• Atmosphere
• /
• v.22 no.1
• /
• pp.47-55
• /
• 2012

The characteristics of flow and pollutant dispersion for fire scenarios in an urban area are numerically investigated. A computational fluid dynamics (CFD) model coupled to a mesoscale weather research and forecasting (WRF) model is used in this study. In order to more accurately represent the effect of topography and buildings, the geographic information system (GIS) data is used as an input data of the CFD model. Considering prevailing wind, firing time, and firing points, four fire scenarios are setup in April 2008 when fire events occurred most frequently in recent five years. It is shown that the building configuration mainly determines wind speed and direction in the urban area. The pollutant dispersion patterns are different for each fire scenario, because of the influence of the detailed flow. The pollutant concentration is high in the horse-shoe vortex and recirculation zones (caused by buildings) close to the fire point. It thus means that the potential damage areas are different for each fire scenario due to the different flow and dispersion patterns. These results suggest that the accurate understanding of the urban flow is important to assess the effect of the pollutant dispersion caused by fire in an urban area. The present study also demonstrates that CFD model can be useful for the assessment of urban environment.

• Journal of Convergence for Information Technology
• /
• v.11 no.3
• /
• pp.7-13
• /
• 2021

This study develops an artificial intelligence prediction system for Fine particulate Matter(PM2.5) based on the deep learning algorithm GAN model. The experimental data are closely related to the changes in temperature, humidity, wind speed, and atmospheric pressure generated by the time series axis and the concentration of air pollutants such as SO2, CO, O3, NO2, and PM10. Due to the characteristics of the data, since the concentration at the current time is affected by the concentration at the previous time, a predictive model for recursive supervised learning was applied. For comparative analysis of the accuracy of the existing models, CNN and LSTM, the difference between observation value and prediction value was analyzed and visualized. As a result of performance analysis, it was confirmed that the proposed GAN improved to 15.8%, 10.9%, and 5.5% in the evaluation items RMSE, MAPE, and IOA compared to LSTM, respectively.

• Journal of Environmental Science International
• /
• v.28 no.8
• /
• pp.701-707
• /
• 2019

Highland farming is agriculture that takes place 400 m above sea level and typically involves both low temperatures and long sunshine hours. Most highland Chinese cabbages are harvested in the Gangwon province. The Ubiquitous Sensor Network (USN) has been deployed to observe Chinese cabbages growth because of the lack of installed weather stations in the highlands. Five representative Chinese cabbage cultivation spots were selected for USN and meteorological data collection between 2015 and 2017. The purpose of this study is to develop a weight prediction model for Chinese cabbages using the meteorological and growth data that were collected one week prior. Both a regression and random forest model were considered for this study, with the regression assumptions being satisfied. The Root Mean Square Error (RMSE) was used to evaluate the predictive performance of the models. The variables influencing the weight of cabbage were the number of cabbage leaves, wind speed, precipitation and soil electrical conductivity in the regression model. In the random forest model, cabbage width, the number of cabbage leaves, soil temperature, precipitation, temperature, soil moisture at a depth of 30 cm, cabbage leaf width, soil electrical conductivity, humidity, and cabbage leaf length were screened. The RMSE of the random forest model was 265.478, a value that was relatively lower than that of the regression model (404.493); this is because the random forest model could explain nonlinearity.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.101-112
• /
• 2018

The purpose of the study is to predict the number of police calls using neural network which is one of the machine learning and negative binomial regression, by using the data of 112 police calls received from Chungnam Provincial Police Agency from June 2016 to May 2017. The variables which may affect the police calls have been selected for developing the prediction model : time, holiday, the day before holiday, season, temperature, precipitation, wind speed, jurisdictional area, population, the number of foreigners, single house rate and other house rate. Some variables show positive correlation, and others negative one. The comparison of the methods can be summarized as follows. Neural network has correlation coefficient of 0.7702 between predicted and actual values with RMSE 2.557. Negative binomial regression on the other hand shows correlation coefficient of 0.7158 with RMSE 2.831. Neural network has low interpretability, but an excellent predictability compared with the negative binomial regression. Based on the prediction model, the police agency can do the optimal manpower allocation for given values in the selected variables.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.40 no.4
• /
• pp.201-212
• /
• 2016

A Wind resource assessment and optimal micrositing of wind turbines were implemented for the development of an onshore wind farm of 30 MW capacity on Gadeok Island in Busan, Republic of Korea. The wind data measured by the automatic weather system (AWS) that was installed and operated in the candidate area were used, and a reliability investigation was conducted through a data quality check. The AWS data were measured for one year, and were corrected for the long term of 30 years by using the modern era retrospective analysis for research and application (MERRA) reanalysis data and a measure- correlate-predict (MCP) technique; the corrected data were used for the optimal micrositing of the wind turbines. The micrositing of the 3 MW wind turbines was conducted under 25 conditions, then the best-optimized layout was analyzed with a various wake model. When the optimization was complete, the estimated park efficiency and capacity factor were from 97.6 to 98.7 and from 37.9 to 38.3, respectively. Furthermore, the annual energy production (AEP), including wake losses, was estimated to be from 99,598.4 MWh to 100,732.9 MWh, and the area was confirmed as a highly economical location for development of a wind farm.

