• 제목/요약/키워드: Water level prediction

검색결과 341건 처리시간 0.033초

지방하천 유역의 지속시간별 강우강도와 첨두수위 관계식 산정 (Evaluation of Relationship between Rainfall Intensity for Duration of Watersheds and Peak Water Levels of Local Rivers)

  • 최한규;공지혁;백효선
    • 산업기술연구
    • /
    • 제31권A호
    • /
    • pp.71-78
    • /
    • 2011
  • As the need for predicting the flood stage of river from torrential downpouring caused by climate change is increasingly emphasized, the study, centered on the area of Gangwon-do Inje-gun and Jeongseon-gun of local river, is to develop peak water level regression equation by rainfall. Through the correlation between rainfall and peak water level, it is confirmed that rainfall according to duration and peak water level have a high correlation coefficient. Based on this, a relational expression of rainfall and peak water level is verified and then the adequacy of the calculated expression is analyzed and the result shows that a very accurate prediction is not easy to achieve but a rough prediction of the change of water level at each point is possible.

  • PDF

LSTM 기반 배수지 수위 변화 예측모델과 적합성 평가 연구 (A Study on LSTM-based water level prediction model and suitability evaluation)

  • 이은지;박형욱;김은주
    • 스마트미디어저널
    • /
    • 제11권5호
    • /
    • pp.56-62
    • /
    • 2022
  • 배수지는 정수처리 된 물을 급수하기 위해 정수물을 모아두는 저장소로서, 물의 수요량에 따라 급수량을 조절하여 안정적으로 물을 공급하기 위해 배수지의 수위 관리는 매우 중요하다. 현재 배수지 내에 수위 계측 센서를 설치하여, 가압장의 펌프운영을 통해 배수지의 최적 수위를 관리하고 있으나, 센서의 오작동 및 통신두절 등 사고대응을 관리자 감시에 의존하고 있어, 사고의 위험을 안고 있다. 본 연구에서는 배수시설의 안정적 운영을 위하여, 배수지의 수위 변화 예측 인공지능 모델을 제안하였으며, 배수지 수위 변화 예측모델의 현장적용에 대한 안정성을 확인하기 위하여 수위 데이터의 결측 상황에 대한 시뮬레이션을 통하여, 실제 수위 변화값과 예측된 수위 변화값의 비교를 통하여 모델의 유용성을 확인하였다.

Nuclear reactor vessel water level prediction during severe accidents using deep neural networks

  • Koo, Young Do;An, Ye Ji;Kim, Chang-Hwoi;Na, Man Gyun
    • Nuclear Engineering and Technology
    • /
    • 제51권3호
    • /
    • pp.723-730
    • /
    • 2019
  • Acquiring instrumentation signals generated from nuclear power plants (NPPs) is essential to maintain nuclear reactor integrity or to mitigate an abnormal state under normal operating conditions or severe accident circumstances. However, various safety-critical instrumentation signals from NPPs cannot be accurately measured on account of instrument degradation or failure under severe accident circumstances. Reactor vessel (RV) water level, which is an accident monitoring variable directly related to reactor cooling and prevention of core exposure, was predicted by applying a few signals to deep neural networks (DNNs) during severe accidents in NPPs. Signal data were obtained by simulating the postulated loss-of-coolant accidents at hot- and cold-legs, and steam generator tube rupture using modular accident analysis program code as actual NPP accidents rarely happen. To optimize the DNN model for RV water level prediction, a genetic algorithm was used to select the numbers of hidden layers and nodes. The proposed DNN model had a small root mean square error for RV water level prediction, and performed better than the cascaded fuzzy neural network model of the previous study. Consequently, the DNN model is considered to perform well enough to provide supporting information on the RV water level to operators.

