• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• Horticultural Science & Technology
• /
• v.32 no.3
• /
• pp.340-345
• /
• 2014

Since the moisture content (MC) of growing medium closely related with the crop transpiration, the MC should be included to the environmental factors to be considered for irrigation control in soilless culture. The objective of this study was to analyze the transpiration of paprika plants using daily mean solar radiation (RAD) and vapor pressure deficit (VPD) as well as the growth of the plants at different MCs of rockwool growing media. The starting points of irrigation were controlled by a moisture sensor with minimum set points of 40%, 50%, and 60% of MCs. The canopy transpirations were measured for 80 to 120 days after transplanting and analyzed. The transpirations were well regressed with a combination of both RAD and VPD rather than daily mean RAD only under the controlled MCs. The transpiration at 60% MC was higher than those at 50% and 40% MCs. Leaf area, leaf fresh and dry weights at 60% MC were higher than those at 50% and 40% MCs while the number of leaves had no significant difference among the MCs. There were no significant differences in number of fruits and fruit size among all the MCs, while fruit weight was significantly lower at 40% MC than other treatments. Fresh and dry fruit yields were the highest at 60% MC. Therefore it was concluded that the transpiration was affected by the MC of rockwool growing medium and the minimum set point of 50-60% MC of rockwool growing medium gave better effects on the growth of the paprika plants.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.56 no.3
• /
• pp.75-81
• /
• 2014

Fossil energy is needed for a whole year greenhouse cropping due to climate in South Korea. Because the most of the fossil energy resources is imported, it is necessary to develop technology to be able to reduce the energy cost in order to manage greenhouse profitably. The greenhouse commonly consume less amount of energy as compared to other industrial sectors. Replacement of fossil fuel with solar thermal storage, therefore, can be an economical as well as environmentally sustainable option for greenhouse heating. The fluid flow, heat storage and radiation characteristic of the gravel bed model were analyzed to provide basic data for design of the experimental solar heated greenhouse with underground thermal storage using gravel. The air flow velocity in the gravel storage bed was proven to be affected from the capacity of circulation fan and the circulation method and the positive pressure method was proven to be the best among the different air circulation methods. The initial air temperature of the thermal storage bed of 1.2 m $wide{\times}9$ m $long{\times}0.9$ m deep was $10^{\circ}C$. After the thermal storage bed is heated by air of the mean temperature $4^{\circ}C$ during 9 hours, the temperature has increased about $20.3^{\circ}C$ and the storage of heat was about 33,000 kcal. The important factors should be taken into consideration for design of the solar heated greenhouse with underground thermal storage using gravel are insulation of rock storage, amount of storing heat, inflow rate and direction of inlet and outlet duct.

• Journal of Animal Environmental Science
• /
• v.10 no.3
• /
• pp.141-154
• /
• 2004

The solar powered water pump is very ideal equipment because solar power is more intensive when the water is more needed in summer and it is very helpful in the rural area, in which the electrical power is not available. The average so]ar radiation energy is 3.488 kWh/($m^2{\cdot}day$) in Korea. In this study, the automatic control logic and system of the water pump driven by the radiation energy were studied, designed, assembled, tested and analyzed for realizing the solar powered water pump. The experimental system was operated automatically and the cycle was continued. The average quantity of the water pumped per cycle was about 5,320 cc. The cycle time was about 4.9 minutes. The thermal efficiency of the system was about $0.030\%$. The pressure level of the n-pentane vapour in flash tank was 150$\%$450 hPa(gauge) which was set by the computer program for the control of the vapour supply. The pressure in the condenser and air tank during cycles was maintained as about 600 hPa and 1,200 hPa respectively. The water could be pumped by the amount of 128kg/($m^2{\cdot}day$) with the efficiency of $0.1\%$ and the pumping head of 10 m for the average solar energy in Korea.

• Journal of Bio-Environment Control
• /
• v.23 no.1
• /
• pp.11-18
• /
• 2014

To investigate the influence of surrounding environment on the plant temperature and examine the effect of plant temperature control by fogging and airflow, plant temperature of tomato, inside and outside air temperature and relative humidity, solar radiation and wind speed were measured and analyzed under various experimental conditions in plastic greenhouse with two-fluid fogging systems and air circulation fans. According to the analysis of plant temperature and the change of inside and outside air temperature in each condition, inside air temperature and plant temperature were significantly higher than outside air temperature in the control and shading condition. However, in the fogging condition, inside air temperature was lower or slightly higher than outside air temperature. It showed that plant temperature could be kept with the temperature similar to or lower than inside air temperature in fogging and airflow condition. To derive the relationship between surrounding environmental factor and plant temperature, we did multiple regression analysis. The optimum regression equation for the temperature difference between plant and air included solar radiation, wind speed and vapor pressure deficit and RMS error was $0.8^{\circ}C$. To investigate whether the fogging and airflow contribute to reduce high temperature stress of plant, photosynthetic rate of tomato leaf was measured under the experimental conditions. Photosynthetic rate was the highest when using both fogging and airflow, and then fogging, airflow and lastly the control. So, we could assume that fogging and airflow can make better effect of plant temperature control to reduce high temperature stress of plant which can increase photosynthetic rate. It showed that the temperature difference between plant and air was highly affected by surrounding environment. Also, we could estimate plant temperature by measuring the surrounding environment, and use it for environment control to reduce the high temperature stress of plant. In addition, by using fogging and airflow, we can decrease temperature difference between plant and air, increase photosynthetic rate, and make proper environment for plants. We could conclude that both fogging and airflow are effective to reduce the high temperature stress of plant.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.60 no.3
• /
• pp.15-25
• /
• 2018

