• Journal of The Korean Society of Agricultural Engineers
• /
• v.55 no.6
• /
• pp.1-9
• /
• 2013

미래 기후 정보를 이용한 수문 환경의 단기 미래 예측은 안정적 수자원 공급을 위한 필수적 과제이다. 미국 플로리다 주 중서부 템파지역에서는 주요 수자원 중 하나인 지하수의 효과적 활용을 위해 지하수위 인공신경망 모델 (GWANN)을 개발하여 피압 대수층과 비피압 대수층에 대한 주 단위 평균 지하수위를 월별로 예측하고 그 결과를 수자원 공급 의사 결정에 반영하고 있다. 본 논문은 템파지역에 대한 GWANN 모델을 이용한 지하수위 예측 시스템을 소개하고 모델의 기후 입력 자료의 민감도를 분석함으로써 양질의 기후 정보에 대한 현 시스템의 활용성을 검토하였다. 2006년과 2007년에 대한 연구 결과, 관측 자료를 최적 예측 시나리오 (the best forecast)로 가정하여 적용한 결과는 지하수위 관측 지점에 따라 큰 차이를 보였지만 일반적으로 현 시스템 (현 시점의 실시간 주 단위 평균 강우량을 향후 4주간 동일하게 적용함) 에 비해 예측 성능이 개선되는 것으로 나타났다. 더불어 강우 관측 자료의 백분위 (percentile forecast; 20분위, 50분위, 80분위)를 강우 예측 자료로 활용한 경우에도 현 시스템과 비교하여 일부 나은 결과를 보여주었다. 그러나 지하수위 예측 모델을 활용하지 않고 현 시점의 지하 수위가 지속된다고 가정하는 경우 (na$\ddot{i}$ve model) 향후 2주간의 예측 결과가 best forecast 경우에 비해 높은 정확도를 보이는 등, GWANN 모델의 단기 예측에 대한 양질의 강우 예측 정보의 활용성은 낮으며, 향후 3주 이상에 대한 예측 성능에 있어 best forecast결과가 na$\ddot{i}$ve model 결과에 비해 높은 정확도를 보이기 시작하는 것으로 나타났다. 또한 GWANN 모델의 예측 성능은 적용 기간과 지역 및 지하대수층의 특성에 따라 큰 다양성을 가지는 단점을 보여 강우 예측 자료 활용에 앞서 모델 개선의 필요성이 있다고 판단된다. 본 연구는 단기수자원 공급 계획 수립을 위하여 사용되는 지역 모델링 시스템에 대한 기후 예측정보의 활용성 평가를 위한 방법론으로 고려될 수 있을 것으로 기대된다.

• Journal of Korea Water Resources Association
• /
• v.56 no.11
• /
• pp.801-813
• /
• 2023

Recently, as studies about Artificial Neural Network (ANN) are actively progressing, studies for predicting water quality of rivers using ANN are being conducted. However, it is difficult to analyze the operation process inside ANN, because ANN is form of Black-box. Although eXplainable Artificial Intelligence (XAI) is used to analyze the computational process of ANN, research using XAI technology in the field of water resources is insufficient. This study analyzed Multi Layer Perceptron (MLP) to predict Water Temperature (WT), Dissolved Oxygen (DO), hydrogen ion concentration (pH) and Chlorophyll-a (Chl-a) at the Dasan water quality observatory in the Nakdong river using Layer-wise Relevance Propagation (LRP) among XAI technologies. The MLP that learned water quality was analyzed using LRP to select the optimal input data to predict water quality, and the prediction results of the MLP learned using the optimal input data were analyzed. As a result of selecting the optimal input data using LRP, the prediction accuracy of MLP, which learned the input data except daily precipitation in the surrounding area, was the highest. Looking at the analysis of MLP's DO prediction results, it was analyzed that the pH and DO a had large influence at the highest point, and the effect of WT was large at the lowest point.

