Number of duck and its breeding facilities have been steadily decreasing for financial and social issues in Korea. Therefore, the ‘turning point’ for duck industry is strongly demanded. In this study, the questionary survey was carried out to provide backgrounds for developing policy and technology for duck breeding farms. The questionary survey aimed to investigate the information of operation strategy of farm, ventilation, cooling and heating. The total number of survey respondents was 74. In case of facility type, 55.4% of respondents stated they used greenhouse type, 31.3% for winch-curtain type, and 2.7% for windowless type (mechanically ventilated facility). More than 85% of the facilities were using ‘natural ventilation’, it meant that these situation can restrict the not only environmental control but also the supply policy for ‘smart farm’ of the Government. 44.6% used the combination of the cross-ventilation method and roof-ventilation method for ventilation operation in summer season, and 31.1% followed only the cross-ventilation method. In case of winter season, 36.5% used the cross-ventilation method, and 33.3% used the combination of cross and roof-ventilation, method. For the ventilation strategy, about 86.5% depended on farmer’s experience. In case of heating and cooling, 79.7% were using kerosene heater for winter season, and 43.2% were using mist-spray for summer season, respectively. More than 75% stated that cooling and heating strategies were based on farmer’s experience. From the analyses of the survey results, a few proposals for developing policy and technology for duck breeding farm was suggested.
Impact of Activation Functions on Flood Forecasting Model Based on Artificial Neural Networks
김지혜 Kim Jihye , 전상민 Jun Sang-min , 황순호 Hwang Soonho , 김학관 Kim Hak-kwan , 허재민 Heo Jaemin , 강문성 Kang Moon-seong
The objective of this study was to analyze the impact of activation functions on flood forecasting model based on Artificial neural networks (ANNs). The traditional activation functions, the sigmoid and tanh functions, were compared with the functions which have been recently recommended for deep neural networks; the ReLU, leaky ReLU, and ELU functions. The flood forecasting model based on ANNs was designed to predict real-time runoff for 1 to 6-h lead time using the rainfall and runoff data of the past nine hours. The statistical measures such as R2, Nash-Sutcliffe Efficiency (NSE), Root Mean Squared Error (RMSE), the error of peak time (ETp), and the error of peak discharge (EQp) were used to evaluate the model accuracy. The tanh and ELU functions were most accurate with R2=0.97 and RMSE=30.1 (m3/s) for 1-h lead time and R2=0.56 and RMSE=124.6∼124.8 (m3/s) for 6-h lead time. We also evaluated the learning speed by using the number of epochs that minimizes errors. The sigmoid function had the slowest learning speed due to the ‘vanishing gradient problem’ and the limited direction of weight update. The learning speed of the ELU function was 1.2 times faster than the tanh function. As a result, the ELU function most effectively improved the accuracy and speed of the ANNs model, so it was determined to be the best activation function for ANNs-based flood forecasting.
Assessing Irrigation Water Supply from Agricultural Reservoir Using Automatic Water Level Data of Irrigation Canal
방재홍 Bang Jehong , 최진용 Choi Jin-yong , 윤푸른 Yoon Pureun , 오창조 Oh Chang-jo , 맹승진 Maeng Seung-jin , 배승종 Bae Seung-jong , 장민원 Jang Min-won , 장태일 Jang Taeil , 박명수 Park Myeong Soo
KRC (Korea Rural Community Corporation) is in charge of about 3,400 agricultural reservoirs out of 17,240 agricultural reservoirs, and automatic water level gauges in reservoirs and canals were installed to collect reservoir and canal water level data from 2010. In this study, 10-minute water level data of 173 reservoir irrigation canals from 2016 to 2018 are collected, and discharge during irrigation season was calculated using rating curves. For estimation of water supply, irrigation water requirement was calculated with HOMWRS (Hydrological Operation Model for Water Resources System), and the summation of reservoir water storage decrease was calculated with daily reservoir storage data from RAWRIS (Rural Agricultural Water Resource Information System). From the results, the total yearly amount of irrigation water supply showed less than 10% difference than the irrigation water requirement. The regional analysis revealed that reservoirs in Jeollanam-do and Chungcheongnam-do supply greater irrigation water than average. On the contrary, reservoirs in Gyeongsangnam-do and Chungcheongbuk-do supply less than others. This study was conducted with a limited number of reservoirs compared to total agricultural reservoirs. Nevertheless, it can indicate irrigation water supply from agricultural reservoirs to provide information about agricultural water use for irrigation.
