• Korean Journal of Agricultural Science
• /
• v.49 no.2
• /
• pp.193-202
• /
• 2022

The recurrent neural network (RNN) algorithm has been widely used in water-related research areas, such as water level predictions and water quality predictions, due to its excellent time series learning capabilities. However, studies on water quality predictions using RNN algorithms are limited because of the scarcity of water quality data. Therefore, most previous studies related to water quality predictions were based on monthly predictions. In this study, the quality of the water in a reservoir in Nonsan, Chungcheongnam-do Republic of Korea was predicted using the RNN-LSTM algorithm. The study was conducted after constructing data that could then be, linearly interpolated as daily data. In this study, we attempt to predict the water quality on the 7th, 15th, 30th, 45th and 60th days instead of making daily predictions of water quality factors. For daily predictions, linear interpolated daily water quality data and daily weather data (rainfall, average temperature, and average wind speed) were used. The results of predicting water quality concentrations (chemical oxygen demand [COD], dissolved oxygen [DO], suspended solid [SS], total nitrogen [T-N], total phosphorus [TP]) through the LSTM algorithm indicated that the predictive value was high on the 7th and 15th days. In the 30th day predictions, the COD and DO items showed R² that exceeded 0.6 at all points, whereas the SS, T-N, and T-P items showed differences depending on the factor being assessed. In the 45th day predictions, it was found that the accuracy of all water quality predictions except for the DO item was sharply lowered.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.450-450
• /
• 2021

기후변화 보고서에 따르면 집중 호우의 강도 및 빈도 증가가 향후 몇 년동안 지속될 것이라 제시하였다. 이러한 집중호우가 빈번히 발생하게 된다면 강우 침식성이 증가하여 표토 침식에 더 취약하게 발생된다. Universal Soil Loss Equation (USLE) 입력 매개 변수 중 하나인 강우침식능인자는 토양 유실을 예측할때 강우 강도의 미치는 영향을 제시하는 인자이다. 선행 연구에서 USLE 방법을 사용하여 강우침식능인자를 산정하였지만, 60분 단위 강우자료를 이용하였기 때문에 정확한 30분 최대 강우강도 산정을 고려하지 못하는 한계점이 있다. 본 연구의 목적은 강우침식능인자를 이전의 진행된 방법보다 더 빠르고 정확하게 예측하는 머신러닝 모델을 개발하며, 총 월별 강우량, 최대 일 강우량 및 최대 시간별 강우량 데이터만 있어도 산정이 가능하도록 하였다. 이를 위해 본 연구에서는 강우침식능인자의 산정 값의 정확도를 높이기 위해 1분 간격 강우 데이터를 사용하며, 최근 강우 패턴을 반영하기 위해서 2013-2019년 자료로 이용했다. 우선, 월별 특성을 파악하기 위해 USLE 계산 방법을 사용하여 월별 강우침식능인자를 산정하였고, 국내 50개 지점을 대상으로 계산된 월별 강우침식능인자를 실측 값으로 정하여, 머신러닝 모델을 통하여 강우침식능인자 예측하도록 학습시켜 분석하였다. 이 연구에 사용된 머신러닝 모델들은 Decision Tree, Random Forest, K-Nearest Neighbors, Gradient Boosting, eXtreme Gradient Boost 및 Deep Neural Network을 이용하였다. 또한, 교차 검증을 통해서 모델 중 Deep Neural Network이 강우침식능인자 예측 정확도가 가장 높게 산정하였다. Deep Neural Network은 Nash-Sutcliffe Efficiency (NSE) 와 Coefficient of determination (R²)의 결과값이 0.87로서 모델의 예측성을 입증하였으며, 검증 모델을 테스트 하기 위해 국내 6개 지점을 무작위로 선별하여 강우침식능인자를 분석하였다. 본 연구 결과에서 나온 Deep Neural Network을 이용하면, 훨씬 적은 노력과 시간으로 원하는 지점에서 월별 강우침식능인자를 예측할 수 있으며, 한국 강우 패턴을 효율적으로 분석 할 수 있을 것이라 판단된다. 이를 통해 향후 토양 침식 위험을 지표화하는 것뿐만 아니라 토양 보전 계획을 수립할 수 있으며, 위험 지역을 우선적으로 선별하고 제시하는데 유용하게 사용 될 것이라 사료된다.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.168-168
• /
• 2022