• Journal of Korea Water Resources Association
• /
• v.32 no.1
• /
• pp.3-13
• /
• 1999

In this study, an alternative spatial analysis method against conventional methods such as Thiessen method, Inverse Distance method, and Kriging method, named Spatial-Analysis Neural-Network (SANN) is presented. It is based on neural network modeling and provides a nonparametric mean estimator and also estimators of high order statistics such as standard deviation and skewness. In addition, it provides a decision-making tool including an estimator of posterior probability that a spatial variable at a given point will belong to various classes representing the severity of the problem of interest and a Bayesian classifier to define the boundaries of subregions belonging to the classes. In this paper, the SANN is implemented to be used for analyzing a mean annual precipitation filed and classifying the field into dry, normal, and wet subregions. For an example, the whole area of South Korea with 39 precipitation sites is applied. Then, several useful results related with the spatial variability of mean annual precipitation on South Korea were obtained such as interpolated field, standard deviation field, and probability maps. In addition, the whole South Korea was classified with dry, normal, and wet regions.

• Journal of Korea Water Resources Association
• /
• v.44 no.7
• /
• pp.537-551
• /
• 2011

Based on optimal input data combination selected in the earlier study, Neuro-Fuzzy flood forecasting model linked Takagi-Sugeno fuzzy inference theory with neural network in Wangsukcheon and Gabcheon is established. The established model was applied to Wangsukcheon and Gabcheon and water levels for lead time of 0.5 hr, 1 hr, 1.5 hr, 2.0 hr, 2.5 hr, 3.0 hr are forecasted. For the verification of the model, the comparisons between forecasting floods and observation data are presented. The forecasted results have shown good agreements with observed data. Additionally to evaluate quantitatively for applicability of the model, various statistical errors such as Root Mean Square Error are calculated. As a result of the flood forecasting can be simulated successfully without large errors in all statistical error. This study can greatly contribute to the construction of a high accuracy flood information system that secure lead time in medium and small streams.

• Journal of the Korean GEO-environmental Society
• /
• v.24 no.2
• /
• pp.31-40
• /
• 2023

We installed temporary strong motion seismometers at the ground surface, 1 m, 2 m, and 9 m at an existing seismic station that houses permanent seismometers installed at 20 m and 100 m, to investigate the influence of installation depth on the recorded ambient and anthropogenic noise level and the characteristics of earthquake signals. Analysis of the ambient noise shows that anthropogenic noise dominates where vibration period T < 1 s at the studied site, whereas wind speed appears to be strongly correlated with the noise level at T > 1 s. Frequency-wavenumber analysis of 2D seismometer array suggests that ambient noise in short periods are predominantly body waves, rather than surface waves. The level of ambient noise was low at 9 m and 20 m, but strong amplification of noise level at T < 0.1 s was observed at the shallow seismometers. Both the active-source test result and the recorded earthquake data demonstrated that the signal level is decreased with the increase of depth. Our result also shows that recorded motions at the ground and 1 m are strongly amplified at 20 Hz (T = 0.05 s), likely due to the resonance of the 3 m thick soil layer. This study demonstrates that analysis of ambient and active-source vibration may help find optimal installation depth of strong motion seismometers. We expect that further research considering various noise environments and geological conditions will be helpful in establishing a guideline for optimal installation of strong motion seismometers.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.715-727
• /
• 2023

To provide detailed and appropriate meteorological information in mountainous areas, the Korea Forest Service has established an Automatic Mountain Meteorology Observation Station (AMOS) network in major mountainous regions since 2012, and 464 stations are currently operated. In this study, we proposed an optimal kriging technique with lapse rate correction to produce gridded temperature data suitable for Korean forests using AMOS point observations. First, the outliers of the AMOS temperature data were removed through statistical processing. Then, an optimized theoretical variogram, which best approximates the empirical variogram, was derived to perform the optimal kriging with lapse rate correction. A 500-meter resolution Kriging map for temperature was created to reflect the elevation variations in Korean mountainous terrain. A blind evaluation of the method using a spatially unbiased validation sample showed a correlation coefficient of 0.899 to 0.953 and an error of 0.933 to 1.230℃, indicating a slight accuracy improvement compared to regular kriging without lapse rate correction. However, the critical advantage of the proposed method is that it can appropriately represent the complex terrain of Korean forests, such as local variations in mountainous areas and coastal forests in Gangwon province and topographical differences in Jirisan and Naejangsan and their surrounding forests.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.2B
• /
• pp.159-167
• /
• 2010