Estimating the reference evapotranspiration is an important factor to consider in irrigation system design and agricultural water use. However, there is a limitation in using the FAO Penman-Monteith (FAO P-M) equation, which requires various meteorological data. The purpose of this study is to compare three reference evapotranspiration (ETo) equations in the case of meteorological data missing for 11 study weather stations. Firstly, the FAO P-M equation is used for reference potential evapotranspiration estimation with the actual solar radiation data $R_n$ and the actual vapor pressure $e_a$. Then, in the case of $R_n$, and $e_a$ are missed, the reference evapotranspirations applying FAO P-M, Priestley-Taylor (P-T), Hargreaves (HG) equation were calculated using other meteorological factors. Secondly, MAE, RMSE, $R^2$ were calculated to compare ETo relationship from the ETo equations. From the results, ETo with Hargreaves equation in coastal areas and the Priestley-Taylor equation in the inland areas showed relatively high correlation with FAO P-M when $e_a$ data is missed. In the case of $R_n$ data is missed or two weather data, $e_a$, and $R_n$ data are all missed, $R^2$ value in Priestley-Taylor equation was highest in coastal areas, and $R^2$ values in Hargreaves equation were the high values for 7 inland areas. The results of sensitivity analysis showed that net radiation was the most sensitive for P-T and HG equation, and for FAO P-M, the most sensitive factor was net radiation and relative humidity, air temperature and wind speed were follows. Therefore, in considering of the accessibility to the coast, the types of the missing wether data, and the correlation and the magnitude of error, the reference evapotranspiration equations would be selected in sense of different conditions.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.30 no.6
• /
• pp.974-983
• /
• 1997

The Okhotsk Sea is unique natural object with climatic peculiarities. The climate of the Okhotsk Sea results from the general distribution of solar radiation during a year, and the characteristics of the atmospheric circulation that varies through a year: In cold half year the main pressure formations are Siberian high and Aleutian low. Asian low centered on Afghanistan dominates over the Asian continent in summer. The North-Pacific sea surface is under effect of permanent North Pacific high. The changes in their position from year to year are very significant. The anticyclonic activity over the Far Eastern Seas is one of the main factors for the formation of weather anomalies over the adjacent territories. The analysis of summer weather characteristics over the coast of Okhotsk and East Sea using the data obtained from Hydrometeorological stations during $1949\~1990$ showed that, to a great extent, distribution of the air temperature depends on thermal state of the Okhotsk Sea and atmospheric circulation over it. We show some relations between weather characteristics and the intensity of atmospheric action center for the North Pacific high in summer when its ridge propagates to Okhotsk Sea. Correlation coefficients between air pressure over the Okhotsk Sea and air temperature for the coastal areas reach up to 0.7. Analysis of the spatial-temporal distribution of main meteorological values over the Okhotsk Sea such as air pressure, and air temperature are also performed.

• Journal of Advanced Navigation Technology
• /
• v.16 no.6
• /
• pp.900-909
• /
• 2012

Low Earth orbit satellites with satellite navigation receiver use onboard navigation filters for filtering measurement signals and for orbit prediction under signal loss. Precision satellite dynamic models, core of the navigation filter, are studied and a computation program is developed. Gravity acceleration, precision coordinate transform, third-body gravity, atmospheric drag, and solar radiation pressure models are combined into an orbit prediction algorithm, and a proven precision orbit determination software is used to validate the program. Orbit prediction accuracy is analyzed with simulated and flight orbit data. The program meets an accuracy level for onboard real-time navigation filter.

• Journal of Life Science
• /
• v.19 no.10
• /
• pp.1382-1388
• /
• 2009

Rubus crataegifolius is a shrub species and is primarily distributed throughout Asia and Europe. We collected 550 representative samples of the eleven populations in Korea to estimate leaf variation within species. The 35 morphological characteristics allowed us to resolve well-supported fixed characteristics and variable characteristics. Sixteen of twenty-three quantitative characteristics and five of twelve qualitative characteristics showed significant differences among populations. We argued that the population differentiation can accounted for the variation in phenetic characteristics such as spine in this species, but were less successful in accounting for variation in other traits. Within a polystatistic leaf structure, their morphological differences could be modulated by ecological pressure such as temperature, altitude, duration of sunshine, and solar radiation. The phenogram showed two distinct clades. One was a group in central Korea and the other was a group in the southern regions of Korea. If morphological characteristics in R. crataegifolius populations reflect their ecological niche, morphology should be regarded with caution as the main criterion for population studies in R. crataegifolius.

• International Journal of Computer Science & Network Security
• /
• v.24 no.3
• /
• pp.196-200
• /
• 2024

Weather forecasting is considered to be of utmost important among various important sectors such as flood management and hydro-electricity generation. Although there are various numerical methods for weather forecasting but majority of them are reported to be Mechanistic computationally demanding due to their complexities. Therefore, it is necessary to develop and build models for accurately predicting the weather conditions which are faster as well as efficient in comparison to the prevalent meteorological models. The study has been undertaken to forecast various atmospheric parameters in the city of Bangalore using Naïve Bayes algorithms. The individual parameters analyzed in the study consisted of wind speed (WS), wind direction (WD), relative humidity (RH), solar radiation (SR), black carbon (BC), radiative forcing (RF), air temperature (AT), bar pressure (BP), PM₁₀ and PM_2.5 of the Bangalore city collected from Air Quality Monitoring Station for a period of 5 years from January 2015 to May 2019. The study concluded that Naive Bayes is an easy and efficient classifier that is centered on Bayes theorem, is quite efficient in forecasting the various air pollution parameters of the city of Bangalore.