• 환경영향평가
• /
• 제31권2호
• /
• pp.83-94
• /
• 2022

본 연구는 국가측정망(에어코리아)에서 제공하는 2017년, 2019년 및 2020년도 대기질확정 데이터를 이용하여 Deep Neural Network(DNN) 모델을 학습하고, 2016년과 2018년도 데이터를 이용하여 학습된 모델을 평가·검증하였다. 피어슨 상관계수 0.2를 기준으로 SO₂, CO, NO₂, PM₁₀ 항목을 독립변수로 하여 초기 모델링을 진행하였고, 예측의 정확도를 높이기 위한 방법으로 시계열적 요소를 반영한 월별 모델링(개선모델)을 진행하여 초기모델과 비교·분석하였다. 분석에 사용한 지표는 RMSE(Root mean square error) 방법으로 오차를 계산하였으며, 예측 결과 초기모델의 RMSE값은 5.78로 국가측정망의 예측이동 평균모델의 결과(10.77)와 비교하여 초기모델에서 약 46% 오차가 감소하였다. 또한, 개선모델의 경우, 초기모델 대비 11월 모델을 제외한 모든 월별모델에서 정확도 향상이 있었다. 따라서, 본 연구에서는 DNN 모델링이 PM_2.5 농도 예측에 효과적인 방법임을 제안할 수 있었으며, 향후 추가적인 독립변수 선정 및 시계열 요소를 고려한 방법으로 모델의 정확도 개선 가능성을 확인할 수 있었다.

• 환경영향평가
• /
• 제20권5호
• /
• pp.747-755
• /
• 2011

This study was investigated the relationship between the temperature and the mortality of aged (${\geq}65$ yr) during the winter seasons from 1992 to 2007 in Seoul, Korea by utilizing climate data and death records. The study also estimated the future risks by employing the projections of the population in Seoul, Korea and climate change scenario of Korea from 2011 to 2030. The limitation of this study was the impossibility in the prediction of daily mortality counts. Therefore, daily death numbers could be predicted based on the future population projection for Korea and the death records of 2005. The result indicated that risks increased by 0.27%, 0.52%, 0.32% and 0.41% in association with the $1^{\circ}C$ decrease in daily minimum temperature from the mortality counts of total, respiratory, cardiovascular, and cardiorespiratory in the past date while 0.31%, 0.42%, 0.59% and 0.66% in the future. Based on the results obtained from this study, it is concluded that the risk in the future will be higher than the past date although there is an uncertainty in estimating death counts in the future.

• 환경영향평가
• /
• 제25권3호
• /
• pp.175-189
• /
• 2016

철도소음지도는 환경부 고시 소음 진동관리법에 따라서 그 작성방법이 고시되어 있고, 소음지도 작성 시에 철도소음원 관련 영향인자에 대하여 적용 예측식 별 열차구분을 제시하고 있으며, 열차 특성 입력 시에 브레이크 흡음율을 "0"으로 설정할 것을 제시한다. 소음지도 작성방법이 고시 된 이후 국내의 고속철도차량은 그 구조가 변경되어 가고 있고, 고시된 작성방법에서 제시되지 않은 신규 열차유형도 생겨나고 있다. 따라서 현재의 시점에서 국외의 철도소음 예측식을 활용하여 고시된 소음지도 작성방법에 의하여 철도소음을 예측하는 경우 열차의 유형과 관련된 입력인자에 따른 예측결과를 검토할 필요가 있다. 본 논문에서는 철도소음을 예측할 시에 국내에서 통상적으로 가장 빈번히 사용되는 Schall03을 활용하여 철도소음을 예측하였으며, 열차의 유형 선택, 열차의 특성 중 디스크브레이크 사용율 입력, 레일의 이음매 여부에 의한 예측결과에의 영향을 파악하고자 하였다. 2013년 이후 추가된 신규 국내의 열차에 대하여 대응하는 국외 열차의 유형을 검토하였고, 디스크브레이크사용율 설정은 실측값과 예측값의 차이에 적지 않은 비중을 차지함을 파악할 수 있었으며, 이뿐 아니라, 레일표면의 조도(roughness)레벨 수준도 함께 고찰하고자 하였다. 또한 레일의 이음매가 존재하는 구간에 대하여 예측 시에 이를 고려하지 않았을 경우에의 실측값과의 차이에 대한 분석을 수행하였다.

