• Water for future
• /
• v.27 no.3
• /
• pp.45-54
• /
• 1994

Basic theory of fractal dimension is introduced and performed for the generated time series using the water balance model. The water balance equation over a large area is analyzed at seasonal time scales. In the generation and modification of mesoscale circulation local recycling of precipitation and dynamic effects of soil moisture are explicitly included. Time delay is incorporated in the analysis. Depending on the parameter values, the system showed different senarios in the evolution such as fixed point, limit cycle, and chaotic types of behavior. The stochastic behavior of the generated time series is due to deterministic chaos which arises from a nonlinear dynamic system with a limited number of equations whose trajectories are highly sensitive to initial conditions. The presence of noise arose from the characterization of the incoming precipitation, destroys the organized structure of the attractor. The existence of the attractor although noise is present is very important to the short-term prediction of the evolution. The implications of this nonlinear dynamics are important for the interpretation and modeling of hydrologic records and phenomena.

• Journal of the Korea Convergence Society
• /
• v.11 no.5
• /
• pp.153-158
• /
• 2020

The present study identify the predictive power of confrontational naming and generative naming as screening tests for normal and early cognitive impairment. The subjects were analyzed for 203 healthy elderly, 106 mild cognitive impairment (MCI), 31 mild dementia. The confrontational naming was measured by the short-term Korean Boston Name Waiting Test, and the generative naming was measured by the Control Associative Word Test. As a result of polynomial logistic regression, both confrontational naming and generative naming had a significant effect on discriminating cognitive impairment (MCI, mild dementia) in general elderly (p<0.05). On the other hand, when distinguishing mild dementia from mild cognitive impairment, the generative naming-phonetic test had no significant odds ratio. The results of this study suggest that when discriminating mild dementia in mild cognitive impairment group, it is not meaningful to look only at the total score of generative naming test.

• The Journal of Engineering Geology
• /
• v.18 no.2
• /
• pp.207-214
• /
• 2008

We conducted uniaxial consolidation tests in mudstone samples with different clay content, in order to investigate time-dependent deformation and its characteristics. A significant amount of time-dependent strain was observed at a constant stress level immediately after a jump of stress was applied. For a given mudstone, the amount of time-dependent deformation was nearly proportional to the increment of stress, suggesting a linear viscous rheology. The amount of time-dependent strain increases with clay content, implying that clay plays an important role in creep of the unconsolidated mudstone. A power-law model was suitably applied to our results, suggesting that a short-term prediction of time-dependent deformation of the mudstone is tentatively feasible.

• Journal of the Society of Naval Architects of Korea
• /
• v.31 no.1
• /
• pp.94-101
• /
• 1994

This paper describes a short-term prediction model for the movement of an oil slick in shallow waters. Under the assumption that the initial movement of the oil slick is governed by spreading and advection, the model has been developed and applied to Kyungki-Bay near Incheon Harbor. The initial spreading is estimated by using an empirical formula. The depth-averaged momentum equations are solved numerically for the volume transport velocities, in which the $M_2$ tide is the main driving source. A staggered grid system is adopted fur spatial discretization and the half-time method is implemented for time marching. The numerical result is visualized with the help of animation and thus the contaminated area is displayed on a monitor in time sequence. The input data are the time, the location and the volume of spill accident as well as environmental data such as md and $M_2$ tide.

• Journal of the Korean Solar Energy Society
• /
• v.39 no.3
• /
• pp.59-66
• /
• 2019

New and renewable energy forecasts are key technology to reduce the annual operating cost of new and renewable facilities, and accuracy of forecasts is paramount. In this study, we intend to build a model for the prediction of short-term solar power generation for 1 hour to 3 hours. To this end, this study applied two time series technique, ARIMA model without considering seasonality and SARIMA model with considering seasonality, comparing which technique has better predictive accuracy. Comparing predicted errors by MAE measures of solar power generation for 1 hour to 3 hours at four locations, the solar power forecast model using ARIMA was better in terms of predictive accuracy than the solar power forecast model using SARIMA. On the other hand, a comparison of predicted error by RMSE measures resulted in a solar power forecast model using SARIMA being better in terms of predictive accuracy than a solar power forecast model using ARIMA.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.852-857
• /
• 2019