• The Korean Journal of Applied Statistics
• /
• v.30 no.5
• /
• pp.633-645
• /
• 2017

This study proposes a statistical procedure for analyzing container ship operation data that can help determine fuel consumption patterns. We first investigate the features that affect fuel consumption and develop the prediction model to find current fuel consumption. The ship data can be divided into two-type data. One set of operation data includes sea route, voyage information, longitudinal water speed, longitudinal ground speed, and wind, the other includes machinery data such as engine power, rpm, fuel consumption, temperature, and pressure. In this study, we separate the effects of external force on ships according to Beaufort Scale and apply a partial least squares regression to develop a prediction model.

• Advances in environmental research
• /
• v.4 no.4
• /
• pp.219-231
• /
• 2015

In recent years, raising air pollutants has become as a big concern, especially in metropolitan cities such as Tehran. Therefore, forecasting the level of pollutants plays a significant role in air quality management. One of the forecasting tools that can be used is an artificial neural network which is able to model the complicated process of air pollution. In this study, we applied two different methods of artificial neural networks, the Multilayer Perceptron (MLP) and Radial Basis Function (RBF), to predict the hourly air concentrations of toluene in Tehran. Hourly temperature, wind speed, humidity and $NO_x$ were selected as inputs. Both methods had acceptable results; however, the RBF neural network produced better results. The coefficient of determination ($R^2$) between the observed and predicted data was 0.9642 and 0.99 for MLP and RBF neural networks, respectively. The results of the mean bias errors (MBE) were 0.00 and -0.014 for RBF and MLP, respectively which indicate the adequacy of the models. The index of agreement (IA) between the observed and predicted data was 0.999 and 0.994 in the RBF and the MLP, respectively which indicates the efficiency of the models. Finally, sensitivity analysis related to the MLP neural network determined that temperature was the most significant factor in air concentration of toluene in Tehran which may be due to the volatile nature of toluene.

• Journal of the Korean Institute of Gas
• /
• v.1 no.1
• /
• pp.73-80
• /
• 1997

This study was performed to develop the dispersion modeling methodology for quantitative prediction of the hazard distance or toxic buffer distance by comparing 10-min average, 30-min average, and 1-hr average maximum ground-level concentration with $Cl_2$ regultaion concentration, IDLH and ERPG-3 concentration for hazardous toxic gas, $Cl_2$ releases from the storage tank of the chemical plant facilities. For this dispersion modeling, the source term model, dispersion model, meteorological and topographical data are incorporated into the SuperChems model, and then the effects of the atmospheric stability, wind speed, and surface roughness length changes on the maxum ground-level concentration were estimated.

• 한국전산유체공학회:학술대회논문집
• /
• 2004.10a
• /
• pp.95-99
• /
• 2004

The developing Smart UAV in KARI supposes high speed flight as like a conventional plane, as well as vertical takeoff and landing as like a helicopter. Therefore, the air intake system should be designed to provide the sufficient air flow to the engine and the maximum possible total pressure recovery at the engine intake screen over a wide range of flight conditions. For this purpose, we designed the intake system using a pilot type intake model and plenum chamber In this paper, we designed the intake model and analyzed the performance of designed intake system using the general-purpose commercial CFD code, CFD-ACE+ For 3-D calculation, we generated mesh using the unstructured gird and used $\kappa-\epsilon$ turbulence model. The analysis results of the total pressure variation and the velocity distribution was illustrated in this paper. The pressure recovery and distortion coefficient at a plane coincident with the compressor inlet were calculated and streamline variation through the intake system was investigated at the worst condition as well as the standard flight condition.

• Fire Science and Engineering
• /
• v.32 no.3
• /
• pp.76-87
• /
• 2018

This study describes the damage effects modeling for a quantitative prediction about the hazardous distances from pressurized chlorine saturated liquid tank, which has two-phase leakage. The heavy gas, chlorine is an accidental substance that is used as a raw material and intermediate in chemical plants. Based on the evaluation method for damage prediction and accident effects assessment models, the operating conditions were set as the standard conditions to reveal the optimal variables on an accident due to the leakage of a liquid chlorine storage vessel. A model of the atmospheric diffusion model, ALOHA (V5.4.4) developed by USEPA and NOAA, which is used for a risk assessment of Off-site Risk Assessment (ORA), was used. The Yeosu National Industrial Complex is designated as a model site, which manufactures and handles large quantities of chemical substances. Weather-related variables and process variables for each scenario need to be modelled to derive the characteristics of leakage accidents. The estimated levels of concern (LOC) were calculated based on the Gaussian diffusion model. As a result of ALOHA modeling, the hazardous distance due to chlorine diffusion increased with increasing air temperature and the wind speed decreased and the atmospheric stability was stabilized.