• 환경영향평가
• /
• 제14권4호
• /
• pp.157-164
• /
• 2005

Existing models that predict of Daily water supply include statistical models and neural network model. The neural network model was more effective than the statistical models. Only neural network model, which predict of Daily water supply, is focused on estimation of the operational control. Neural network model takes long learning time and gets into local minimum. This study proposes Neuro Genetic hybrid model which a combination of genetic algorithm and neural network. Hybrid model makes up for neural network's shortcomings. In this study, the amount of supply, the mean temperature and the population of the area supplied with water are use for neural network's learning patterns for prediction. RMSE(Root Mean Square Error) is used for a MOE(Measure Of Effectiveness). The comparison of the two models showed that the predicting capability of Hybrid model is more effective than that of neural network model. The proposed hybrid model is able to predict of Daily water, thus it can apply real time estimation of operational control of water works and water drain pipes. Proposed models include accidental cases such as a suspension of water supply. The maximum error rate between the estimation of the model and the actual measurement was 11.81% and the average error was lower than 1.76%. The model is expected to be a real-time estimation of the operational control of water works and water/drain pipes.

• 한국대기환경학회지
• /
• 제29권5호
• /
• pp.581-600
• /
• 2013

The current status of atmospheric environmental impact assessment (EIA) has been summerized and future prospective for effective and accurate atmospheric EIA has been proposed by reviewing available papers and reports for the atmospheric EIA. The number of reports for the EIA in the EIA support system which is operated by the Korean Environmental Institute have been dramatically decreased from 282 reports in 2008 to 113 reports in 2012 during recent five years. This is partially due to simplification of the EIA procedure, the contraction of the public development and economic recession. We analyzed details of the EIA report to review how actual atmospheric EIA has preformed according to the EIA guidelines from the Korean Ministry of Environment. The 264 reports of EIA published in 2011 and 2012 had been reviewed especially focusing on the atmospheric evaluation items such as meteorology, air quality measurement and modeling, odor measurement and modeling, wind corridor in urban planning, and climate change. In overall sense, the atmospheric EIA has been performed quite well by abiding the guidelines except for local meteorological data measurement, permit standard for air quality and wind corridor. The new approaches to improve the procedure of atmospheric EIA and to reflect future of national air quality standard of $PM_{2.5}$ have been proposed. The guidelines on how to evaluate the wind corridor, to implement atmospheric EIA for $PM_{2.5}$ permit, and how to acquire local meteorological data by combining local measurement and model prediction are required for the effective and future oriented atmospheric EIA.

• 환경영향평가
• /
• 제12권4호
• /
• pp.245-257
• /
• 2003

$SO_2$ concentrations in the Seoul Metropolitan Area (SMA) were predicted by the regional segment ISCST3 modeling. The SMA was segmented by three modeling regions where the weather monitoring station exists since the area of the SMA, approximately $100km{\times}100km$, is too wide to be modeled by one modeling domain. The predicted concentrations by the model were compared with the measured concentrations at 39 air monitoring stations located in the SMA to validate the ISCST3 modeling coupled with the regional segment approach. The predicted concentrations by the regional segment method showed better performance in depicting the measurements than those by the non-segment ISCST3 modeling. The correction methods of the calculated concentrations reviewed were here the correlation method by the first order linear equation and the ratio method of observed to calculated concentrations. The corrected concentrations by two methods showed good agreement with the measured data. The ratio method was, however, easily applicable to the concentration correction in case of a wide modeling region considered in this study.