Development and Field-evaluation of Automatic Spreader for Bedding Materials in Duck Houses
권경석 Kwon Kyeong-seok , 우제석 Woo Jae-seok , 노재희 Noh Je-hee , 오상익 Oh Sang-ik , 김종복 Kim Jong-bok , 김중곤 Kim Jung-kon , 양가영 Yang Kayoung , 장동화 Jang Donghwa , 최성민 Choi Sungmin
The automatic-spreader of bedding materials was developed to reduce labor cost, and to achieve successful biosecurity in duck houses. Algorithm of the device was designed to realize a concept of the automatic unmanned operation including entire processes such as loading and spreading of the bedding materials. From the field measurement, the relationship between the expected water content reduction and weight of bedding materials per unit area according to the operation condition of the devices was induced. In the case of the measurement of particulate matters during the process of spreading works, the results of using both conventional manual-spreader and automatic-spreader were exceeded the allowable limit of inhalable and respirable dust, respectively. But, workers using automatic-spreader could be free from harmful aero-condition because they did not stay inside the facility during the spreading works. In addition, from the Duck hepatitis virus PCR test, influence on pulmonary tissue of the duck was not found. It could be expected that the development of the automatic-spreader of bedding materials for duck house can contribute to the advancement of duck breeding facilities.
An Analysis of How Rural Experience Influence on Rural Perception Changing and Migration Settlement
This paper analyzes causal relationship between rural experience and settlement. Structural Equation Modeling is the combination of factor analysis and multiple regression analysis which can explain causal relation between factors. Rural perception factor has conceptualized positive sector (attitude, values) and negative sector (perceived risk, sentiment). Statistically significant causality results are as follows. People think about migration into rural when they have high level of attitude about rural but fear of rural life make avoid migration into rural. When people have fear of rural life, they also have bad feeling about rural infrastructure and facility. Attitude of rural, values of rural and low fear of rural life gives positive influence to satisfaction. Satisfaction gives positive influence to migration into rural.
An Analysis of the Water Quality Improvement Measures and Evaluation of Wonju Stream
금동혁 Kum Donghyuk , 신민환 Shin Minhwan , 유나영 Yu Nayeong , 이서로 Lee Seolo , 김동진 Kim Dongjin , 성윤수 Sung Younsoo , 이상수 Lee Sang Soo
Recently, the deterioration of water quality in Wonju stream has been reported due to the increase in diverse pollution sources along with community development and urbanization. Various types of attempts with a huge budget were made for better water quality so far, but its effectiveness is still doubted. In order to establish site-oriented measures for water quality improvement, the topographic and hydrologic factors were evaluated based on site inspection and survey. As the major streams merged into the Wonju stream, the Hwa and Heungyang streams were found to have higher pollution loads and contributions compared to other streams due to the scattered livestock farms and industries, and vulnerable land use. Notably, the discharge water from the Wonju Public Sewage Treatment Plant had the highest level of pollution load, impacting on the water quality of Wonju Stream. According to the SWAT model as water quality measures, the improvement effect of water quality in this treatment plant can be reached to the reductions in BOD 11.06%, T-N 23.56%, T-P 10.60% when the proper managements applied, whereas the improvement of water quality would be 3.89%, 1.23%, and 3.32% for BOD, T-N, T-P, respectively, for the industries. The reduction of the livestock industry was generally very high as a pollution source, but it was not much higher at the end of Wonju Stream than other measures. These results recommended that the w ater q uality improvement measures should be designated for each upper-middle-lower section in Wonju stream.