딥러닝 기반 LSTM 모형을 이용한 감조하천 수위 예측 (Prediction of water level in a tidal river using a deep-learning based LSTM model)

  • 정성호;조효섭;김정엽;이기하
    • 한국수자원학회논문집
    • /
    • 제51권12호
    • /
    • pp.1207-1216
    • /
    • 2018
  • 본 연구는 물리적 수리 수문모형의 적용이 제한적인 감조하천에서의 수위예측을 목적으로 하고 있으며, 이를 위해 한강 잠수교를 대상으로 딥러닝 오픈소스 소프트웨어 라이브러리인 TensorFlow를 활용하여 LSTM 모형을 구성하고 2011년부터 2017년까지의 10분 단위의 잠수교 수위, 팔당댐 방류량과 한강하구 강화대교지점의 예측조위 자료를 이용하여 모형학습(2011~2016) 및 수위예측(2017)을 수행하였다. 모형 매개변수는 민감도 분석을 통해 은닉층의 개수는 6개, 학습속도는 0.01, 학습횟수는 3000번로 결정하였으며, 모형 학습 시 학습정보의 시간적 양을 결정하는 중요한 매개변수인 시퀀스길이는 1시간, 3시간, 6시간으로 변화시키며 모의하였다. 최종적으로 선행시간에 따른 모의 예측능력을 평가하기 위해 LSTM 모형의 예측 선행시간을 6개(1 ~ 24시간)로 구분하여 실측수위와 예측수위와의 비교 분석을 수행한 결과, LSTM 모형의 최적의 성능을 내는 결과는 시퀀스길이를 1시간으로 하였을 때로 분석되었으며, 특히 선행시간 1시간에 대한 예측정확도는 RMSE는 0.065 m, NSE는 0.99로 실측수위에 매우 근접한 예측 결과를 나타내었다. 또한 시퀀스길이에 상관없이 선행시간이 길어질수록 모형의 예측 정확도는 2017년 전기간에 걸쳐 평균적으로 RMSE 0.08 m에서 0.28 m로 오차가 증가하였으며, NSE는 0.99에서 0.74로 감소하였다.

상류 수위관측소 자료를 활용한 하류 지점 수위 예측 (Prediction of Water Level at Downstream Site by Using Water Level Data at Upstream Gaging Station)

  • 홍원표;송창근
    • 한국안전학회지
    • /
    • 제35권2호
    • /
    • pp.28-33
    • /
    • 2020
  • Recently, the overseas construction market has been actively promoted for about 10 years, and overseas dam construction has been continuously performed. For the economic and safe construction of the dam, it is important to prepare the main dam construction plan considering the design frequency of the diversion tunnel and the cofferdam. In this respect, the prediction of river level during the rainy season is significant. Since most of the overseas dam construction sites are located in areas with poor infrastructure, the most efficient and economic method to predict the water level in dam construction is to use the upstream water level. In this study, a linear regression model, which is one of the simplest statistical methods, was proposed and examined to predict the downstream level from the upstream level. The Pyeongchang River basin, which has the characteristics of the upper stream (mountain stream), was selected as the target site and the observed water level in Pyeongchang and Panwoon gaging station were used. A regression equation was developed using the water level data set from August 22th to 27th, 2017, and its applicability was tested using the water level data set from August 28th to September 1st, 2018. The dependent variable was selected as the "level difference between two stations," and the independent variable was selected as "the level of water level in Pyeongchang station two hours ago" and the "water level change rate in Pyeongchang station (m/hr)". In addition, the accuracy of the developed equation was checked by using the regression statistics of Root Mean Square Error (RMSE), Adjusted Coefficient of Determination (ACD), and Nach Sutcliffe efficiency Coefficient (NSEC). As a result, the statistical value of the linear regression model was very high, so the downstream water level prediction using the upstream water level was examined in a highly reliable way. In addition, the results of the application of the water level change rate (m/hr) to the regression equation show that although the increase of the statistical value is not large, it is effective to reduce the water level error in the rapid level rise section. Accordingly, this is a significant advantage in estimating the evacuation water level during main dam construction to secure safety in construction site.

