• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.133-133
• /
• 2023

풍화작용에 의해 생성된 유사는 자연 매체에 의해 이동하고 하천에 도달하기 이전이나 이후 퇴적되며, 해당 과정 중에서 하상변동, 홍수위 상승, 제방 안정성, 두부 침식, 생태환경 변화, 수질문제 등 다양한 침식과 퇴적 관련 문제들이 발생한다. 이러한 유사 문제의 해결과 지속적인 하천관리를 위해서는 유사의 생성, 이송, 그리고 퇴적 과정에 대한 충분한 이해와 정량적인 유사량을 파악하는 것이 필수적이다. 다양한 연구들을 통해서 유사량을 정량적으로 파악하기 위해 여러 종류의 모델과 공식들이 제안 되어져 왔다. 그 중 경험적 모델의 경우 실제로 관측된 값을 기반으로 하며, 복잡한 계산이나 요구하는 자료가 다른 종류의 모델들 보다 적어 쉽게 접근이 가능하다. 이러한 경험적 모델은 유사에 영향을 주는 인자를 규명하거나 특정 유역이나 지역에서 이송 및 퇴적 되는 유사의 출처와 특성을 규명하는 초기 단계에서 유용하게 이용된다. 국내 하천의 경우 여름에 강우가 집중되고 대부분의 국토가 산지로 이루어져있어 상류에서 침식이 주로 발생한다. 또한, 본류 및 하류 지역의 하천은 유사의 퇴적이 주로 일어나서 하천의 형태와 물길이 형성된 충적 하천 형태로 발전 되어있기 때문에 국내 하천에서는 전반적으로 국부적이며 다양한 형태의 유사 관련 문제가 발생한다. 국내 하천에서 발생하는 유사 관련 문제를 해결하기 위해 국내 하천의 유사량을 추정하는 다양한 경험적 모델들이 지속적으로 개발되어왔다. 하지만 과거에 개발된 모델들의 경우 계측 자료가 충분하지 않은 시기에 개발 되었으며, 현재에는 활용하기 불가능하다. 본 연구에서는 국내 하천의 비유사량을 예측하는 동시에 국내 하천의 유사 특성을 이해하기 위해 과거에 국내 하천을 대상으로 비유사량을 추정하기 위해 개발되었던 경험적 모델을 개선하였다. 본 연구를 통해 기존 경험 모델의 경우 주기적인 업데이트가 필요함을 확인하였으며, 개발된 모델의 경우 국내 하천 유사 관리를 위해 미래 유사량 예측하는 등 다양한 방면으로 활용 관리가 가능할 것으로 보인다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.198-203
• /
• 2020

In this paper, we propose an artificial water level prediction system for small river flood prediction. River level prediction can be a measure to reduce flood damage. However, it is difficult to build a flood model in river because of the inherent nature of the river or rainfall that affects river flooding. In general, the downstream water level is affected by the water level at adjacent upstream. Therefore, in this study, we constructed an artificial intelligence model using Recurrent Neural Network(LSTM) that predicts the water level of downstream with the water level of two upstream points. The proposed artificial intelligence system designed a water level meter and built a server using Nodejs. The proposed neural network hardware system can predict the water level every 6 hours in the real river.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1143-1154
• /
• 2021

The selection of activation function has a great influence on the groundwater level prediction performance of artificial neural network (ANN) model. In this study, five activation functions were applied to ANN model for two groundwater level observation wells in the middle mountainous area of the Pyoseon watershed in Jeju Island. The results of the prediction of the groundwater level were compared and analyzed, and the optimal activation function was derived. In addition, the results of LSTM model, which is a widely used recurrent neural network model, were compared and analyzed with the results of the ANN models with each activation function. As a result, ELU and Leaky ReLU functions were derived as the optimal activation functions for the prediction of the groundwater level for observation well with relatively large fluctuations in groundwater level and for observation well with relatively small fluctuations, respectively. On the other hand, sigmoid function had the lowest predictive performance among the five activation functions for training period, and produced inappropriate results in peak and lowest groundwater level prediction. The ANN-ELU and ANN-Leaky ReLU models showed groundwater level prediction performance comparable to that of the LSTM model, and thus had sufficient potential for application. The methods and results of this study can be usefully used in other studies.

