• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.88-88
• /
• 2021

최근 수자원과 수질관리 분야에 자료기반 머신러닝 모델과 딥러닝 모델의 활용이 급증하고 있다. 그러나 딥러닝 모델은 Blackbox 모델의 특성상 고전적인 질량, 운동량, 에너지 보존법칙을 고려하지 않고, 데이터에 내재된 패턴과 관계를 해석하기 때문에 물리적 법칙을 만족하지 않는 예측결과를 가져올 수 있다. 또한, 딥러닝 모델의 예측 성능은 학습데이터의 양과 변수 선정에 크게 영향을 받는 모델이기 때문에 양질의 데이터가 제공되지 않으면 모델의 bias와 variation이 클 수 있으며 정확도 높은 예측이 어렵다. 최근 이러한 자료기반 모델링 방법의 단점을 보완하기 위해 프로세스 기반 수치모델과 딥러닝 모델을 결합하여 두 모델링 방법의 장점을 활용하는 연구가 활발히 진행되고 있다(Read et al., 2019). Process-Guided Deep Learning (PGDL) 방법은 물리적 법칙을 반영하여 딥러닝 모델을 훈련시킴으로써 순수한 딥러닝 모델의 물리적 법칙 결여성 문제를 해결할 수 있는 대안으로 활용되고 있다. PGDL 모델은 딥러닝 모델에 물리적인 법칙을 해석할 수 있는 추가변수를 도입하며, 딥러닝 모델의 매개변수 최적화 과정에서 Cost 함수에 물리적 법칙을 위반하는 경우 Penalty를 추가하는 알고리즘을 도입하여 물리적 보존법칙을 만족하도록 모델을 훈련시킨다. 본 연구의 목적은 대청호의 수심별 수온을 예측하기 위해 역학적 모델과 딥러닝 모델을 융합한 PGDL 모델을 개발하고 적용성을 평가하는데 있다. 역학적 모델은 2차원 횡방향 평균 수리·수질 모델인 CE-QUAL-W2을 사용하였으며, 대청호를 대상으로 2017년부터 2018년까지 총 2년간 수온과 에너지 수지를 모의하였다. 기상(기온, 이슬점온도, 풍향, 풍속, 운량), 수문(저수위, 유입·유출 유량), 수온자료를 수집하여 CE-QUAL-W2 모델을 구축하고 보정하였으며, 모델은 저수위 변화, 수온의 수심별 시계열 변동 특성을 적절하게 재현하였다. 또한, 동일기간 대청호 수심별 수온 예측을 위한 순환 신경망 모델인 LSTM(Long Short-Term Memory)을 개발하였으며, 종속변수는 수온계 체인을 통해 수집한 수심별 고빈도 수온 자료를 사용하고 독립 변수는 기온, 풍속, 상대습도, 강수량, 단파복사에너지, 장파복사에너지를 사용하였다. LSTM 모델의 매개변수 최적화는 지도학습을 통해 예측값과 실측값의 RMSE가 최소화 되로록 훈련하였다. PGDL 모델은 동일 기간 LSTM 모델과 동일 입력 자료를 사용하여 구축하였으며, 역학적 모델에서 얻은 에너지 수지를 만족하지 않는 경우 Cost Function에 Penalty를 추가하여 물리적 보존법칙을 만족하도록 훈련하고 수심별 수온 예측결과를 비교·분석하였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1143-1150
• /
• 2023

The global climate crisis and the implementation of low-carbon policies have led to a growing interest in renewable energy and a growing number of related industries. Among them, solar power is attracting attention as a representative eco-friendly energy that does not deplete and does not emit pollutants or greenhouse gases. As a result, the supplement of solar power facility is increasing all over the world. However, solar power is easily affected by the environment such as geography and weather, so accurate solar power forecast is important for stable operation and efficient management. However, it is very hard to predict the exact amount of solar power using statistical methods. In addition, the conventional prediction methods have focused on only short- or long-term prediction, which causes to take long time to obtain various prediction models with different prediction horizons. Therefore, this study utilizes a many-to-many structure of a recurrent neural network (RNN) to integrate short-term and long-term predictions of solar power generation. We compare various RNN-based very short- and long-term prediction methods for solar power in terms of MSE and R² values.

• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.367-375
• /
• 2023

This study developed a new distance metric for vessel trajectories, applicable to marine traffic control services in the Korean coastal waters. The proposed metric is designed through the weighted summation of the traditional Hausdorff distance, which measures the similarity between spatiotemporal data and incorporates the differences in the average Speed Over Ground (SOG) and the variance in Course Over Ground (COG) between two trajectories. To validate the effectiveness of this new metric, a comparative analysis was conducted using the actual Automatic Identification System (AIS) trajectory data, in conjunction with an agglomerative clustering algorithm. Data visualizations were used to confirm that the results of trajectory clustering, with the new metric, reflect geographical distances and the distribution of vessel behavioral characteristics more accurately, than conventional metrics such as the Hausdorff distance and Dynamic Time Warping distance. Quantitatively, based on the Davies-Bouldin index, the clustering results were found to be superior or comparable and demonstrated exceptional efficiency in computational distance calculation.

• Journal of the Korean earth science society
• /
• v.41 no.2
• /
• pp.95-110
• /
• 2020

Comparisons between two different surface temperatures from high-resolution ECMWF ReAnalysis 5 (ERA5) and Automated Synoptic Observing System (ASOS) observations were performed to investigate the reliability of the new reanalysis data over South Korea. As ERA5 has been recently produced and provided to the public, it will be highly used in various research fields. The analysis period in this study is limited to 1999-2018 because regularly recorded hourly data have been provided for 61 ASOS stations since 1999. Topographic characteristics of the 61 ASOS locations are classified as inland, coastal, and mountain based on Digital Elevation Model (DEM) data. The spatial distributions of whole period time-averaged temperatures for ASOS and ERA5 were similar without significant differences in their values. Scatter plots between ASOS and ERA5 for three different periods of yearlong, summer, and winter confirmed the characteristics of seasonal variability, also shown in the time-series of monthly error probability density functions (PDFs). Statistical indices NMB, RMSE, R, and IOA were adopted to quantify the temperature differences, which showed no significant differences in all indices, as R and IOA were all close to 0.99. In particular, the daily mean temperature differences based on 1-hour-averaged temperature had a smaller error than the classical daily mean temperature differences, showing a higher correlation between the two data. To check if the complex topography inside one ERA5 grid cell is related to the temperature differences, the kurtosis and skewness values of 90-m DEM PDFs in a ERA5 grid cell were compared to the one-year period amplitude among those of the power spectrum in the time-series of monthly temperature error PDFs at each station, showing positive correlations. The results account for the topographic effect as one of the largest possible drivers of the difference between ASOS and ERA5.

• Ecology and Resilient Infrastructure
• /
• v.7 no.4
• /
• pp.227-237
• /
• 2020

Microclimatic data were measured, and the human thermal sensation was analyzed at 10 local climate zones based on the major land cover classification to investigate the thermal environment of urban areas during summer nighttime. From the results, the green infrastructure areas (GNIAs) showed an average air temperature of 1.6℃ and up to 2.4℃ lower air temperature than the gray infrastructure areas (GYIAs), and the GNIAs showed an average relative humidity of 9.0% and up to 15.0% higher relative humidity. The wind speed of the GNIAs and GYIAs had minimal difference and showed no significance at all locations, except for the forest location, which had the lowest wind speed owing to the influence of trees. The local winds and the surface roughness, which was determined based on the heights of buildings and trees, appeared to be the main factors that influenced wind speed. At the mean radiant temperature, the forest location showed the maximum value, owing to the influence of trees. Except at the forest location, the GNIAs showed an average decrease of 5.5℃ compared to GYIAs. The main factor that influenced the mean radiant temperature was the sky view factor. In the analysis of the human thermal sensation, the GNIAs showed a "neutral" thermal perception level that was neither hot nor cold, and the GYIAs showed a "slightly warm" level, which was a level higher than those of the GNIAs. The GNIAs showed a 3.2℃ decrease compared to the GYIAs, except at the highest forest location, which indicated a half-level improvement in the human thermal environment.

• Korean Journal of Environmental Agriculture
• /
• v.37 no.4
• /
• pp.251-259
• /
• 2018