DNN 및 LSTM 기반 딥러닝 모형을 활용한 태화강 유역의 수위 예측 (Water level prediction in Taehwa River basin using deep learning model based on DNN and LSTM)

  • 이명진;김종성;유영훈;김형수;김삼은;김수전
    • 한국수자원학회논문집
    • /
    • 제54권spc1호
    • /
    • pp.1061-1069
    • /
    • 2021
  • 최근 이상 기후로 인해 극한 호우 및 국지성 호우의 규모 및 빈도가 증가하여 하천 주변의 홍수 피해가 증가하고 있다. 이에 따라 하천 또는 유역 내 수문학적 시스템의 비선형성이 증가하고 있으며, 기존의 물리적 기반의 수문 모형을 활용하여 홍수위를 예측하기에는 선행시간이 부족한 한계점이 존재한다. 본 연구에서는 Deep Neural Network (DNN) 및 Long Short-Term Memory (LSTM)기반의 딥러닝 기법을 적용하여 울산시(태화교) 지점의 수위를 0, 1, 2, 3, 6, 12시간에 대해 선행 예측을 수행하였고 예측 정확도를 비교 분석하였다. 그 결과 sliding window 개념을 적용한 DNN 모형이 선행시간 12시간까지 상관계수 0.97, RMSE 0.82 m로 가장 높은 정확도를 보이고 있음을 확인하였다. 향후 DNN 모형을 활용하여 딥러닝 기반의 수위 예측을 수행한다면 기존의 물리적 모형을 통한 홍수위 예측보다 향상된 예측 정확도와 충분한 선행시간을 확보할 수 있을 것으로 판단된다.

Water Level Prediction on the Golok River Utilizing Machine Learning Technique to Evaluate Flood Situations

  • Pheeranat Dornpunya;Watanasak Supaking;Hanisah Musor;Oom Thaisawasdi;Wasukree Sae-tia;Theethut Khwankeerati;Watcharaporn Soyjumpa
    • 한국수자원학회:학술대회논문집
    • /
    • 한국수자원학회 2023년도 학술발표회
    • /
    • pp.31-31
    • /
    • 2023
  • During December 2022, the northeast monsoon, which dominates the south and the Gulf of Thailand, had significant rainfall that impacted the lower southern region, causing flash floods, landslides, blustery winds, and the river exceeding its bank. The Golok River, located in Narathiwat, divides the border between Thailand and Malaysia was also affected by rainfall. In flood management, instruments for measuring precipitation and water level have become important for assessing and forecasting the trend of situations and areas of risk. However, such regions are international borders, so the installed measuring telemetry system cannot measure the rainfall and water level of the entire area. This study aims to predict 72 hours of water level and evaluate the situation as information to support the government in making water management decisions, publicizing them to relevant agencies, and warning citizens during crisis events. This research is applied to machine learning (ML) for water level prediction of the Golok River, Lan Tu Bridge area, Sungai Golok Subdistrict, Su-ngai Golok District, Narathiwat Province, which is one of the major monitored rivers. The eXtreme Gradient Boosting (XGBoost) algorithm, a tree-based ensemble machine learning algorithm, was exploited to predict hourly water levels through the R programming language. Model training and testing were carried out utilizing observed hourly rainfall from the STH010 station and hourly water level data from the X.119A station between 2020 and 2022 as main prediction inputs. Furthermore, this model applies hourly spatial rainfall forecasting data from Weather Research and Forecasting and Regional Ocean Model System models (WRF-ROMs) provided by Hydro-Informatics Institute (HII) as input, allowing the model to predict the hourly water level in the Golok River. The evaluation of the predicted performances using the statistical performance metrics, delivering an R-square of 0.96 can validate the results as robust forecasting outcomes. The result shows that the predicted water level at the X.119A telemetry station (Golok River) is in a steady decline, which relates to the input data of predicted 72-hour rainfall from WRF-ROMs having decreased. In short, the relationship between input and result can be used to evaluate flood situations. Here, the data is contributed to the Operational support to the Special Water Resources Management Operation Center in Southern Thailand for flood preparedness and response to make intelligent decisions on water management during crisis occurrences, as well as to be prepared and prevent loss and harm to citizens.