• Journal of Korea Water Resources Association
• /
• v.33 no.2
• /
• pp.247-262
• /
• 2000

In this paper, the WSANN(Water Stage Analysis with Neural Network) model was presented so as to predict flood water stage at Jindong which has been the major stream gauging station in Nakdong river basin. The WSANN model used the improved backpropagation training algorithm which was complemented by the momentum method, improvement of initial condition and adaptive-learning rate and the data which were used for this study were classified into training and testing data sets. An empirical equation was derived to determine optimal hidden layer node between the hidden layer node and threshold iteration number. And, the calibration of the WSANN model was performed by the four training data sets. As a result of calibration, the WSANN22 and WSANN32 model were selected for the optimal models which would be used for model verification. The model verification was carried out so as to evaluate model fitness with the two-untrained testing data sets. And, flood water stages were reasonably predicted through the results of statistical analysis. As results of this study, further research activities are needed for the construction of a real-time warning of the impending flood and for the control of flood water stage with neural network method in river basin. basin.

• Journal of Korea Water Resources Association
• /
• v.35 no.4 s.129
• /
• pp.359-366
• /
• 2002

The damages from the natural disasters, especially from the floods, have been increasing. Therefore, it is imperative to establish a BMP to diminish the damages from the floods and to enhance the welfare of the nation. Developed countries have been generating and utilizing flood risk maps to raise the alertness of the residents, and thereby achieving efficient flood management. The major objectives of this research were to develop a prototype management system for flood risk map to forecast the boundaries oi the inundation and to plot them through the integration of geographic and hydrologic database. For more efficient system development, the user requirement analysis was made. The GIS database design was done based on the results from the research work of river information standardization. A GIS database for the study area was built by using topographic information to support the hydrologic modeling. The developed prototype include several modules; river information edition module, map plotting module, and hydrologic modeling support module. Each module enabled the user to edit graphic and attribute data, to analyze and to represent the modeling results visually. Subjects such as utilization of the system and suggestions for future development were discussed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.3
• /
• pp.635-642
• /
• 2018

In the Era of the Fourth Industrial Revolution, we live in huge amounts of software. However, as software increases, software vulnerabilities are also increasing. Therefore, it is important to detect and remove software vulnerabilities. Currently, many researches have been studied to predict and detect software security problems, but it takes a long time to detect and does not have high prediction accuracy. Therefore, in this paper, we describe a method for efficiently predicting software vulnerabilities using machine learning algorithms. In addition, various machine learning algorithms are compared through experiments. Experimental results show that the k-nearest neighbors prediction model has the highest prediction rate.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.298-298
• /
• 2021

본 연구에서는 국내 6개 지역 서울, 강릉, 대전, 광주, 부산, 제주의 30년 치 시강우 자료에 해석적 확률모형(Analytical Probabilistic Models) 방법을 적용하여 도시 홍수 저감을 목적으로 하는 저류시설 설계를 위한 유출량 예측 정도를 지역별로 비교하고자 하였다. 강우 사상 분포의 해석적 확률모형을 적용하기 위해 무강우 시간을 결정하여 독립 호우를 결정하는데, 자기상관계수와 변동계수를 활용한 무강우 지속시간의 산정(IETD, Interevent Time Definition) 방법을 사용하였다. 해석적 확률모형인 유출량의 확률밀도함수(PDF, Probability Density Function)를 유도하기 위해서 불투수 지역과 투수 지역의 영향을 고려하여 유출계수를 적용하는 강우-유출 관계를 가지고 유출량을 정의하였다. 강우량, 강우 지속시간, 무강우시간과 같은 강우특성은 1변수 지수함수의 PDF를 따른다고 가정하였다. 확률모형 방법의 적합성을 판단하기 위해 결정된 IETD에 따라 각 지역별로 실제 강우 사상을 해석적 모델과 연속모의실험인 SWWM(Storm Water Management Model)에 적용하여 불투수율에 따른 유출량을 산정하였다. 각 방식으로 얻은 유출량 결과는 모든 지역에서 매우 유사하게 나타났고 결론적으로 우리나라에서 도시 홍수 저감을 위한 저류시설의 계획과 설계에 확률모형 방법이 적용 가능하다는 것을 확인할 수 있었다.