BACKGROUND: Various culture media have been used for hydroponic cultures of horticultural plants under the smart greenhouses with natural and artificial light types. Management of the culture medium for the control of medium amounts and/or necessary components absorbed by plants during the cultivation period is performed with ICT (Information and Communication Technology) and/or IoT (Internet of Things) in a smart farm system. This study was conducted to develop the cloud-based data analysis system for effective management of culture medium applying to hydroponic culture and plant growth in smart greenhouses. METHODS AND RESULTS: Conventional inorganic Yamazaki and organic media derived from agricultural byproducts such as a immature fruit, leaf, or stem were used for hydroponic culture media. Component changes of the solutions according to the growth stage were monitored and plant growth was observed. Red and green lettuce seedlings (Lactuca sativa L.) which developed 2~3 true leaves were considered as plant materials. The seedlings were hydroponically grown in the smart greenhouse with fluorescent and light-emitting diodes (LEDs) lights of $150{\mu}mol/m^2/s$ light intensity for 35 days. Growth data of the seedlings were classified and stored to develop the relational database in the virtual machine which was generated from an open stack cloud system on the base of growth parameter. Relation of the plant growth and nutrient absorption pattern of 9 inorganic components inside the media during the cultivation period was investigated. The stored data associated with component changes and growth parameters were visualized on the web through the web framework and Node JS. CONCLUSION: Time-series changes of inorganic components in the culture media were observed. The increases of the unfolded leaves or fresh weight of the seedlings were mainly dependent on the macroelements such as a $NO_3-N$, and affected by the different inorganic and organic media. Though the data analysis system was developed, actual measurement data were offered by using the user smart device, and analysis and comparison of the data were visualized graphically in time series based on the cloud database. Agricultural management in data visualization and/or plant growth can be implemented by the data analysis system under whole agricultural sites regardless of various culture environmental changes.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.19-43
• /
• 2016

This study examines the causes of the Asian exchange rate crisis and compares it to the European Monetary System crisis. In 1997, emerging countries in Asia experienced financial crises. Previously in 1992, currencies in the European Monetary System had undergone the same experience. This was followed by Mexico in 1994. The objective of this paper lies in the generation of useful insights from these crises. This research presents a comparison of South Korea, United Kingdom and Mexico, and then compares three different models for prediction. Previous studies of economic crisis focused largely on the manual construction of causal models using linear techniques. However, the weakness of such models stems from the prevalence of nonlinear factors in reality. This paper uses a structural equation model to analyze the causes, followed by a neural network model to circumvent the linear model's weaknesses. The models are examined in the context of predicting exchange rates In this paper, data were quarterly ones, and Consumer Price Index, Gross Domestic Product, Interest Rate, Stock Index, Current Account, Foreign Reserves were independent variables for the prediction. However, time periods of each country's data are different. Lisrel is an emerging method and as such requires a fresh approach to financial crisis prediction model design, along with the flexibility to accommodate unexpected change. This paper indicates the neural network model has the greater prediction performance in Korea, Mexico, and United Kingdom. However, in Korea, the multiple regression shows the better performance. In Mexico, the multiple regression is almost indifferent to the Lisrel. Although Lisrel doesn't show the significant performance, the refined model is expected to show the better result. The structural model in this paper should contain the psychological factor and other invisible areas in the future work. The reason of the low hit ratio is that the alternative model in this paper uses only the financial market data. Thus, we cannot consider the other important part. Korea's hit ratio is lower than that of United Kingdom. So, there must be the other construct that affects the financial market. So does Mexico. However, the United Kingdom's financial market is more influenced and explained by the financial factors than Korea and Mexico.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.394-394
• /
• 2015