• 환경영향평가
• /
• 제27권5호
• /
• pp.447-474
• /
• 2018

본 연구의 목적은 다양한 지리통계학적 공간화 기법을 적용한 격자기후자료와 기상청에서 제공하는 국지예보모델(Local Data Assimilation and Prediction System, LDAPS) 격자기후자료를 비교 분석하여 남한 지역의 고해상도 격자기후지도 작성 방안을 모색하는 것이다. 2017년의 595개 기후관측자료 중, 80%의 지점자료를 이용하여 순간 온도와 1시간 누적강수량에 대한 격자기후자료를 생성하였고 나머지 117개의 지점자료를 검증에 이용하였다. ArcGIS10.3.1과 Python3.6.4을 이용하여 관측자료 및 DEM을 IDW, 공동크리깅, 크리깅에 적용한 후, 공간보간 결과를 3개 군집으로 나누어 검증하였으며 LDAPS 격자기후자료를 바탕으로 유역 별 패턴 비교를 수행하였다. 결과적으로 순간 온도의 공간화에는 고도를 부변수로 추가한 공동크리깅이, 1시간 누적강수량 공간화에는 IDW가 가장 적합하였다.

• Earthquakes and Structures
• /
• 제9권4호
• /
• pp.911-936
• /
• 2015

This work evaluates the performance of a number of seismic assessment procedures when applied to a case study reinforced concrete (RC) wall building. The performance of each procedure is evaluated through its ability to accurately predict deformation demands, specifically, roof displacement, inter-storey drift ratio and wall curvatures are considered as the key engineering demand parameters. The different procedures include Direct Displacement-Based Assessment, nonlinear static analysis and nonlinear dynamic analysis. For the latter two approaches both lumped and distributed plasticity modelling are examined. To thoroughly test the different approaches the case study building is considered in different configurations to include the effects of unequal length walls and plan asymmetry. Recommendations are made as to which methods are suited to different scenarios, in particular focusing on the balance that needs to be made between accurate prediction of engineering demand parameters and the time and expertise required to undertake the different procedures. All methods are shown to have certain merits, but at the same time a number of the procedures are shown to have areas requiring further development. This work also highlights a number of key aspects related to the seismic response of RC wall buildings that may significantly impact the results of an assessment. These include the influence of higher-mode effects and variations in spectral shape with ductility demands.

• 환경영향평가
• /
• 제23권5호
• /
• pp.364-378
• /
• 2014

과거 50여 년간 한국의 생태발자국(Ecological Footprint, EF)은 가파르게 증가해 왔으며, 이에 따라 오버슈트(Overshoot) 역시 증가해 왔다. 오버슈트를 야기하는 중요한 원인에는 인구 증가와 일인당 자원 사용 강도 증가가 있다. 본 연구에서는 이들 원인 가운데 어떤 변수가 지난 50여 년간 한국의 EF에 더 큰 영향을 미쳤는지에 대해 알아보았다. 소비 부문들 가운데, 에너지 소비에 따른 탄소발자국(Carbon Footprint, CF), 단백질 섭취에 따른 초지발자국(Grazing Land Footprint)과 어장 발자국(Fishing Grounds)이 EF 증가에 크게 영향을 주었다. 지난 50여 년간의 추세가 앞으로도 유지된다면, 2060년에는 일인당 EF 값이 2009년 현재의 2배에 달할 것으로 보이며, 2031년 이후 인구가 감소함에도 불구하고 1인당 EF 값의 증가에 따른 영향으로 EF는 2059년까지 증가할 것으로 보인다. 그러므로 향후 개개인의 소비 패턴과 행동 변화를 유도하는 것으로 환경관리 방향을 전환해갈 필요가 있을 것이다.

• Coupled systems mechanics
• /
• 제6권1호
• /
• pp.55-74
• /
• 2017

The evaluation of torsional effects on multistory buildings remains an open issue, despite considerable research efforts and numerous publications. In this study, a large number of multiple test structures are considered with normally distributed topological attributes, in order to quantify the statistically derived relationships between the torsional criteria and response parameters. The linear regression analysis results, depict that the center of twist and the ratio of torsion (ROT) index proved numerically to be the most reliable criteria for the prediction of the modal rotation and displacements, however the residuals distribution and R-squared derived for the ductility demands prediction, was not constant and low respectively. Thus, the assessment of the torsional parameters' contribution to the nonlinear structural response was investigated using artificial neural networks. Utilizing the connection weights approach, the Center of Strength, Torsional Stiffness and the Base Shear Torque curves were found to exhibit the highest impact numerically, while all the other torsional indices' contribution was investigated and quantified.