• The KIPS Transactions:PartD
• /
• v.19D no.1
• /
• pp.113-120
• /
• 2012

Today, Internet users can easily create and share the digital contents with others through various online content sharing services such as YouTube. So, many portal sites are flooded with lots of user created contents (UCC) in various media such as texts and videos. Estimating popularity of UCC is a crucial concern to both users and the site administrators. This paper proposes a method to predict the popularity of Internet articles, a kind of UCC, using the dynamics of the online contents themselves. To analyze the dynamics, we regarded the access counts of Internet posts as the popularity of them and analyzed the variation of the access counts. We derived a model to predict the popularity of a post represented by the time series of access counts, which is based on an exponential function. According to the experimental results, the difference between the actual access counts and the predicted ones is not more than 10 for 20,532 posts, which cover about 90.7% of the test set.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.224-224
• /
• 2023

국내·외로 Soil and Water Assessment Tool (SWAT) 모델은 유역 단위에서 유출 및 수질을 예측하는데 활용되고 있다. 하지만 SWAT 모델의 결과물은 데이터 테이블 형식으로만 이루어져 있기 때문에 모델 사용자가 유역 내 하천별 수문 모의 결과물을 직관적으로 확인하기 어렵다는 단점이 있다. 최근 다양한 분야에서 3D 가상환경을 구축하는데 디지털 트윈 기술의 활용성이 증가하고 있다. 디지털 트윈 기술은 현실의 공간을 가상환경으로 구축해 실시간 현실의 상황을 파악하여, 의사결정 지원을 제공한다는 장점이 있다. 이에 본 연구에서는 디지털 트윈 기술과 SWAT 모델을 연계하여, 모델의 결과값을 가상환경 3D 지도인 CESIUM에 실시간으로 표출할 수 있는 디지털 트윈 기반 SWAT 모델 수문 모의 시스템을 개발하였다. 이 시스템은 3D 지형에 SWAT 모델을 통해 모의 된 하천의 수위 및 SS에 대한 표출이 가능할 뿐만 아니라 기후나 유역환경에 따른 유역 내 수문 변화를 시·공간적으로 파악할 수 있는 장점이 있다. 향후 본 연구에서 개발된 디지털 트윈 기반 SWAT 모델 수문 모의 시스템은 홍수 및 가뭄과 같은 재해에 대응할 수 있는 유역 및 하천관리 대책을 효율적으로 수립하는데 활용될 수 있을 것으로 판단된다.

• Smart Media Journal
• /
• v.12 no.10
• /
• pp.93-101
• /
• 2023

Climate change has emerged as a global problem, with frequent temperature increases, droughts, and floods, and it is predicted that it will have a great impact on the characteristics and productivity of crops. Cnidium officinale is used not only as traditionally used herbal medicines, but also as various industrial raw materials such as health functional foods, natural medicines, and living materials, but productivity is decreasing due to threats such as continuous crop damage and climate change. Therefore, this paper proposes a model that can predict the physiologically active ingredient index according to the climate change scenario of Cnidium officinale, a representative medicinal crop vulnerable to climate change. In this paper, data was first augmented using the CTGAN algorithm to solve the problem of data imbalance in the collection of environment information, physiological reactions, and physiological active ingredient information. Column Shape and Column Pair Trends were used to measure augmented data quality, and overall quality of 88% was achieved on average. In addition, five models RF, SVR, XGBoost, AdaBoost, and LightBGM were used to predict phenol and flavonoid content by dividing them into ground and underground using augmented data. As a result of model evaluation, the XGBoost model showed the best performance in predicting the physiological active ingredients of the sacrum, and it was confirmed to be about twice as accurate as the SVR model.