• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.05b
• /
• pp.527-531
• /
• 2004

본 연구에서는 미국 환경청에서 개발하여 유역 오염총량관리를 위한 수질모형으로 이용되고 있는 HSPF 모형을 선정하여 발안 $HP\#6$ 시험유역을 내상으로 모형의 적용성을 분석하였다. HSPF 모형을 이용하여 $HP\#6$ 시험유역에서 모형의 보정기간인 1996년부터 1997년까지 유출량을 모의한 겉과, RMSE는 2.1mm, RMAE는 0.4mm, $R^2$는 0.92로 모의되었으며, 모형의 검정기간인 1999년부터 2000년의 모의 길과 RMSE는 6.03mm, RMAE는 0.49mm, $R^2$는 0.84로 모의되었다. 총질소에 대한 모형의 보정결과 RMSE는 0.086kg/ha/day, RMAE는 0.534kg/ha/day, $R^2$는 0.812로 나타났으며, 모형의 검정결과 RMSE는 0.326kg/ha/day, RMAE는 0.708kg/ha/day, $R^2$는 0.427로 분석되었다. 총인에 대한 모형의 보정결과 RMSE는 0.0117 kg/ha/day, RMAE는 0.622kg/ha/day, $R^2$는 0.70으로 모의되었으며, 모형의 검정결과 RMSE는 0.063kg/ha/day, RMAE는 2.269kg/ha/day, $R^2$는 0.756으로 분석되었다.

• Journal of Korea Water Resources Association
• /
• v.37 no.8
• /
• pp.643-651
• /
• 2004

In this paper, the Hydrologic Simulation Program-Fortran (HSPF) was validated to estimate the pollutant loads from rural small watershed. The study watershed was the HP#6 subwatershed in Balhan reservoir watershed, located southwest from Suwon. The drainage area of HP#6 study watershed was 3.85$\textrm{km}^2$. Parameters of the HSPF model related to hydrology and water quality were calibrated from 1996 to 1997, and validated from 1999 to 2000 using observed hydrologic and water quality data. The average simulated runoff ratio for the calibration period was 0.579 and the measured runoff ratio was 0.583. The root mean square error (RMSE) for runoff during the calibration period was 2.1mm and correlation coefficient ($R^2$) was 0.92. Regarding the total nitrogen simulation, the RMSE was 0.086kg/ha/day and $R^2$ was 0.81 for the calibration period. In the case of total phosphorus, the RMSE was 0.012kg/ha/day and $R^2$ was 0.70 for the calibration period.

• Computers and Concrete
• /
• v.28 no.6
• /
• pp.635-642
• /
• 2021

In this paper, soft learning techniques are used to predict the ultimate torsional capacity of Reinforced Concrete beams strengthened with Fiber Reinforced Polymer. Soft computing techniques, namely Artificial Neural Network, trained by various back propagation algorithms, and Particle Swarm Optimization (PSO) algorithm, have been used to model and predict the torsional strength of Reinforced Concrete beams strengthened with Fiber Reinforced Polymer. The performance of each model has been evaluated by using statistical parameters such as coefficient of determination (R²), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The hybrid PSO NN model resulted in an R² of 0.9292 with an RMSE of 5.35 for training and an R² of 0.9328 with an RMSE of 4.57 for testing. Another model, ANN BP, produced an R² of 0.9125 with an RMSE of 6.17 for training and an R² of 0.8951 with an RMSE of 5.79 for testing. The results of the PSO NN model were in close agreement with the experimental values. Thus, the PSO NN model can be used to predict the ultimate torsional capacity of RC beams strengthened with FRP with greater acceptable accuracy.

• Steel and Composite Structures
• /
• v.49 no.2
• /
• pp.231-244
• /
• 2023

Many of the recent investigations in the field of geotechnical engineering focused on the bearing capacity theories of multilayered soil. A number of factors affect the bearing capacity of the soil, such as soil properties, applied overburden stress, soil layer thickness beneath the footing, and type of design analysis. An extensive number of finite element model (FEM) simulation was performed on a prototype slope with various abovementioned terms. Furthermore, several non-linear artificial intelligence (AI) models are developed, and the best possible neural network system is presented. The data set is from 3443 measured full-scale finite element modeling (FEM) results of a circular shallow footing analysis placed on layered cohesionless soil. The result is used for both training (75% selected randomly) and testing (25% selected randomly) the models. The results from the predicted models are evaluated and compared using different statistical indices (R² and RMSE) and the most accurate model BBO (R²=0.9481, RMSE=4.71878 for training and R²=0.94355, RMSE=5.1338 for testing) and TLBO (R²=0.948, RMSE=4.70822 for training and R²=0.94341, RMSE=5.13991 for testing) are presented as a simple, applicable formula.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.521-521
• /
• 2015

