• 한국관개배수논문집
• /
• 제19권1호
• /
• pp.87-96
• /
• 2012

Information of local solar radiation is essential for many field, including water resources management, crop yield estimation, crop growth model, solar energy systems and irrigation and drainage design. Unfortunately, solar radiation measurements are not easily available due to the cost and maintenance and calibration requirements of the measuring equipment and station. Therefore, it is important to elaborate methods to estimate the solar radiation based on readily available meteorological data. In this study, two empirical equations are employed to estimate daily solar radiation using Cheongju Regional Meteorological Office data. Two scenarios are considered: (a) sunshine duration data are available for a given location, or (b) only daily cloudiness index records exist. Simple linear regression with daily sunshine duration and cloudiness index as the dependent variable accounted for 91% and 80%, respectively of the variation of solar radiation(H) at 2011. Daily global solar radiation is highly correlated with sunshine duration. In order to indicate the performance of the models, the statistical test methods of the mean bias error(MBE), root mean square error(RMSE) and correlation coefficient(r) are used. Sunshine duration and cloudiness index can be easily and reliably measured and data are widely available.

• Wind and Structures
• /
• 제32권2호
• /
• pp.161-167
• /
• 2021

In this study, the artificial neural network (ANN) method was used for estimating the monthly mean wind speed of Sivas, in the central part of Turkey. Eighteen years of wind speed data obtained from nine measurement stations during the period of 2000-2017 at 10 m height was used for ANN analysis. It was found that mean absolute percentage error (MAPE) ranged from 3.928 to 6.662, mean bias error (MBE) ranged from -0.089 to -0.003, while root mean square error (RMSE) ranged from 0.050 to 0.157 and R2 ranged from 0.86 to 0.966. ANN models provide a good approximation of the wind speed for all measurement stations, however, a tendency to underestimate is also obvious.

• KIEAE Journal
• /
• 제11권1호
• /
• pp.15-20
• /
• 2011

Computer simulation of buildings and solar energy systems is being used increasingly in energy assessments and design. For the six locations (Seoul, Incheon, Daejeon, Deagu, Gwangju and Busan) in South Korea where the global hourly solar irradiation (GHSI) is currently measured, GHSI was calculated using a comparatively simple cloud cover radiation model (CRM) and sunshine fraction radiation model (SFRM). The result was that the measured and calculated values of GHSI were similar for the six regions. Results of cloud cover and sunshine fraction models have been compared with the measured data using the coefficient of determination (R2), root-mean-square error (RMSE) and mean bias error (MBE). The strength of correlation R2 varied within similar ranges: 0.886-0.914 for CRM and 0.908-0.934 for SFRM. Average MBE for the CRM and SFRM were 6.67 and 14.02 W/m2, respectively, and average RMSE 104.36 and 92.15 W/m2. This showed that SFRM was slightly accurate and used many regions as compared to CRM for prediction of GHSI.

• 대한원격탐사학회지
• /
• 제38권5_3호
• /
• pp.967-977
• /
• 2022

산불의 발생과 강도는 기후 변화로 인하여 증가하고 있다. 산불 연기에 의한 배출가스 대기질과 온실 효과에 영향을 미치는 주요 원인 중 하나로 인식되고 있다. 산불 연기의 효과적인 탐지를 위해서는 위성 산출물과 기계학습의 활용이 필수적이다. 현재까지 산불 연기 탐지에 대한 연구는 구름 식별의 어려움 및 모호한 경계 기준 등으로 인한 어려움이 존재하였다. 본 연구는 우리나라 환경위성 센서인 Geostationary Environment Monitoring Spectrometer (GEMS)의 Level 1, Level 2 자료와 기계학습을 이용한 산불 연기 탐지를 목적으로 한다. 2022년 3월 강원도 산불을 사례로 선정하여 산불 연기 레이블 영상을 생성하고, 랜덤 포레스트 모델에 GEMS Level 1 및 Level 2 자료를 투입하여 연기 픽셀 분류 모델링을 수행하였다. 훈련된 모델에서 입력변수의 중요도는 Aerosol Optical Depth (AOD), 380 nm 및 340 nm의 복사휘도 차, Ultra-Violet Aerosol Index (UVAI), Visible Aerosol Index (VisAI), Single Scattering Albedo (SSA), 포름알데히드, 이산화질소, 380 nm 복사휘도, 340 nm 복사휘도의 순서로 나타났다. 또한 2,704개 픽셀에 대한 산불 연기 확률(0≤p≤1) 추정에서 Mean Bias Error (MBE)는 -0.002, Mean Absolute Error (MAE)는 0.026, Root Mean Square Error (RMSE)는 0.087, Correlation Coefficient (CC)는 0.981의 정확도를 보였다.