According to the 5th Climate Change Report, global average temperature in 2081~2100 will increase 1.8℃ based on RCP 4.5 and 3.7℃ based on RCP 8.5 from the current climate value (IPCC Working Group I AR5). As temperature is expected to increase due to global warming and the intensity and frequency of rainfall are expected to increase, damage to crops is expected, and countermeasures must be taken. This study intends to evaluate rice growth in terms of nitrogen utilization efficiency according to future climate change conditions. In this experiment, Oryza sativa cv. Shindongjin were planted at the SPAR facility of the NICS in Wanju-gun, Jeollabuk-do on June 10, and were planted and grown according to the standard cultivation method. Cultivation conditions are high temperature, high CO₂ (current temperature+4.7℃·CO₂ 800ppm), high temperature (current temperature+4.7℃·CO₂ 400ppm), current climate (current tempreture·CO₂ 400 ppm). Nitrogen was varied as 0, 9, 18 kg/10a. The N content and C/N ratio of all rice leaves, stems, and seeds increased at high temperature, and the N content and C/N ratio decreased under high temperature and high CO₂ conditions com pared to high temperature. Compared to the current climate, NUE increases by about 8% under high temperature and high CO₂ conditions and by about 2% under high temperature conditions. This seems to be because the increase in temperature and CO₂ induced the increase in biomass. ANUE related to yield decreased by about 70% compared to the current climate under high temperature conditions, and decreased by about 45% at high temperature and high CO₂, showing a tendency to decrease compared to high temperature. This appears to be due to reduced fertility and poor ripening due to high temperature stress. However, as the nitrogen increased, the number of ears and the number of grains increased, slightly offsetting the production reduction factor.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.21 no.1
• /
• pp.24-35
• /
• 2016

To assess the relationship between environmental factors and seasonal phytoplankton community structure, we investigated abiotic and biotic factors in Ulsan Bay, Korea. We divided the bay into two areas based on geographical characteristics and compared the difference in each factor between inner and outer bay with t-test statistics. As a result, temperature in the outer bay was higher than that of the inner bay during winter (t = -5.833, p < 0.01) and autumn (p > 0.05). However, opposite trend was observed during spring (t = 4.247, p < 0.01) and summer (t = 2.876, p < 0.05). Salinity was significantly lower in the inner bay than in the outer bay in winter, spring, and summer (p < 0.01). However, the salinity was not significantly different between the inner and the outer bay in the autumn (p > 0.05). In particular, high nutrient concentration was observed in most stations during winter season due to vertical well mixing. The nutrient concentration was significantly higher in surface layers of inner bay after rainfall, particularly in the summer. The relative contribution (approximately 70%) of < $20{\mu}m$ (nano and pico) size phytoplankton was increased in all seasons with continuously low nutrients from the offshore water due to their adaption to low nutrient without other large competitors. Interestingly, high population of Eutreptiella gymnastica was kept in the inner bay during the spring and summer associated with high DIN (nitrate+nitrite, ammonium) after river discharge following rainfall, suggesting that DIN supply might have triggered the increase of Eutreptiella gymnastica population. In addition, high density of freshwater species Oscillatoria sp. and Microcystis sp. were found in several stations of the inner bay that were provided with large amounts of freshwater from the Tae-wha River. Diatom and cryptophyta species were found to be dominant species in the autumn and winter. Of these, centric diatom Chaetoceros genus was occupied in the outer bay in the autumn. Cryptophyta species known as opportunistic micro-algae were found to have high biomass without competitors in the inner bay. Our results demonstrated that Ulsan Bay was strongly affected by freshwater from Tae-wha River during the rainy season and by the surface warm water current from the offshore of the bay during dry season. These two external factors might play important roles in regulating the seasonal phytoplankton community structures.