The purpose of this study is to get the adjusted radar rainfalls by ANN(Artificial Neural Network) method. In the case of radar rainfall, it has an advantage of spatial distribution characteristics of rainfall while point rainfall has an advantage at the point. Therefore we adjusted the radar rainfall by ANN method considering the advantages of two rainfalls of radar and point. This study constructed two ANN models of Model I and Model II for radar rainfall adjustment. We collected the three rainfall events and adjusted the radar rainfall for Anseong-cheon basin. The two events were inputted into the Modeland Model to derive the optimum parameters and the rest event was used for validation. The adjusted radar rainfalls by ANN method and the raw radar rainfall were used as the input data of ModClark model which is a semi-distributed model to simulate the runoff. As the results of the simulation, the runoff by raw radar rainfall were overestimated but the peak time and peak runoff from the adjusted rainfall by ANN were well fitted to the observed hydrograph.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.301-304
• /
• 2012

홍수예경보는 강우로 인하여 발생되는 홍수의 규모와 시간을 가능한 한 정확하고 빨리 예측하여 홍수에 대비할 수 있도록 유관기관 및 지역주민에게 사전에 홍수에 관한 정보 즉 예측되는 수위와 시간을 제공함으로써 홍수로부터의 피해를 최소화하는 것이다. 이와 같은 목적을 성공적으로 완수하기 위해서는 홍수시 급변하는 하천유량에 영향을 미치는 모든 수문학적 기상학적 자료를 신속 정확하게 수집할 수 있는 관측 시스템의 구축 뿐 아니라 이들 수집된 자료를 이용하여 실시간 홍수추적을 할 수 있는 효율적인 유출량 계산모형이 조화를 이룰 때 가능하다. 이에 본 연구에서는 중 소하천에서 홍수예경보를 위한 지능형 U-River 시스템의 실시간 모니터링 기술을 조사하고 하천수위를 이용한 예측시스템에 대해 연구하였다. 기존의 홍수예경보의 문제점을 해결하기 위해 간단한 입력자료만으로 홍수예측이 가능한 인공지능 기반의 신경망 모형을 이용 하였으며, 예측 모형의 효율성과 적용성을 높이기 위해 유사한 수문 사상을 가지는 상 하류간 입력 자료를 동시에 사용하였다. 또한 하천수위를 이용한 모델의 수행은 각 지점별 훈련성과를 토대로 최적의 은닉층 노드수를 선발하여 실시간 수위예측에 활용하였으며 수치적 기준을 적용하여 실측 수위와 모형에 의해 예측된 수위를 이용하여 평가하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.3
• /
• pp.224-232
• /
• 2003

In this paper, efficient deployment method of sensors and target positioning performance with respect to measurement error are dealt with. Active sonar can be categorized into Monostatic, Bistatic, Multistatic sonar, and characteristics of respective sonar are different. Assuming that each sensor can receive range and angular information, we compare the performance of Monostatic, Bistatic, and Multistatic systems. And we suggest Weighted least square (WLS) which gives the weight to former case, LS. In particular. adopting suggested method we investigate the target positioning performance according to number of sensor, distance from transmitter to receiver, and propose efficient arrangement rule for Multistatic sonar configurations. According to the experimental results, RMSE of Multistatic sonar is found to be superior to Monostatic and Bistatic by 35.98%. 37.45% respectively, and WLS is superior to LS approximately by 7.4% in average. Furthermore, as the difference of respective sensor's variance is large, it is observed that the improvement ratio of target positioning performance is increased.

• Spatial Information Research
• /
• v.12 no.1
• /
• pp.101-110
• /
• 2004

Research that establish new cadastral survey model that use GPS to introduce GPS observation technique in cadastral survey and research that develop connection technologies are now abuzz. The purpose of this research is to keep in step in such trend and grasp present condition and performance of surveying connection to common use GPS data processing software, and analyze data processing algorithm, and develop suitable GPS data processing software in our real condition regarding GPS data processing and result of control point calculation. This research studies analysis common use software and error occurrence by data processing method that college and company have. Also, It analyzes algorithm that is applied to existing GPS data processing software. After that we study algorithm that is most suitable with cadastral survey and then develop cadastral survey calculation software for new cadastral control points.