• 한국태양에너지학회 논문집
• /
• 제30권2호
• /
• pp.16-21
• /
• 2010

Computer simulation of buildings and solar energy systems are being used increasingly in energy assessments and design. This paper discusses the possibility of using sunshine duration data instead of global hourly solar irradiation (GHSI) data for localities with abundant data on sunshine duration. For six locations in South Korea where global radiation is currently measured, the global radiation was calculated using Sunshine Duration Radiation Model (SDRM), compared and analyzed. Results of SDRM has been compared with the measured data on the coefficients of determination (R2), root-mean-square error (RMSE) and mean bias error (MBE). This study recommends the use of sunshine duration based irradiation models if measured solar radiation data is not available.

• 한국환경과학회지
• /
• 제11권12호
• /
• pp.1195-1204
• /
• 2002

We calculated dose rate using radiative transfer equations to consider radiative processes distinctly. The dose rate at Pohang(36°02'N, 129°23'E) was calculated using measured ozone and meteorological data and two-stream approximations(quadrature, Eddington, delta Eddington, PIFM(practical improved flux method), discrete ordinate, delta discrete ordinate) are used in solving equation. The purpose of this study is to determine the most compatible radiative transfer approximation for simulating the radiative and photochemical processes of atmosphere through comparision between calculated and measured values. Dose rate of the biologically effective irradiance in the region 0.28-0.32 U m showed the highest value when quadrature and Eddington was used and lower value on condition that delta scaling was applied. Correlation coefficient between dose rate at surface using radiation transfer equation and measured UV-B at Pohang was 0.78, 0.79 and 0.81 when delta Eddington, PIFM and delta discrete ordinate were used. Also, in case of above approximations were used, MBE(Mean Bias Error) was within -0.3MED/30min and RMBE(Relative Mean Bias Error) was below 10% between 1200 LST and 1400 LST Approximations which are compatible in estimating radiative process are delta Eddington, PIFM and delta discrete ordinate. Especially, in case that radiative process is considered more detail, delta discrete ordinate increased the number of stream is proper.

• 대한원격탐사학회지
• /
• 제38권5_3호
• /
• pp.953-966
• /
• 2022

에어로솔(aerosol)은 대기 질을 악화시키는 등 인체 건강에 악영향을 끼치므로 에어로솔의 분포 및 특성에 대한 정량적인 관측이 필수적이다. 최근 전 지구 규모에서의 주기적이고 정량적인 정보 획득 수단으로 위성관측 Aerosol Optical Depth (AOD) 영상이 다양한 연구에 활용되지만 광학센서 기반의 위성 AOD 영상은 구름 등의 조건을 가진 일부 지역에서 결측을 가진다. 이에 본 연구는 위성자료의 결측복원을 위하여 격자형 기상자료와 지리적 요소를 입력변수로 하여 Random Forest (RF) 기반 gap-filling 모델을 생성한 이후, gap-free GK-2A/AMI AOD hourly 영상을 산출하였다. 모델의 정확도는 -0.002의 Mean Bias Error (MBE), 0.145의 Root Mean Square Error (RMSE)로, 원자료의 목표 정확도보다 높으며 상관계수 0.714로 복원 대상이 대기변수인 점을 감안하면 상관계수 측면에서도 충분한 설명력을 갖춘 모델이다. 정지궤도 위성의 높은 시간 해상도는 일변화 관측에 적합하며 대기보정을 위한 입력, 지상 미세먼지 농도 추정, 소규모 화재 또는 오염원 분석 등 타 연구를 위한 자료 활용 측면에서 중요하다.

