• Journal of Environmental Science International
• /
• v.26 no.10
• /
• pp.1167-1180
• /
• 2017

Numerical Weather Prediction (NWP) models such as the Weather Research and Forecasting (WRF) model are essential for forecasting one-day-ahead solar irradiance. In order to evaluate the performance of the WRF in forecasting solar irradiance over the Korean Peninsula, we compared WRF prediction data from 2008 to 2010 corresponding to weather observation data (OBS) from the Korean Meteorological Administration (KMA). The WRF model showed poor performance at polluted regions such as Seoul and Suwon where the relative Root Mean Square Error (rRMSE) is over 30%. Predictions by the WRF model alone had a large amount of potential error because of the lack of actual aerosol radiative feedbacks. For the purpose of reducing this error induced by atmospheric particles, i.e., aerosols, the WRF model was coupled with the Community Multiscale Air Quality (CMAQ) model. The coupled system makes it possible to estimate the radiative feedbacks of aerosols on the solar irradiance. As a result, the solar irradiance estimated by the coupled system showed a strong dependence on both the aerosol spatial distributions and the associated optical properties. In the NF (No Feedback) case, which refers to the WRF-only stimulated system without aerosol feedbacks, the GHI was overestimated by $50-200W\;m^{-2}$ compared with OBS derived values at each site. In the YF (Yes Feedback) case, in contrast, which refers to the WRF-CMAQ two-way coupled system, the rRMSE was significantly improved by 3.1-3.7% at Suwon and Seoul where the Particulate Matter (PM) concentrations, specifically, those related to the $PM_{10}$ size fraction, were over $100{\mu}g\;m^{-3}$. Thus, the coupled system showed promise for acquiring more accurate solar irradiance forecasts.

• Journal of the Korean Geosynthetics Society
• /
• v.19 no.1
• /
• pp.11-23
• /
• 2020

In this paper development artificial neural networks (ANN) for preliminary design and prediction of urban tunnelling and deep excavation-induced ground settlement was presented. In order to form training and validation data sets for the ANN development, field design and measured data were collected for various tunnelling and deep-excavation sites. The field data were then used as a database for the ANN training. The developed ANN was validated against a testing set and the unused field data in terms of statistical parameters such as R², RMSE, and MAE. The practical use of ANN was demonstrated by applying the developed ANN to hypothetical conditions. It was shown that the developed ANN can be effectively used as a tool for preliminary excavation design and ground settlement prediction for urban excavation problems.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.55 no.4
• /
• pp.55-63
• /
• 2013

This study investigates the trends and uncertainty of the impacts of climate change on paddy rice production in the Geumho river basin. The Long Ashton Research Station stochastic Weather Generator (LARS-WG) was used to derive future climate data for the Geumho river basin from 15 General Circulation models (GCMs) for 3 Special Report on Emissions Scenarios (SRES) (A2, A1B and B1) included in the Intergovernmental Panel on Climate Change (IPCC) 4th assessment report. The Food and Agricultural Organization (FAO) AquaCrop, a water-driven crop model, was statistically calibrated for the 1982 to 2010 climate. The index of agreement (IoA), prediction efficiency ($R^2$), percent bias (PBIAS), root mean square error (RMSE) and a visual technique were used to evaluate the adjusted AquaCrop simulated yield values. The adjusted simulated yields showed RMSE, NSE, IoA and PBIAS of 0.40, 0.26, 0.76 and 0.59 respectively. The 5, 9 and 15 year central moving averages showed $R^2$ of 0.78, 0.90 and 0.96 respectively after adjustment. AquaCrop was run for the 2020s (2011-2030), 2050s (2046-2065) and 2090s (2080-2099). Climate change projections for Geumho river basin generally indicate a hotter and wetter future climate with maximum increase in the annual temperature of $4.5^{\circ}C$ in the 2090s A1B, as well as maximum increase in the rainfall of 45 % in the 2090s A2. The means (and ranges) of paddy rice yields are projected to increase by 21 % (17-25 %), 34 % (27-42 %) and 43 % (31-54 %) for the 2020s, 2050s and 2090s, respectively. The A1B shows the largest rice yield uncertainty in all time slices with standard deviation of 0.148, 0.189 and $0.173t{\cdot}ha^{-1}$ for the 2020s, 2050s and 2090s, respectively.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.6
• /
• pp.9-18
• /
• 2017