• Journal of Wetlands Research
• /
• v.19 no.1
• /
• pp.30-36
• /
• 2017

SS(Suspended Solid) concentration by soil erosion into river at normal and flood season should be measured. However, to present the variation of SS due to various development project such as EIA(Environmental Impact Assessment), River Master Plan, and so on, it is necessary to estimate not measure SS, but there are not exist how to estimate SS. In the present study, therefore, we propose the hydrologic method of estimating SS concentration using the results of particular frequency flood discharge and sediment discharge by RUSLE method. SS consists of silty and clay soil and colloid particle etc. However, in the present study, silty and clay soils of sediment discharge except send set up SS standards. The flow discharge to estimate SS concentration are 1~2 years for normal season, 30~100 years for flood season. Meanwhile, analysis software for probable rainfall uses Fard2006, probable rainfalls under 2-year frequency are estimated using rainfall data and frequency factor of Gumbel distribution. The results of estimating SS concentration using runoff volume by sediment and flow discharges of silty and cray soils as above method show that reliable level of SS concentration is considered in predevelopment of natural condition and under development of barren condition. Especially, SS concentration takes notice that the value of sediment discharge makes a huge difference according to channel slope, it was confirmed that the value obtained by dividing the SS concentration by the channel slope is relatively constant even though the topographical factors are different. Therefore, if the present study will be proceeded for various watersheds, it will be developed as estimation method of SS concentration.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.3
• /
• pp.3-10
• /
• 2010

The development of various spatial information and GIS has led to the research on interpretation of natural phenomena and correlational studies. This study is aimed to analyze the correlation between RUSLE(Revised Universal Soil Loss Equation) around Nakdong River area during the period of 1955 to 2005 and the amount of area change in the islets at the estuary terrain calculated in the study "Change Detection at the Nakdong Estuary Delta using Satellite Image and GIS". For the calculation of RUSLE, The 'Revised-USLE' model, a modified USLE model commonly used in Korea was used. For the rainfall erosion factor to calculate and compare the area of islets, the actual observation data for one year before the observation of satellite image from all observatories across Korea was used. The correlation coefficient between RUSLE and area change of islets was 0.57 for Jinwoo Islet; 0.7 for Sinja Islet; 0.87 for Doyodeung. This results showed that there was a great influence from Doyodeung where the main water way of Nakdong River runs. This study showed that the study using USLE for various fields and through identifying the characteristics of each factor is useful to understand natural phenomenon in practice.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.58 no.6
• /
• pp.23-30
• /
• 2016

Soil loss is an accompanying phenomenon of hydrologic cycle in watersheds. Both rainfall drops and runoff lead to soil particle detachment, the detached soil particles are transported into streams by runoff. Here, a sediment-laden water problem can be issued if soil particles are severely detached and transported into stream in the watershed. There is a need to estimate or simulate soil erosion in watersheds so that an adequate plan to manage soil erosion can be established. Universal Soil Loss Equation (USLE), therefore, was developed and modified by many researchers for their watersheds, moreover the simple model, USLE, has been employed in many hydrologic models for soil erosion simulations. While the USLE has been applied even in South-Korea, the model is often regarded as being limited in applications for the watersheds in South-Korea since monthly conditions against soil erosion on soil surface are not capable to represent. Thus, the monthly USLE factors against soil erosion, soil erodibility and crop management factors, were established for four major watersheds, which are Daecheong-dam, Soyang-dam, Juam-dam, and Imha-dam watersheds. The monthly factors were established by recent fifteen years from 2000 to 2015. Five crops were selected for the monthly crop management factor establishments. Soil loss estimations with the modified factors were compared to conventional approach that is average annual estimations. The differences ranged from 9.3 % (Juam-dam watershed) to 28.1 % (Daecheong-dam watershed), since the conventional approaches were not capable of seasonally and regionally different conditions.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.5
• /
• pp.506-513
• /
• 2020

