• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.183-185
• /
• 2015

Recently, big data analysis based on machine learning has gained popularity and many machine learning techniques have been applied to the field of agriculture. By using machine learning technique to analyze huge number of samples of biological and environmental data, new observations can be found. In this research, we consider the estimation of proportional daily weight increase (PDWI) based on measurement data from experimental swine farm. In order to derive the exact formulation for PDWI estimation, we have used measured value of mean, daily maximum, daily minimum of temperature, humidity, CO2, wind speed and measured PDWI values. Based on collected data, we have derived equation for PDWI estimation using tree-based algorithm. In the derived formulation, we have found that the daily average temperature is the most dominant factor that affects PDWI. Our results can be applied to pig farms to estimate the PDWI of swine.

• Journal of Wetlands Research
• /
• v.21 no.4
• /
• pp.281-289
• /
• 2019

In this study, the typhoon damage forecasting model was developed for southern inland district. The typhoon damage in the inland district is caused by heavy rain and strong winds, variables are many and varied, but the damage data of the inland district are not enough to develop the model. The hydrological data related to the typhoon damage were hour maximum rainfall amount which is accumulated 3 hour interval, the total rainfall amount, the 1-5 day anticipated rainfall amount, the maximum wind speed and the typhoon center pressure at latitude 33° near the Jeju island. The Multivariate Analysis such as cluster Analysis considering the lack of damage data and principal component analysis removing multi-collinearity of rainfall data are adopted for the damage forecasting model. As a result of applying the developed model, typhoon damage estimated and observed values were up to 2.2 times. this is caused it is difficult to estimate the damage caused by strong winds and it is assumed that the local rainfall characteristics are not considered properly measured by 69 ASOS.

• Journal of Navigation and Port Research
• /
• v.26 no.2
• /
• pp.221-226
• /
• 2002

To provide reliable data for drift prediction models, field experiments were carried out in the coastal region off Busan port. Four different size of vessels(10, 30, 50, 90G/T ton) were deployed for the experiment. Among them G/T 50ton class vessel was equipped with instruments measuring the currents, winds, headings and trajectory data. In the rest of vessels only the position data were recorded for the purpose of target divergence study. The trajectories of each vessel were measured by DGPS(Differential Global Positioning System) and collected by APRS(Automatic Position Reporting System). The experiment was done in wind of 2~10m/s and current of 0.5~1.5m/s. The leeway was derived by subtracting surface current velocity from target drifting velocity. The leeway rate of G/T 50ton vessel was found to be about 3.6% and the computed leeway speed equation was $U_L$=0.042 W - 0.034. The processed leeway angle data were deflected by $-30^{\circ}$~$40^{\circ}$ from the direction of ship drift.

• Korean Journal of Agricultural Science
• /
• v.46 no.1
• /
• pp.67-78
• /
• 2019

The purpose of this study was to predict the water quality using the RNN (recurrent neutral network) and LSTM (long short-term memory). These are advanced forms of machine learning algorithms that are better suited for time series learning compared to artificial neural networks; however, they have not been investigated before for water quality prediction. Three water quality indexes, the BOD (biochemical oxygen demand), COD (chemical oxygen demand), and SS (suspended solids) are predicted by the RNN and LSTM. TensorFlow, an open source library developed by Google, was used to implement the machine learning algorithm. The Okcheon observation point in the Geum River basin in the Republic of Korea was selected as the target point for the prediction of the water quality. Ten years of daily observed meteorological (daily temperature and daily wind speed) and hydrological (water level and flow discharge) data were used as the inputs, and irregularly observed water quality (BOD, COD, and SS) data were used as the learning materials. The irregularly observed water quality data were converted into daily data with the linear interpolation method. The water quality after one day was predicted by the machine learning algorithm, and it was found that a water quality prediction is possible with high accuracy compared to existing physical modeling results in the prediction of the BOD, COD, and SS, which are very non-linear. The sequence length and iteration were changed to compare the performances of the algorithms.

• 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.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.29-39
• /
• 2017

In this research, thermal design data such as heat transfer coefficient on the wall surface required for ventilation system design which is to prevent the temperature rise in the underground utility tunnel that three sides are adjoined with the ground was investigated in numerical analalysis. The numerical model has been devised including the tunnel lining of the underground utility tunnel in order to take account for the heat transfer in the tunnel walls. The air temperature in the tunnel, wall temperature, and the heating value through the wall based on heating value(117~468 kW/km) of the power cable installed in the tunnel and the wind speed in the tunnel(0.5~4.0 m/s) were calculated by CFD simulation. In addition, the wall heat transfer coefficient was computed from the results analysis, and the limit distance used to keep the air temperature in the tunnel stable was examined through the research. The convective heat transfer coefficient at the wall surface shows unstable pattern at the inlet area. However, it converges to a constant value beyond approximately 100 meter. The tunnel wall heat transfer coefficient is $3.1{\sim}9.16W/m^2^{\circ}C$ depending on the wind speed, and following is the dimensionless number:$Nu=1.081Re^{0.4927}({\mu}/{\mu}_w)^{0.14}$. This study has suggested the prediction model of temperature in the tunnel based on the thermal resistance analysis technique, and it is appraised that deviation can be used in the range of 3% estimation.