The objective of this study was to estimate the climate change impact on inflow to Namgang Dam using SWAT (Soil and Water Assessment Tool) model. The SWAT model was calibrated and validated using observed flow data from 2003 to 2014 for the study watershed. The $R^2$ (Determination Coefficient), RMSE (Root Mean Square Error), NSE (Nash-Sutcliffe efficiency coefficient), and RMAE (Relative Mean Absolute Error) were used to evaluate the model performance. Calibration results showed that the annual mean inflow were within ${\pm}5%$ error compared to the observed. $R^2$ were ranged 0.61~0.87, RMSE were 1.37~7.00 mm/day, NSE were 0.47~0.83, and RMAE were 0.25~0.73 mm/day for daily runoff, respectively. Climate change scenarios were obtained from the HadGEM3-RA. The quantile mapping method was adopted to correct bias that is inherent in the climate change scenarios. Based on the climate change scenarios, calibrated SWAT model simulates the future inflow and evapotranspiration for the study watershed. The expected future inflow to Namgang dam using RCP 4.5 is increasing by 4.8 % and RCP 8.5 is increasing by 19.0 %, respectively. The expected future evapotranspiration for Namgang dam watershed using RCP 4.5 is decreasing by 6.7 % and RCP 8.5 is decreasing by 0.7 %, respectively.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.6
• /
• pp.145-154
• /
• 2012

This paper analyzed the characteristics of traffic accidents in all tunnels on nationwide freeways and selected some various independent variables related to accident occurrence in tunnels. The study aims to develop reliable accident forecasting models using the various dependent variables such as the number of accident (no.), no./km, and no./MVK. Finally, reliable multiple linear regression models were proposed in this paper. This study tested the validity verification of developed models through statistics such as $R^2$, F values, multicollinearity, residual analysis. The paper selected the accident forecasting models considering the characteristics of tunnel accidents and two models were finally proposed according to two groups of tunnel length. In the selected models, natural logarithm of ln(no./MVK) is used for the dependent variable and AADT, vertical slope, and tunnel hight are used for the independent variables. The reliability of two models was proved by the comparison analysis between field data and estimating data using RMSE and MAE. These models may be not only effective in evaluating tunnel safety under design and planning phases of tunnel but also useful to reduce traffic accidents in tunnels and to manage the traffic flow of tunnel.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.51-51
• /
• 2017

지역빈도해석은 짧은 기간의 자료를 보유하고 있는 계측 지점이나 자료가 없는 미계측 지점에서의 확률수문량을 산정하기 위하여 많이 쓰여 진다. 지역빈도해석을 실시하기 위한 조건으로는 우선 수집된 하천유역들을 대상으로 수문학적 동질 지역을 구분하는 것이 중요하다. 그리고 구분되어진 지역에 포함되는 모든 지점들의 자료를 빈도해석 함으로써 관심 지점의 신뢰할 만한 확률수문량을 산정하는 것이다. 그동안의 지역빈도해석은 주로 비건조지역을 중심으로 홍수와 같은 재난재해 대비 그리고 수자원 관리를 위한 연구들을 실시해왔다. 본 연구의 주 목적은 건조지역의 수자원 관리를 위해 건조지역 하천유역을 중심으로 지역빈도해석을 실시하여 신뢰할만한 확률수문량을 산정하는 것이다. 확률수문량 산정값의 정확도를 향상시키기 위해 지역빈도해석 모델에 쓰여 지는 새로운 지형학적 변수들을 제공하였고 수문학적 동질 지역을 구분 위해 수집된 각 하천유역의 형상들을 확인하여 동질 지역을 정의하였다. 예를 들면, 수지형 유역, 부채형 유역, 격자형 유역과 같은 다른 형상들을 구분하여 각 유역 형상 종류별로 동질 지역을 만들었다. 건조지역의 지역빈도해석을 위해 미국 건조지역의 105개 하천유역 유량자료들을 수집 및 이용하였다. 확률수문량 산정을 위하여 앙상블 인경신경망 (Ensemble Artificial Neural Network)과 정준 상관 계수(Canonical Correlation Analysis)를 이용한 지역빈도해석 모델을 만들었다. 제안된 모델의 수행평가와 정확성 평가를 위해 리샘플링 기법인 10-겹 교차 검증 (10-fold cross-validation), 잭나이프 (Jackknife) 기법들을 이용하였고 모델로부터 산정된 확률수문량값을 편향 (Bias), 상대 편향(rBias), 평균 제곱근 오차 (RMSE), 상대 평균 제곱근 오차 (rRMSE)를 통하여 산정 값과 실제 관측 값의 차이를 분석하였다. 그 결과 건조지역의 지역빈도해석을 위해 새롭게 제시된 지형학적 변수들을 사용하였을 때 모델의 수행능력이 향상되었음을 확인하였다. 또한 하천유역 형상에 따라 동질 지역을 구분하였을 때 향상된 확률수문량이 산정되었다. 향상된 지역빈도해석 모델을 통해 건조지역의 신뢰할만한 확률수문량을 산정함으로써 건조지역의 효과적인 수자원 관리를 위한 수공시설물 설계에 중요한 정보들을 제공할 것이다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.491-491
• /
• 2018