In order to manage the demand resources of project participants and to provide appropriate strategies in the virtual power plant's power trading platform for consumers or operators who want to participate in the distributed resource collective trading market, it is very important to forecast the next day's demand of individual participants and the overall system's electricity demand. This paper developed a power demand forecasting model for the next day. For the model, we used LSTM algorithm of deep learning technique in consideration of time series characteristics of power demand forecasting data, and new scheme is applied by applying one-hot encoding method to input/output values such as power demand. In the performance evaluation for comparing the general DNN with our LSTM forecasting model, both model showed 4.50 and 1.89 of root mean square error, respectively, and our LSTM model showed high prediction accuracy.

• Atmosphere
• /
• v.31 no.5
• /
• pp.489-510
• /
• 2021

In this paper, we propose an algorithm for detecting convective initiation (CI) using GEO-KOMPSAT-2A/advanced meteorological imager data. The algorithm identifies clouds that are likely to grow into convective clouds with radar reflectivity greater than 35 dBZ within the next two hours. This algorithm is developed using statistical and qualitative analysis of cloud characteristics, such as atmospheric instability, cloud top height, and phase, for convective clouds that occurred on the Korean Peninsula from June to September 2019. The CI algorithm consists of four steps: 1) convective cloud mask, 2) cloud object clustering and tracking, 3) interest field tests, and 4) post-processing tests to remove non-convective objects. Validation, performed using 14 CI events that occurred in the summer of 2020 in Korean Peninsula, shows a total probability of detection of 0.89, false-alarm ratio of 0.46, and mean lead-time of 39 minutes. This algorithm can be useful warnings of rapidly developing convective clouds in future by providing information about CI that is otherwise difficult to predict from radar or a numerical prediction model. This CI information will be provided in short-term forecasts to help predict severe weather events such as localized torrential rainfall and hail.

• Geomechanics and Engineering
• /
• v.31 no.6
• /
• pp.545-556
• /
• 2022

Evaluation and optimization of tunnel wall convergence (TWC) plays a vital role in preventing potential problems during tunnel construction and utilization stage. When convergence occurs at a high rate, it can lead to significant problems such as reducing the advance rate and safety, which in turn increases operating costs. In order to design an effective solution, it is important to accurately predict the degree of TWC; this can reduce the level of concern and have a positive effect on the design. With the development of soft computing methods, the use of deep learning algorithms and neural networks in tunnel construction has expanded in recent years. The current study aims to employ the long-short-term memory (LSTM) deep neural network predictor model to predict the TWC, based on 550 data points of observed parameters developed by collecting required data from different tunnelling projects. Among the data collected during the pre-construction and construction phases of the project, 80% is randomly used to train the model and the rest is used to test the model. Several loss functions including root mean square error (RMSE) and coefficient of determination (R²) were used to assess the performance and precision of the applied method. The results of the proposed models indicate an acceptable and reliable accuracy. In fact, the results show that the predicted values are in good agreement with the observed actual data. The proposed model can be considered for use in similar ground and tunneling conditions. It is important to note that this work has the potential to reduce the tunneling uncertainties significantly and make deep learning a valuable tool for planning tunnels.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.520-520
• /
• 2023