  • PDF

하천 홍수 예측을 위한 CNN 기반의 수위 예측 모델 구현 (Implementation of CNN-based water level prediction model for river flood prediction)

  • 조민우;김수진;정회경
    • 한국정보통신학회논문지
    • /
    • 제25권11호
    • /
    • pp.1471-1476
    • /
    • 2021
  • 수해는 홍수나 해일을 유발하여 막대한 인명과 재산의 피해를 초래할 수 있다. 이에 대해 홍수 예측을 통한 빠른 대피 결정으로 피해를 줄일 수 있으며, 해당 분야에서는 시계열 데이터를 활용하여 홍수를 예측하려는 연구들도 많이 진행되고 있다. 본 논문에서는 CNN 기반의 시계열 예측 모델을 제안한다. 하천의 수위와 강수량을 사용하여 CNN 기반의 수위 예측 모델을 구현하였고, 시계열 예측에 많이 사용되는 LSTM, GRU 모델과 비교하여 성능을 확인하였다. 또한 입력 데이터의 크기에 따른 성능 차이를 확인하여 보완해야 할 점을 찾을 수 있었고, LSTM과 GRU보다 더 좋은 성능을 낼 수 있다는 것을 확인하였다. 이를 통해 홍수 예측을 위한 초기 연구로서 활용할 수 있을 것으로 사료된다.

상류지점 수위표 수위변동에 따른 하류지점 수위표 수위변동예측 (The estimation of water level fluctuation in the down stream water mark by water level fluctuation in the upper region water mark)

  • 최한규;임윤수;백효선
    • 산업기술연구
    • /
    • 제30권B호
    • /
    • pp.83-89
    • /
    • 2010
  • Generally, the accuracy of the prediction of flood elevation is difficult to identify due to the sedimentation on a river bed, earth and sand being moved by flow, and localized torrential downpours caused by climate change. It is also because of natural and artificial influences on rivers. To predict river floodings successfully, more precise and reliable flood elevation prediction system is needed, in which the concentration time of downstream is numerically interpreted through analyzing and utilizing the watermark of the upper region. Therefore, this research analyzed the prediction methods of the changes in water levels, which use the watermarks of the upper region. The watermarks which impacts the spot being predicted of flood was selected through floodgate analysis and correlation analysis. With the selected watermarks, a statistically reliable regression equation was yielded.

  • PDF

Prediction of the DO concentration using the machine learning algorithm: case study in Oncheoncheon, Republic of Korea

  • Lim, Heesung;An, Hyunuk;Choi, Eunhyuk;Kim, Yeonsu
    • 농업과학연구
    • /
    • 제47권4호
    • /
    • pp.1029-1037
    • /
    • 2020
  • The machine learning algorithm has been widely used in water-related fields such as water resources, water management, hydrology, atmospheric science, water quality, water level prediction, weather forecasting, water discharge prediction, water quality forecasting, etc. However, water quality prediction studies based on the machine learning algorithm are limited compared to other water-related applications because of the limited water quality data. Most of the previous water quality prediction studies have predicted monthly water quality, which is useful information but not enough from a practical aspect. In this study, we predicted the dissolved oxygen (DO) using recurrent neural network with long short-term memory model recurrent neural network long-short term memory (RNN-LSTM) algorithms with hourly- and daily-datasets. Bugok Bridge in Oncheoncheon, located in Busan, where the data was collected in real time, was selected as the target for the DO prediction. The 10-month (temperature, wind speed, and relative humidity) data were used as time prediction inputs, and the 5-year (temperature, wind speed, relative humidity, and rainfall) data were used as the daily forecast inputs. Missing data were filled by linear interpolation. The prediction model was coded based on TensorFlow, an open-source library developed by Google. The performance of the RNN-LSTM algorithm for the hourly- or daily-based water quality prediction was tested and analyzed. Research results showed that the hourly data for the water quality is useful for machine learning, and the RNN-LSTM algorithm has potential to be used for hourly- or daily-based water quality forecasting.