Due to climate change, there is an increasing risk of complex (hybrid) disasters, comprising rising sea-levels, typhoons, and torrential rains. This study focuses on Marine City, Busan, a new residential city built on a former landfill site in Suyeong Bay, which recently suffered massive flood damage following a combination of typhoons, storm surges, and wave overtopping and run-up. Preparations for similar complex disasters in future will depend on risk impact assessment and prioritization to establish appropriate countermeasures. A framework was first developed for this study, followed by the collection of data on flood prediction and socioeconomic risk factors. Five socioeconomic risk factors were identified: (1) population density, (2) basement accommodation, (3) building density and design, (4) design of sidewalks, and (5) design of roads. For each factor, absolute criteria were determined with which to assess their level of risk, while expert surveys were consulted to weight each factor. The results were classified into four levels and the risk level was calculated according to the sea-level rise predictions for the year 2100 and a 100-year return period for storm surge and rainfall: Attention 43 %, Caution 24 %, Alert 21 %, and Danger 11 %. Finally, each level, indicated by a different color, was depicted on a complex disaster risk map.

• Spatial Information Research
• /
• v.14 no.4 s.39
• /
• pp.363-377
• /
• 2006

Mean annual soil loss was calculated and critical soil erosion areas were identified for the Congaree River Basin in South Carolina, USA using the Revised Universal Soil Loss Equation (RUSLE) model. In the RUSLE model, the mean annual soil loss (A) can be calculated by multiplying rainfall-runoff erosivity (R), soil erodibility (K), slope length and steepness (LS), crop-management (C), and support practice (P) factors. The critical soil erosion areas can be identified as the areas with soil loss amounts (A) greater than the soil loss tolerance (T) factor More than 10% of the total area was identified as a critical soil erosion area. Among seven subwatersheds within the Congaree River Basin, the urban areas of the Congaree Creek and the Gills Creek subwatersheds as well as the agricultural area of the Cedar Creek subwatershed appeared to be exposed to the risk of severe soil loss. As a prototype model for examining future effect of human and/or nature-induced changes on soil erosion, the RUSLE model customized for the area was embedded into ESRI ArcGIS ArcMap 9.0 using Visual Basic for Applications. Using the embedded model, users can modify C, LS, and P-factor values for each subwatershed by changing conditions such as land cover, canopy type, ground cover type, slope, type of agriculture, and agricultural practice types. The result mean annual soil loss and critical soil erosion areas can be compared to the ones with existing conditions and used for further soil loss management for the area.

• Korean Journal of Environmental Biology
• /
• v.29 no.2
• /
• pp.98-106
• /
• 2011

In order to investigate water quality factors controlling chlorophyll-$a$ concentrations, the by-daily monitoring was conducted from February to November 2010 in 4 stations of Masan Bay. Seasonal variability in physico-chemical factors was mainly controlled by freshwater loading as a result of precipitation: chemical oxygen demand, suspended solids and nutrient concentrations rapidly increase during the heavy rainy season, whereas they decrease in the dry season. From late winter to mid spring, phosphorus and silica sources relative to Redfield ratio were probably functioned as limiting factor for phytoplankton flourishing in surface waters, but nitrogen concentration during mid-spring to autumn might be responsible for the increase of phytoplankton biomass. The multiple regression analysis revealed that variations in chlorophyll-$a$ concentration may be strongly correlated with changes of water temperature, chemical oxygen demand, dissolved inorganic phosphorus in spring, and salinity, chemical oxygen demand and precipitation in summer. Consequently, in the Masan Bay, a heavy rainfall event is an important factor to determine changes of biotic and abiotic factors, and in addition the dynamics of chlorophyll-$a$ concentration are strongly affected by changes of hydrological factors, especially water temperature, precipitation and nutrients.