This study evaluated the gap filler radar as an implementation of the 1.5 km CAPPI data in Korea. The use of the 1.5 km CAPPI data was an inevitable choice, given the topography of the Korean Peninsula and the location of the radar. However, there still exists a significant portion of beam blockage, and thus there has been debate about the need to introduce the gap filler radar (or, the gap-filler). This study evaluated the possible benefits of introducing gap-fillers over the Korean Peninsula. As a first step, the error of the radar data was quantified by the G/R ratio and RMSE, and the radar data over the Korean Peninsula were evaluated. Then, the gap-fillers were located where the error was high, whose effect was then evaluated by the decrease in the G/R ratio and RMSE. The results show that the mean values of the G/R ratio and RMSE of the 1.5 m CAPPI data over the Korean Peninsula were estimated to be about 2.5 and 4.5 mm/hr, respectively. Even after the mean-field bias correction, the RMSE of the 1.5 km CAPPI data has not decreased much to be remained very high around 4.4 mm/hr. Unfortunately, the effect of the gap-filler on the 1.5 CAPPI data was also found very small, just 1 - 2%. However, the gap-filler could be beneficial, if the lowest elevation angle data were used instead of the 1.5 km CAPPI data. The effect of five gap-fillers could be up to 7% decrease in RMSE.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.120-120
• /
• 2021

2020년 8월 7일부터 8월 8일까지 호우는 용담댐, 섬진강댐, 합천댐 하류 유역의 막대한 침수피해를 일으켰다. 이들 다목적 댐 유입량의 신뢰도 높은 모의는 홍수기 댐 운영 및 하류하천의 홍수 해석에 필수다. 여기서는 일 유출 모의 기반으로 개발된 ONE 모형을 10분 단위, 1시간 단위로 적용한 결과를 제시하고자 한다. 보통 홍수모의는 사상별로 실시하지만, 여기서는 1월1일부터 12월 31일까지 연속으로 모의한 결과에서 해당 홍수사상 결과를 제시하였다. 3개 다목적 댐의 홍수사상은 8월6일부터 8월 10일까지 5일간으로 설정하였다. 유역면적은 용담댐, 섬진강댐, 합천댐, 각각 930km², 763km², 925km², 총강우량은 각각 490.7mm, 451.9mm, 452.4mm, 첨두유입량은 10분 단위는 각각 4,872.7m³/s, 3,533.7.0m³/s, 2,776.0m³/s, 1시간 단위는 각각 4,394.9m³/s, 3,401.8m³/s, 2,745.6m³/s, 총유입량은 각각 3억8,836만m³, 3억1,324만m³, 3억2,816만m³였다. 첨두유입량 상대오차가 0일 때의 매개변수로 모의한 결과를 제시하며, 총유입량 상대오차(Vq), R², RMSE, NSE 등으로 평가하였다. 용담댐 결과는 10분 단위 경우 최대면적강우량 7.3mm, 첨두유입량 4,872.4m³/s, 총유입량 3억 8,138만m³, Vq 1.9%, R² 0.968, RMSE 207.347, NSE 0.978였고, 1시간의 경우 최대면적강우량 29.6mm, 첨두유입량 4394.9m³/s, 총유입량 4억157만m³, Vq -8.4%, R² 0.970, RMSE 186.962, NSE 0.982였다. 섬진강댐 결과는 10분 단위 경우 최대면적강우량 9.2mm, 첨두유입량 3,533.3m³/s, 총유입량 2억7,223만m³, Vq 18.4%, R² 0.885, RMSE 808.296, NSE 0.925였고, 1시간의 경우 최대 면적강우량 37.9mm, 첨두유입량 3401.6m³/s, 총유입량 2억7,029만m³, Vq 13.7%, R² 0.907, RMSE 285.544, NSE 0.936였다. 합천댐 결과는 10분 단위 경우 최대면적강우량 5.5mm, 첨두유입량 2,776.2m³/s, 총유입량 3억3,667만m³, Vq -2.7%, R² 0.941, RMSE 191.896, NSE 0.965였고, 1시간의 경우 최대면적강우량 17.0mm, 첨두유입량 2,746.7m³/s, 총유입량 3억1,333만m³, Vq 4.5%, R² 0.965, RMSE 140.739, NSE 0.981였다. 이상 ONE 모형으로 10분, 1시간 단위의 댐 홍수 유입량 모의결과는 높은 신뢰도를 나타냈다.