Investigation and Analysis of Particulate-matters and Ammonia Concentrations in Mechanically Ventilated Broiler House According to Seasonal Change, Measurement Locations and Age of Broilers
장동화 Jang Dong-hwa , 권경석 Kwon Kyeong-seok , 김종복 Kim Jong-bok , 김중곤 Kim Jung-kon , 양가영 Yang Ka-young , 최성민 Choi Sung-min , 장유나 Jang Yuna
Investigation and Analysis of Particulate-matters and Ammonia Concentrations in Mechanically Ventilated Broiler House According to Seasonal Change, Measurement Locations and Age of Broilers
장동화 Jang Dong-hwa , 권경석 Kwon Kyeong-seok , 김종복 Kim Jong-bok , 김중곤 Kim Jung-kon , 양가영 Yang Ka-young , 최성민 Choi Sung-min , 장유나 Jang Yuna
Air quality related to particulate matters and ammonia is being come to the fore as the national concern in Korea. CAPSS (Clean Air Policy Support System) provides emission coefficients of these kinds of particulate and gaseous matters in the fields of livestock; however reliability issues are consistently mentioned. Evaluation of emission rates of PM2.5 and NH3 of the country is very important, but only few studies are available as the background related to observation of the concentration of the particulate matter and ammonia, especially within livestock house in Korea. In this paper, long-term measurement of PM10, PM2.5, and ammonia within the mechanically ventilated broiler house were carried out to introduce backgrounds of generation and emission of the particulate matters and ammonia. Measurement results were analyzed according to seasonal changes, age of broilers(weeks) and measurement locations. Concentration of inhalable and respirable dust were also evaluated in terms of occupational respiratory health according to increase in broiler’s activity. From the results of this study, identification of the generation mechanisms of the particulate and gaseous matters, and evaluation of the emission rate of these in the broiler house will be carried out.
Analysis of Organic Matter and Nutrient Leaching Characteristics of Agricultural Land Soils in Reservoir Area
Soils in agricultural lands contain large amount of organic matter and nutrients due to the injected fertilizers and manure. During heavy rain, surface water and base runoff pollutants flows into a nearby stream or lake with eroded soil from agricultural lands. On the other hands, agricultural lands near the lake are inundated due to the increase of the water level in the lake, leading to organic matter and nutrient release from the inundated soil. In this study, releasing rates of nutrient salts and organic substances were analyzed for the soil in the agricultural land, where cultivation activities has been carried out and periodically flooded, to account for the possibility of contamination from the inundated agricultural land in reservoir areas The experiment results have shown that COD was released from the soil in anaerobic conditions, and T-P was released in both anaerobic and aerobic conditions. However, in the case of T-N, it was found that the runoff by soil was not made before the rainfall occurred, and when the soil was impound due to rainfall, the elution occurred under the aerobic conditions. Through the results of this study, it was possible to account for the effect of flooded agricultural lands on the water quality in the lake, and this could be reflected in an efficient agricultural non-point pollution management policy. In order to determine the precise releasing rate for each agricultural land, it is believed that the leaching experiment for paddy fields and grasslands are needed.
Comparison of Artificial Neural Network Model Capability for Runoff Estimation about Activation Functions
김마가 Kim Maga , 최진용 Choi Jin-yong , 방재홍 Bang Jehong , 윤푸른 Yoon Pureun , 김귀훈 Kim Kwihoon
Analysis of runoff is substantial for effective water management in the watershed. Runoff occurs by reaction of a watershed to the rainfall and has non-linearity and uncertainty due to the complex relation of weather and watershed factors. ANN (Artificial Neural Network), which learns from the data, is one of the machine learning technique known as a proper model to interpret non-linear data. The performance of ANN is affected by the ANN’s structure, the number of hidden layer nodes, learning rate, and activation function. Especially, the activation function has a role to deliver the information entered and decides the way of making output. Therefore, It is important to apply appropriate activation functions according to the problem to solve. In this paper, ANN models were constructed to estimate runoff with different activation functions and each model was compared and evaluated. Sigmoid, Hyperbolic tangent, ReLU (Rectified Linear Unit), ELU (Exponential Linear Unit) functions were applied to the hidden layer, and Identity, ReLU, Softplus functions applied to the output layer. The statistical parameters including coefficient of determination, NSE (Nash and Sutcliffe Efficiency), NSEln (modified NSE), and PBIAS (Percent BIAS) were utilized to evaluate the ANN models. From the result, applications of Hyperbolic tangent function and ELU function to the hidden layer and Identity function to the output layer show competent performance rather than other functions which demonstrated the function selection in the ANN structure can affect the performance of ANN.