• 대기
• /
• 제32권3호
• /
• pp.179-189
• /
• 2022

The purpose of this study is to build and evaluate a high-resolution (50 m) KMAPP (Korea Meteorological Administration Post Processing) reflecting building data. KMAPP uses LDAPS (Local Data Assimilation and Prediction System) data to detail ground wind speed through surface roughness and elevation corrections. During the detailing process, we improved the vegetation roughness data to reflect the impact of city buildings. AWS (Automatic Weather Station) data from a total of 48 locations in the metropolitan area including Seoul in 2019 were used as the observation data used for verification. Sensitivity analysis was conducted by dividing the experiment according to the method of improving the vegetation roughness length. KMAPP has been shown to improve the tendency of LDAPS to over simulate surface wind speeds. Compared to LDAPS, Root Mean Square Error (RMSE) is improved by approximately 23% and Mean Bias Error (MBE) by about 47%. However, there is an error in the roughness length around the Han River or the coastline. Accordingly, the surface roughness length was improved in KMAPP and the building information was reflected. In the sensitivity experiment of improved KMAPP, RMSE was further improved to 6% and MBE to 3%. This study shows that high-resolution KMAPP reflecting building information can improve wind speed accuracy in urban areas.

• 설비공학논문집
• /
• 제27권3호
• /
• pp.128-136
• /
• 2015

Reducing the building energy consumption has become one of the most important issues. However, the current engineering and technological involvement in energy analysis has been relatively low in the existing buildings. In the existing buildings, end-use analysis must be accompanied to calculate the exact amount in energy savings and such analysis should be conducted based on the energy billing data or measurement data by calibration process. Mostly, detailed energy simulation programs have been proposed for the analysis but, it is difficult to utilize them due to realistic problems. In this paper, we developed an end-use analysis tool that have input function for energy audit data and two case studies were conducted in the real-life office buildings located in Seoul, Korea. Mean Bias Error (MBE) and Coefficient of Variation of Root-Mean- Squreaed-Error (CV(RMSE)) are used for the criteria of comparison. Each index was calculated by using monthly utility bills of electricity and gas consumption. Results showed that MBE and CV (RMSE) represented with acceptable values of -0.1% and 5.7% respectively.

• Advances in environmental research
• /
• 제5권3호
• /
• pp.153-167
• /
• 2016

We applied multilayer perceptron (MLP) and radial basis function (RBF) neural network in upstream and downstream water quality stations of the Karaj Reservoir in Iran. For both neural networks, inputs were pH, turbidity, temperature, chlorophyll-a, biochemical oxygen demand (BOD) and nitrate, and the output was dissolved oxygen (DO). We used an MLP neural network with two hidden layers, for upstream station 15 and 33 neurons in the first and second layers respectively, and for the downstream station, 16 and 21 neurons in the first and second hidden layer were used which had minimum amount of errors. For learning process 6-fold cross validation were applied to avoid over fitting. The best results acquired from RBF model, in which the mean bias error (MBE) and root mean squared error (RMSE) were 0.063 and 0.10 for the upstream station. The MBE and RSME were 0.0126 and 0.099 for the downstream station. The coefficient of determination ($R^2$) between the observed data and the predicted data for upstream and downstream stations in the MLP was 0.801 and 0.904, respectively, and in the RBF network were 0.962 and 0.97, respectively. The MLP neural network had acceptable results; however, the results of RBF network were more accurate. A sensitivity analysis for the MLP neural network indicated that temperature was the first parameter, pH the second and nitrate was the last factor affecting the prediction of DO concentrations. The results proved the workability and accuracy of the RBF model in the prediction of the DO.