본 연구는 포장모형(APEX, Agricultural Policy Environmental eXtender)과 유역모형(SWAT, Soil and Water Assessment Tool)을 연계하여 새만금 유역의 미래 수문 수질영향과 용수생산성을 분석하기 위한 기초연구이다. APEX 모형을 연계하기에 앞서 SWAT 모형을 이용하여 만경강 유역의 유출량, T-N, T-P를 모의하고 그 적용성을 평가하였다. 모의 기간은 2004년부터 2017년까지 총 14년이며, 기상, 유출량 그리고 월단위 수질 자료를 모형의 입력자료 및 보정을 위해 사용하였다. 매개변수 보정은 객관적 보정이 가능한 SWAT-CUP을 이용하여 최적화 하였으며, 매개변수 보정의 목적함수는 NSE(Nash-Sutcliffe Efficiency)로 평가하였다. 모형의 적용성 평가 결과, 보정기간의 연평균 유출량은 실측치 835mm, 모의치 677mm로 나타났고, R2는 0.64, RMSE는 3.87mm/day, NSE는 0.61, RMAE는 0.99로 나타났다. 검정기간의 연평균 유출량은 실측치 884mm, 모의치 702mm로 나타났고, R2는 0.67, RMSE는 2.92mm/day, NSE는 0.7, RMAE는 0.94로 나타났다. 유출량의 결과를 살펴보면 검정기간이 보정기간보다 모의결과가 더 나은 것으로 나타나며, 이는 실측자료의 일관성 차이로 판단된다. T-N과 T-P의 경우 매개변수만으론 보정의 한계가 있으며, 실측치와 근접하게 모의하기 위해서 만경강 본류에 영향을 끼칠 수 있는 외부유입량을 고려할 필요가 있다. 따라서 본 연구에서는 만경강 상류의 경천댐, 대아댐 그리고 용담댐으로 부터 유입되는 외부유입량 자료를 수집하여 SWAT의 입력자료로 구축하였으며, 대상유역 내 익산, 완주, 전주, 김제에 위치하고 있는 하수처리장, 축산폐수처리장, 분뇨처리시설, 산업폐수처리시설 그리고 농공단지처리시설 등 총 12곳에 대한 점오염원 데이터를 입력자료로 구축하여 만경강 상류 농업소유역의 수질영향을 평가하였다. 본 연구결과는 향후 미래 수문 수질 모의에 대한 기초자료로 제공될 것이며, 외부유입량을 고려한 만경강 유역의 용수생산성 분석을 통해 미래 농업수자원 관리계획 수립에 활용할 수 있을 것이다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.421-421
• /
• 2019