• Journal of the Korean Geographical Society
• /
• v.43 no.6
• /
• pp.824-842
• /
• 2008

The main objective of the study was to analyze the weather conditions of frost occurrence for protecting crops against frost damage in Korea. The primary data used for the analysis of meteorological characteristics of frost occurrence days are the airmass pattern, minimum temperature, grass minimum temperature, daily temperature range, relative humidity, minimum relative humidity, mean wind speed in autumn and spring. Frost often occurs when the migratory anticyclone passes the southwest of Korea. The importance of grass minimum temperature measurements for agricultural purposes has previously been recognized. The grass minimum thermometer is capable of detecting ground frosts which are often not recorded by the minimum thermometer. The minimum temperature of frost occurrence days is above $0^{\circ}C$ in the coastal area, but the grass minimum temperature of frost occurrence days is below $0^{\circ}C$ in the whole area. The daily temperature of frost occurrence days is about 9 to $12^{\circ}C$ in the coastal area and is over $14^{\circ}C$ in the inland area. The minimum relative humidity of frost occurrence days is about 30 to 50%. The mean wind speed of frost occurrence days is less than 2m/sec.

• Atmosphere
• /
• v.26 no.3
• /
• pp.357-372
• /
• 2016

Northeast Asian regions have recently become the main source of anthropogenic and natural aerosols. Measurement of aerosols on the sea in these regions have been rarely conducted since the experimental campaigns such as ACE-ASIA (Asian Pacific Regional Aerosol Characterization Experiment) in 2001. Research vessel observations of aerosol mass and chemical composition were performed on the Yellow and south sea around the Korean peninsula. The ship measurements showed six representative cases such as aerosol event and non-event cases during the study periods. On non-event cases, the anthropogenic chemical and natural soil composition on the Yellow sea were greater than those on the south sea. On aerosol event cases such as haze, haze with dust, and dust, the measured mass concentrations of anthropogenic chemical and element compositions were clearly changed by the events. In particular, methanesulfonate ($MSA^-$, $CH_3SO_3^-$), a main component of natural oceanic aerosol important for sulfur circulation on Earth, was first observed by the vessel in Korea, and its concentration on the Yellow sea was three times that on the south sea during the study period. Sea salt concentration important to chemical composition on the sea is related to wind speed. Coefficients of determination ($R^2$) between wind speed and sea salt concentration were 0.68 in $PM_{10}$ and 0.82 in $PM_{2.5}$. Maximum wave height was not found to be correlated to the sea salt concentration. When sea-salt comes into contact with pollutants, the total sea-salt mass is reduced, i.e., a loss of $Cl^-$ concentration from NaCl, the main chemical composing sea salt, is estimated by reaction with $HNO_3$(gas) and $H_2SO_4$(gas). The $Cl^-$ concentration loss by $SO_4^{2-}$ and $NO_3^-$ more easily increased for $PM_{10}$ compared to $PM_{2.5}$. The results of this study will be applied to verifying a dust-haze forecasting model. In addition, continued vessel measurements of aerosol data will become important to research for climate change studies in the future.

• Asian Journal of Atmospheric Environment
• /
• v.7 no.4
• /
• pp.191-198
• /
• 2013

Cryptomeria japonica pollen is the most common pollen, which are scattering during each spring season in Japan. Japanese cedar (Cryptomeria japonica) pollinosis is one of seasonal allergic rhinitis that mainly occurs in Japan. In addition, long range transportation of Yellow Sand from the East Asian continent was also found during the pollen scattering seasons in Japan. Therefore, the interaction or impact between pollen and Yellow Sand should be concerned. In this study, our objective was to investigate the airborne behaviour of Cryptomeria japonica pollen grains and its size-segregated allergenic (Cry j 1) particles as the airborne tracer of Cryptomeria japonica pollen during the Yellow Sand events. Airborne Cryptomeria japonica pollen grains and its size-segregated allergenic particles were collected at roadside of urban residential zones of Saitama city during the pollination periods from February to March in two year investigation of 2009 and 2010. The overlap of Yellow Sand events and dispersal peak of pollen grains was observed. According to the Meteorological data, we found that the peaks of airborne pollen grains appeared under higher wind speed and temperature than the previous day. It was thought that Yellow Sand events and airborne pollen counts were related to wind speed. From the investigation of the airborne behavior of the size-segregated allergen particles by determining Cry j 1 with Surface Plasmon Resonance (SPR), the higher concentrations of the allergenic Cry j 1 were detected in particle size equal to or less than $1.1{\mu}m$($PM_{1.1}$) than other particle sizes during Yellow Sand events, especially in the rainy day. We conclude that rainwater trapping Yellow Sand is one of the important factors that affect the release of allergenic pollen species of Cry j 1. Therefore, it is very important to clarify the relationships between Cryptomeria japonica pollen allergenic species and chemical contents of the Yellow Sand particles in further studies.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.9 no.2
• /
• pp.100-108
• /
• 2007

The Gwangneung KoFlux supersite, located in a rugged mountain region, is characterized by a low wind speed due to a mountain-valley circulation and rolling terrain. Therefore, it is essential to understand the effect of coordinate rotation on flux measurements by the eddy-covariance method. In this paper, we review the properties of three orthogonal coordinate frames (i.e., double, triple, and planar fit rotations) and apply to flux data observed at the Gwangneung supersite. The mean offset of vertical wind speed of sonic anemometer was inferred from the planar fit (PF) coordinate rotation, yielding the diurnal variation of about $\pm0.05ms^{-1}$. Double rotation $(\bar{v}=\bar{w}=0)$ produced virtually the same turbulent fluxes of heat, water, and $CO_2$ as those from the PF rotation under windy conditions. The former, however, resulted in large biases under calm conditions. The friction velocity, an important scaling parameter in the atmospheric surface layer, was more sensitive to the choice of coordinate rotation method.