급격히 변화하고 있는 산업화와 도시화로 지구 온난화 현상으로 기상이변의 발생빈도가 높아졌고 기후가 불안정하여 예전보다 많은 집중호우가 발생하면서, 홍수로 인한 제내지 침수가 발생되기도 한다. 기후변화로 인한 수재해에 대응하기 위하여 하천 호소 수리 예측 모형의 개선이 필요한 실정이다. 하지만, 자연하천 유역의 강우-유출 상관관계와 지표면 유출현상 및 하도 수리 특성을 자연현상의 복잡성, 강우발생의 시간적 공간적인 발생과정의 임의성, 정확한 해석방법 및 확률 분석에 따르는 불확실성 들을 토대로 단순한 이론과 제한적인 경험공식 등에 의해서 해석, 재현 및 평가를 한다는 것은 매우 어려운 문제이다. 최근 IT 기술의 발전과 더불어, 많은 연구자, 엔지니어들이 기존 수리 수문학적 지식과 IT기술을 융합하여 복잡 다단한 수자원 환경 문제를 해결하고자 한다. 이와 같은 최근 연구 동향에 의거하여, 본 연구에서는 HEC-RAS, TELEMAC-2D 1, 2차원 수리 모형을 연계하여 하천 흐름 분석 및 홍수 범람 해석에 적용하였다. 본 연구에서는 HEC-RAS, TELEMAC 모형을 적용하여 2012년 태풍 '산바(SANBA)'로 인해 홍수 피해를 입은 고령군에 위치한 낙동강 본류 회천 유역(상류 회천교 ~ 하류 도진교)의 하도 내 흐름 분석과 하천 인근 제내지 홍수범람을 예측하였다. 범람해석에 필요한 지형자료를 기초로 하여 각 지형의 조건에 맞게 수치자료를 이용하여 작성하였고, 수자원 정보를 이용하여 유랑, 수위 등 시계열자료를 지류 및 상 하류의 경계조건으로 설정하고, 조도계수 등 하천 기본정보들을 입력하였다. HEC-RAS 모형은 회천교부터 도진교까지 전구간에 대한 종단면과 횡단면별 홍수침수범위 및 홍수위 크기 등 거시적인 1차원 수리해석에 적용하였고, TELEMAC 모형은 HEC-RAS 시뮬레이션 결과를 바탕으로 HEC-RAS에서 나타내기 힘든 2차원 흐름특성, 침수현상 등 일부 범람 구간에 대해 수리해석에 적용하였다. HEC-RAS 시스템은 수공구조물들의 영향과 하천의 영향을 종 횡단면으로 다양한 홍수침수 범위를 1차원으로 나타 낼 수 있으며, TELEMAC 시스템 수리 모의를 통해 얻어진 결과는 유속, 유량, 수심, 하상고 높이 등 2차원으로 나타낼 수 있다. TELEMAC 시스템을 활용한 2차원 분석은 실측자료와 비교적 유사하고 시각, 공간적으로 이해하기 쉽게 표현되므로, 모형 적용성이 우수한 것으로 판단된다. 향후 유역 해석을 위한 수치데이터, 수위, 유량자료를 확보하여 HEC-RAS, TELEMAC 1, 2차원 연계 모형을 적용 한다면, 하천 준설, 하천 구조물 설치, 홍수피해 등 전반적인 하천관리 계획에 활용할 수 있을 것이라 판단된다.

• Korean Journal of Ecology and Environment
• /
• v.45 no.4
• /
• pp.474-481
• /
• 2012

This study was performed to investigate the degree of long-term pollution at the mainstream of the Han River by comparing the concentration of BOD and COD from 1975 to 2011. The long-term annual average BOD and COD concentration at the mainstream of the Han River showed an increasing trend as it flowed downstream from Paldang Dam to Gayang. The concentration of BOD ($r^2$=0.646) and COD ($r^2$=0.260) showed a consistent decreasing trend for 37 years. In the case of Paldang Dam, BOD has maintained a decreasing trend, whereas the COD value showed an increasing trend after the 1990s. Therefore, a control of non-biodegradable materials in areas around Paldang Dam is required. The result of the seasonal variations of BOD and COD is as follows: spring>winter>summer and fall (p<0.001). The time series analysis revealed a strong correlation for every 12-month period. Also, the amount of water discharge at Paldang Dam has to be systematically controlled because the amount of water discharge from the dam influences the water quality at the mainstream of the Han River.

• Korean Journal of Ecology and Environment
• /
• v.48 no.4
• /
• pp.238-252
• /
• 2015

The effect of weir construction (2009~2011) was investigated on algal bloom dynamics and surrounding conditions in the Youngsan River by analyzing the long-term (2001~2014) data provided by the Water Information System, Ministry of Environment. The data include chlorophyll a and water properties such as total suspended solids (TSS), ammonium ($NH_4{^+}$), nitrate ($NO_3{^-}$), orthophosphate ($PO{_4}^{3-}$), total nitrogen (TN), total phosphorus (TP) and DIN/DIP molar ratio collected from 12 stations along the channel of the river. Temporal variations were examined using data collected monthly from 2001~2014 and Box-Whisker plot was used to examine the difference in algal bloom dynamics between before (2006~2008) and after (2012~2014) the weir construction. Pearson's correlation analysis was also used to analyze the correlation of parameters. The results showed that TSS affecting water turbidity increased during the construction but decreased especially at the stations located in the upper and middle regions of the river after the construction. Ammonium concentrations increased whereas the concentrations of other nutrients decreased after the construction inducing an increase in N:P molar ratio. Chlorophyll a decreased suddenly during the construction but increased clearly after the construction at the stations where TSS decreased. This indicates that algal blooms can develop in the Youngsan River due to a decrease in turbidity that increases light penetration in water column although the concentrations of nutrients such as orthophosphate were reduced after the weir construction.