본 연구의 목적은 HSPF 모델을 이용하여 비점오염물질이 수질에 미치는 영향을 평가하는 것이다. 합천댐 유역을 연구대상지역으로 선정하였으며, 입력자료는 유역도, 하천도, 토지이용도, 수치표고모델 및 기상자료 등을 이용하였다. HSPF 모형은 2000년부터 2016년까지의 실측값을 이용하여 보정 및 검증이 이루어졌다. 수문 보정을 위한 매개변수는 사용자 설명서와 참고문헌에 근거하여 선정하였으며, 시행착오법에 의해 수행되었다. 모델의 적용성 평가는 $R^2$, RMSE, RMAE, NSE를 사용하였고 $R^2$가 0.78에서 0.83, RMSE는 2.55에서 2.76mm/day, RMAE는 0.46에서 0.48mm/day, NSE는 0.81에서 0.82까지의 범위로 나타났으며, 연간 유출량이 ${\pm}4%$ 오차 이내로 산정되었다. 수질 모형을 구동하기 위한 수질 자료는 환경부에서 제시한 지침에 따라 생활계, 축산계, 산업계, 토지이용량에 따른 발생 부하량과 배출부하량을 산정하였다. 수질 모형 또한 수문과 같은 기간의 자료를 이용하여 보정 및 검정이 이루어졌다. 보정 결과 연평균 BOD의 차이가 0.22mg/L이고 오차범위는 13%였으며, T-N과 T-P는 0.66mg/L, 0.027mg/L의 차이를 가지며 오차범위는 각각 16%, 13%로 나타났다. 수질항목 중에서도 비점오염 관리의 효과를 평가하기 위해 비점오염물질 중 가장 큰 비중을 차지하는 축산계에 감소 시나리오를 적용하였다. 축산계의 배출부하량 감소율이 20%일때의 BOD, T-N, T-P는 각각 3%, 1%, 3% 감소하였으며 40% 감소율을 적용하였을때는 5%, 3%, 4% 감소하였다. 이러한 수질 해석을 결과를 토대로 효과적인 오염물질 방법을 적용하여 수질 개선과 합천댐 유역의 목표수질을 달성 할 수 있을 것으로 판단된다.

• Journal of the Korean Solar Energy Society
• /
• v.38 no.5
• /
• pp.11-25
• /
• 2018

The Ln-least method is commonly used to estimate the Weibull parameters from the observed wind speed data. In previous studies, the bin method has been used to calculate the cumulative frequency distribution for the Ln-least method. The purpose of this study is to obtain better performance in the Ln-least method by applying probability plotting position(PPP) instead of the bin method. Two types of the wind speed data were used for the analysis. One was the observed wind speed data taken from three sites with different topographical conditions. The other was the virtual wind speed data which were statistically generated by a random variable with known Weibull parameters. Also, ten types of PPP formulas were applied which were Hazen, California, Weibull, Blom, Gringorten, Chegodayev, Cunnane, Tukey, Beard and Median. In addition, in order to suggest the most suitable PPP formula for estimating Weibull parameters, two accuracy tests, the root mean square error(RMSE) and $R^2$ tests, were performed. As a result, all of PPPs showed better performances than the bin method and the best PPP was the Hazen formula. In the RMSE test, compared with the bin method, the Hazen formula increased estimation performance by 38.2% for the observed wind speed data and by 37.0% for the virtual wind speed data. For the $R^2$ test, the Hazen formula improved the performance by 1.2% and 2.7%, respectively. In addition, the performance of the PPP depended on the frequency of low wind speeds and wind speed variability.

• Journal of Digital Convergence
• /
• v.19 no.9
• /
• pp.257-269
• /
• 2021

The purpose of this study is to collect biosignal data in a non-invasive and non-restrictive manner using a BCG (Ballistocardiogram) sensor, and utilize artificial intelligence machine learning algorithms in ICT and high-performance computing environments. And it is to present and study a method for developing and validating a data-based blood glucose prediction model. In the blood glucose level prediction model, the input nodes in the MLP architecture are data of heart rate, respiration rate, stroke volume, heart rate variability, SDNN, RMSSD, PNN50, age, and gender, and the hidden layer 7 were used. As a result of the experiment, the average MSE, MAE, and RMSE values of the learning data tested 5 times were 0.5226, 0.6328, and 0.7692, respectively, and the average values of the validation data were 0.5408, 0.6776, and 0.7968, respectively, and the coefficient of determination (R²) was 0.9997. If research to standardize a model for predicting blood sugar levels based on data and to verify data set collection and prediction accuracy continues, it is expected that it can be used for non-invasive blood sugar level management.