• Korean Chemical Engineering Research
• /
• v.59 no.2
• /
• pp.191-199
• /
• 2021

A distillation column, which is a main facility of the chemical process, separates the desired product from a mixture by using the difference of boiling points. The distillation process requires the optimization and the prediction of operation because it consumes much energy. The target process of this study is difficult to operate efficiently because the composition of feed flow is not steady according to the supplier. To deal with this problem, we could develop a data-driven model to predict operating conditions. However, data preprocessing is essential to improve the predictive performance of the model because the raw data contains outlier and noise. In this study, after optimizing the predictive model based long-short term memory (LSTM) and Random forest (RF), we used a low-pass filter and one-class support vector machine for data preprocessing and compared predictive performance according to the method and range of the preprocessing. The performance of the predictive model and the effect of the preprocessing is compared by using R2 and RMSE. In the case of LSTM, R2 increased from 0.791 to 0.977 by 23.5%, and RMSE decreased from 0.132 to 0.029 by 78.0%. In the case of RF, R2 increased from 0.767 to 0.938 by 22.3%, and RMSE decreased from 0.140 to 0.050 by 64.3%.

• Journal of radiological science and technology
• /
• v.46 no.2
• /
• pp.131-139
• /
• 2023

High-dose I-131 used for the treatment of thyroid cancer causes localized exposure among radiology technologists handling it. There is a delay between the calibration date and when the dose of I-131 is administered to a patient. Therefore, it is necessary to directly measure the radioactivity of the administered dose using a dose calibrator. In this study, we attempted to apply machine learning modeling to measured external dose rates from shielded I-131 in order to predict their radioactivity. External dose rates were measured at 1 m, 0.3 m, and 0.1 m distances from a shielded container with the I-131, with a total of 868 sets of measurements taken. For the modeling process, we utilized the hold-out method to partition the data with a 7:3 ratio (609 for the training set:259 for the test set). For the machine learning algorithms, we chose linear regression, decision tree, random forest and XGBoost. To evaluate the models, we calculated root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) to evaluate accuracy and R² to evaluate explanatory power. Evaluation results are as follows. Linear regression (RMSE 268.15, MSE 71901.87, MAE 231.68, R² 0.92), decision tree (RMSE 108.89, MSE 11856.92, MAE 19.24, R² 0.99), random forest (RMSE 8.89, MSE 79.10, MAE 6.55, R² 0.99), XGBoost (RMSE 10.21, MSE 104.22, MAE 7.68, R² 0.99). The random forest model achieved the highest predictive ability. Improving the model's performance in the future is expected to contribute to lowering exposure among radiology technologists.

• Journal of Korea Water Resources Association
• /
• v.53 no.6
• /
• pp.395-408
• /
• 2020

This paper aims to develop and apply three different machine learning approaches (i.e., artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), and wavelet-based neural networks (WNN)) combined with an evolutionary optimization algorithm and the k-fold cross validation for multi-step (days) streamflow forecasting at the catchment located in Algeria, North Africa. The ANN and ANFIS models yielded similar performances, based on four different statistical indices (i.e., root mean squared error (RMSE), Nash-Sutcliffe efficiency (NSE), correlation coefficient (R), and peak flow criteria (PFC)) for training and testing phases. The values of RMSE and PFC for the WNN model (e.g., RMSE = 8.590 ㎥/sec, PFC = 0.252 for (t+1) day, testing phase) were lower than those of ANN (e.g., RMSE = 19.120 ㎥/sec, PFC = 0.446 for (t+1) day, testing phase) and ANFIS (e.g., RMSE = 18.520 ㎥/sec, PFC = 0.444 for (t+1) day, testing phase) models, while the values of NSE and R for WNN model were higher than those of ANNs and ANFIS models. Therefore, the new approach can be a robust tool for multi-step (days) streamflow forecasting in the Seybous River, Algeria.

• Journal of Environmental Science International
• /
• v.18 no.9
• /
• pp.1045-1055
• /
• 2009

The discharge within the basin in Jeju Island was calculated by using SWAT model, which a Semi-distributed rainfall-runoff model to the important rivers. The basin of Chunmi river of the eastern region of Jeju Island, as the result of correcting as utilizing direct runoff data of 2 surveys, appeared the similar value to the existing basin average runoff rate as 22% of average direct runoff rate for the applied period. The basin of Oaedo river of the northern region showed $R^2$ of 0.93, RMSE of 14.92 and ME of 0.70 as the result of correcting as utilizing runoff data in the occurrence of 7 rainfalls. The basin of Ongpo river of the western region showed $R^2$ of 0.86, RMSE of 0.62 and ME of 0.56 as the result of correcting as utilizing runoff data except for the period of flood in $2002{\sim}2003$. Yeonoae river of the southern region showed $R^2$ of 0.85, RMSE of 0.99 and ME of 0.83 as the result of correcting as utilizing runoff data of 2003. As the result of calculating runoff for the long term about 4 basins of Jeju Island from the above results, SWAT model wholly appears the excellent results about the long-term daily runoff simulation.