\beta$-3 C3 clones were extensively differentiated compared to the other clones. Nine of 13 $\Delta$Prx II chimeras appeared to have at least 80% chimerism, whereas $\Delta$PLC$\beta$-3 C3 chimeras had 20% chimerism at most. Therefore, the morphological stability of ES cells under stable euploidism might mainly affect the production rate of high-coat chimeric mice. To increase the collection rate of injectable blastocysts (IBs), 5 to 10 week -aged C57BL/6J female mice were sacrificed at 3.5 days post-coitum. Ten week-aged mice were the most optimal IB donors by showing the highest collection rate (2.94/mouse) of injectable blastocysts without increase of non-injectable embryos (0.29/mouse). Foster mothers might be another factor because ICR x C57BL/6J F1 foster mother showed more increased productivity in litter size (2.8 vs. 5.6) and chimera (0 vs. 35.3%) than those of ICR foster mothers. In conclusion, the efficient production of germ-line chimeras mainly depends on the maintenance of ES cell morphology during targeting procedure, and the establishment of manipulation conditions might be a key point to maximize it.

• Korean Journal of Environment and Ecology
• /
• v.37 no.2
• /
• pp.163-178
• /
• 2023

This study was conducted to understand the vegetation characteristics of Cheongwansan Provincial Park through the analysis of the plant community structure and to build data necessary for the continuous management and protection of Cheongwansan Provincial Park. The TWINSPAN and DCS analyses of the plant community structure of 63 survey districts in Cheongwansan Provincial Park identified eight colonies, including Cryptomeria japonica Community (I), Chamaecyparis obtusa-Pinus densiflora Commuity (II), P. rigida-P. densiflora Community (III), mixed coniferous and broad-leaved Community (IV), P. densiflora Community (V), deciduous broad-leaved such as Quercus spp. Community (VI), Q. mongolica-P. densiflora Community (VII) and P. thunbergii Community (VIII). The colonies can be grouped into afforestation communities (I, II, and III) dominated by C. obtusa, C. japonica, and P. rigida and natural forest communities (IV, V, VI, VII, and VIII) dominated by native species. Although Cheongwansan Provincial Park is a provincial park area that can represent natural ecosystems and landscapes, the rate of artificial forests is higher than that of other provincial parks. Most of the artificial forest communities are expected to maintain their current state, but since native species such as Machilus thunbergii, Neolitsea sericea, and deciduous broad-leaved, which are warm-temperate trees introduced through surrounding natural forests, appear in the lower layer, it is determined that it is possible to induce succession to natural forests suitable for climatic characteristics through management, and monitoring for continuous management is also necessary. Deciduous broad-leaved such as Quercus spp. Copete with P. densiflora in most natural forest communities. The vegetation series in the warm-temperate region of Korea appears to be in the early stages, and it is believed that the succession to Q. serrata or Q. mongolica, which appears next to coniferous in the series, is in progress. However, M. thunbergii and N. sericea, which appear in the middle stage of the succession in the warm-temperate region, have started to appear, and since Jangheung-gun belongs to the warm-temperate region considering the climate characteristics, the eventual succession to the warm-temperate forests dominated by evergreen broad-leaved is also expected. In this study, we built vegetation data from Cheongwansan Provincial Park, which lacks research on vegetation. However, since vegetation research in Cheongwansan Provincial Park is still insufficient, it is believed that further research should be continuously conducted to establish forest vegetation data and observe vegetation changes.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.5
• /
• pp.13-29
• /
• 2023

Urban parks are social infrastructure supporting citizens' health, quality of life, and community formation. As the proportion of urban parks that have been established for more than 20 years is increasing, the need for refurbishment to improve the physical space environment and enhance the functions of aging urban parks is increasing. Since the government's refurbishment of aging urban parks has limitations in securing financial resources and promoting attractiveness, they must be promoted through public-private partnerships. Japan, which suffered from the problem of aging urban parks, has successfully promoted several park refurbishment projects by introducing the Park-PFI through the revision of the 「Urban Park Act」 in 2017. This study examines and analyzes the characteristics of the Japan Park-PFI as an alternative to improving the quality of aging domestic urban park services through public-private partnerships and the validity of the aging urban park refurbishment projects through Park-PFI. The main findings are as follows. First, it is necessary to start discussions on introducing Japan's Park-PFI according to the domestic conditions as a means of public-private partnership to improve the service quality and diversify the functions of aging urban parks. In order to introduce Park-PFI social discussions and follow-up studies on the deterioration of urban parks. Must be conducted. The installation of private capital and profit facilities and improvements of related regulations, such as the 「Parks and Green Spaces Act」 and the 「Public Property Act」, is required. Second, it is judged that the Park-PFI project is a policy alternative that can enhance the benefits to citizens, local governments, and private operators under the premise that the need to refurbish aging urban parks is high and the location is suitable for promoting the project. As a result of a pilot application of the Park-PFI project to Seyeong Park, an aging urban park located in Bupyeong-gu, Incheon, it was analyzed to be profitable in terms of the profitability index (PI), net present value (FNPV), and internal rate of return (FIRR). It is considered possible to participate in the business sector. At the local government level, private capital is used to improve the physical space environment of aging urban parks, as well as the refurbishment of the urban parks by utilizing financial resources generated by returning a portion of the facility usage fees and profits (0.5% of annual sales) of private operators. It was found that management budgets could be secured.