제주도 동부 중산간 지역은 화산암으로 구성된 지하지질로 인해 지하수위의 변동폭이 크고 변동양상이 복잡하여 인공신경망(Artificial Neural Network, ANN) 모델 등을 활용한 지하수위의 예측이 어렵다. ANN에 적용되는 활성화함수에 따라 지하수의 예측성능은 달라질 수 있으므로 활성화함수의 비교분석 후 적절한 활성화함수의 사용이 반드시 필요하다. 본 연구에서는 5개 활성화함수(sigmoid, hyperbolic tangent(tanh), Rectified Linear Unit(ReLU), Leaky Rectified Linear Unit(Leaky ReLU), Exponential Linear Unit(ELU))를 제주도 동부 중산간지역에 위치한 2개 지하수 관정에 대해 비교분석하여 최적 활성화함수 도출을 목표로 한다. 또한 최적 활성화함수를 활용한 ANN의 적용성을 평가하기 위해 최근 널리 사용되고 있는 순환신경망 모델인 Long Short-Term Memory(LSTM) 모델과 비교분석 하였다. 그 결과, 2개 관정 중 지하수위 변동폭이 상대적으로 큰 관정은 ELU 함수, 상대적으로 작은 관정은 Leaky ReLU 함수가 지하수위 예측에 적절하였다. 예측성능이 가장 낮은 활성화함수는 sigmoid 함수로 나타나 첨두 및 최저 지하수위 예측 시 사용을 지양해야 할 것으로 판단된다. 도출된 최적 활성화함수를 사용한 ANN-ELU 모델 및 ANN-Leaky ReLU 모델을 LSTM 모델과 비교분석한 결과 대등한 지하수위 예측성능을 나타내었다. 이것은 feed-forward 방식인 ANN 모델을 사용하더라도 적절한 활성화함수를 사용하면 최신 순환신경망과 대등한 결과를 도출하여 활용 가능성이 충분히 있다는 것을 의미한다. 마지막으로 LSTM 모델은 가장 적절한 예측성능을 나타내어 다양한 인공지능 모델의 예측성능 비교를 위한 기준이 되는 참고모델로 활용 가능하다. 본 연구에서 제시한 방법은 지하수위 예측과 더불어 하천수위 예측 등 다양한 시계열예측 및 분석연구에 유용하게 사용될 수 있다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.362-362
• /
• 2023

한정된 수자원의 이용 및 관리로 매년 물 부족과 물 배분 의사결정 문제가 발생하고 있다. 50년간(1965~2014년) 수자원의 총량은 약 1.2배 증가한 반면 인구수 약 1.8배, 생·공·농업용수의 수요는 약 5배가 증가(국회입법조사처, 2018) 했을 뿐 아니라, 기후변화의 영향으로 인한 강수량의 변화와 지역별 편차가 커져 지속가능한 물관리 필요성이 증대되고 있다. 따라서 효율적인 물관리를 위해서는 관리부처가 분절되어 있는 물순환 계통의 데이터를 통합하는 것이 우선시되어야 하고 이를 통해 물순환 모니터링/평가/예측 기술을 개발할 수 있다. 본 연구에서는 생활용수 물순환 계통 통합 DB를 정의 및 구축하였다. 도시의 관점에서 물순환 시스템을 순차적으로 물 유입(수원~취수장)/전달(정수장~급수지역)/유출(하(폐)수처리장~방류구)의 개념으로 설정하고 DB정의서를 마련하였다. 연구대상지는 가뭄이 장기화가 되고 있는 전라남도중 물순환 계통이 비교적 단순한 네트워크로 형성되어 있는 함평군 도시지역으로 선정하였다. 연구 기간은 총 5년(2017년 1월 1일~2021년 12월 31일)이고 일 단위 실계측자료 위주의 원자료를 구축하였다. 이를 이상치 탐지, 제거, 대체의 과정을 거쳐 품질 보정하고 정제된 시계열 자료에 대한 특성 분석을 하였다. 그 결과, 물순환 계통 내 주요 지점 간의 상관관계 및 지연시간을 통한 물흐름의 시계열적 특성을 파악할 수 있었으며 모형의 적합도를 판단하는 데 활용되는 통계량과 유의미하지 않은 잔차의 자기상관성을 볼 때 물 유입-전달-유출의 단기 예측을 위한 ARIMA(Auto-regressive Integrated Moving Average) 모형의 구축도 가능할 것으로 판단되었다. 다만 여름철 발생하는 방류량의 첨두값을 설명하기 위해서는 강우에 의한 불명수 발생으로 증가하는 방류량을 묘사할 수있어야 하므로 향후에는 물순환계통 외 해당 지역의 불명수(강우 효과)도 하수 방류량의 주요 입력 요인으로 추가 검토할 필요가 있다.