In Korea, attention is being paid to the use of renewable energy in the livestock industry, and Ground Source Heat Pump (GSHP), which is advantageous for temperature control, is considered as one of the ways to reduce the use of fossil fuels. But GSHP is expensive to install, which proper capacity calculation is required. GSHP capacity is related to its maximum energy load. Energy loads are affected by climate characteristics and time, so dynamic analysis is required. In this study, the optimal capacity of GSHP was calculated by calculating the heating and cooling load of pig farms using BES (Building Energy Simulation) and economic analysis was performed. After designing the inside of the pig house using TRNSYS, one of the commercial programs of the BES technique, the energy load was calculated based on meteorological data. Through the calculated energy load, three heating devices and GSHP used in pig farms were analyzed for economic feasibility. As a result, GSHP’s total cost of ownership was the cheapest, but the installation cost was the highest. In order to reduce the initial cost of GSHP, the capacity of GSHP was divided, and a scenario was created in which some of it was used as an auxiliary heating device, and economic analysis was conducted. In this study, a method to calculate the proper capacity of GSHP through dynamic energy analysis was proposed, and it can be used as data necessary to expand the spread of GSHP.
Development of 3D Crop Segmentation Model in Open-field Based on Supervised Machine Learning Algorithm
정영준 Jeong Young-joon , 이종혁 Lee Jong-hyuk , 이상익 Lee Sang-ik , 오부영 Oh Bu-yeong , Ahmed Fawzy , 서병훈 Seo Byung-hun , 김동수 Kim Dong-su , 서예진 Seo Ye-jin , 최원 Choi Won
Development of 3D Crop Segmentation Model in Open-field Based on Supervised Machine Learning Algorithm
정영준 Jeong Young-joon , 이종혁 Lee Jong-hyuk , 이상익 Lee Sang-ik , 오부영 Oh Bu-yeong , Ahmed Fawzy , 서병훈 Seo Byung-hun , 김동수 Kim Dong-su , 서예진 Seo Ye-jin , 최원 Choi Won
3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important dataset for various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manual way is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV images and developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models using different data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN (K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value, using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our model performance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach, while it also classified actual non-crop points (e.g. weeds) as crops.
Simplified Analysis of Agricultural Water Network Model Using SWMM - A Case Study of Mandae Reservoir -
안성수 An Sung-soo , 방나경 Bang Na-kyoung , 이종서 Lee Jong-seo , 방성수 Bang Sung-soo , 남원호 Nam Won-ho , 김한중 Kim Han-joong
This study established a water supply network based on the operation case of Mandae Reservoir in Yanggu-gun, Gangwon-do, to analyze the efficient distribution and management of agricultural water supplied from the reservoir to irrigation areas using the hydraulic analysis model SWMM. In order to construct a model to analyze the water canal network, network conditions needs to be simplified, and in particular, excessive detail or simplification of the irrigation area can lead to errors in the analysis results. Therefore, the effect of the water canal network model was analyzed by simulating the appropriate simplification process step by step. The results of simplifying the actual block shape of the analysis target area using SWMM showed that there was no significant difference in the results even if 7 lots were simplified to 2. Also, it was found that the construction and analysis of a simplified network model were reliable when the excess quantity was 2% or more compared to the required quantity for each case of analysis of the paddy field.
Estimation of Optimal Training Period for the Deep-Learning LSTM Model to Forecast CMIP5-based Streamflow
천범석 Chun Beom-Seok , 이태화 Lee Tae-hwa , 김상우 Kim Sang-woo , 임경재 Lim Kyoung-jae , 정영훈 Jung Young-hun , 도종원 Do Jong-won , 신용철 Shin Yong-chul
In this study, we suggested the optimal training period for predicting the streamflow using the LSTM (Long Short-Term Memory) model based on the deep learning and CMIP5 (The fifth phase of the Couple Model Intercomparison Project) future climate scenarios. To validate the model performance of LSTM, the Jinan-gun (Seongsan-ri) site was selected in this study. We comfirmed that the LSTM-based streamflow was highly comparable to the measurements during the calibration (2000 to 2002/2014 to 2015) and validation (2003 to 2005/2016 to 2017) periods. Additionally, we compared the LSTM-based streamflow to the SWAT-based output during the calibration (2000∼2015) and validation (2016∼2019) periods. The results supported that the LSTM model also performed well in simulating streamflow during the long-term period, although small uncertainties exist. Then the SWAT-based daily streamflow was forecasted using the CMIP5 climate scenario forcing data in 2011∼2100. We tested and determined the optimal training period for the LSTM model by comparing the LSTM-/SWAT-based streamflow with various scenarios. Note that the SWAT-based streamflow values were assumed as the observation because of no measurements in future (2011∼2100). Our results showed that the LSTM-based streamflow was similar to the SWAT-based streamflow when the training data over the 30 years were used. These findings indicated that training periods more than 30 years were required to obtain LSTM-based reliable streamflow forecasts using climate change scenarios.
Classification of Summer Paddy and Winter Cropping Fields Using Sentinel-2 Images
홍주표 Hong Joo-pyo , 장성주 Jang Seong-ju , 박진석 Park Jin-seok , 신형진 Shin Hyung-jin , 송인홍 Song In-hong
Up-to-date statistics of crop cultivation status is essential for farm land management planning and the advancement in remote sensing technology allows for rapid update of farming information. The objective of this study was to develop a classification model of rice paddy or winter crop fields based on NDWI, NDVI, and HSV indices using Sentinel-2 satellite images. The 18 locations in central Korea were selected as target areas and photographed once for each during summer and winter with a eBee drone to identify ground truth crop cultivation. The NDWI was used to classify summer paddy fields, while the NDVI and HSV were used and compared in identification of winter crop cultivation areas. The summer paddy field classification with the criteria of -0.195
Characteristics of Non-point Pollution Runoff in Mandae, Gaa, and Jaun Districts and Evaluation of Reduction Projects
Due to muddy water from the highland fields upstream of Soyangho Lake, the Mandae, Gaa, and Jawoon have been redesignated as NPS management areas. This study aims to evaluate the adequacy and supplementation points of the implementation plan by analyzing the operation status of muddy water generation and reduction facilities through on-site investigations by NPS management area to achieve the effective nonpoint pollution reduction goal in the implementation of the implementation plan established in 2020. The SS load calculated based on the survey results from July to October 2019 from 2017 showed a decreasen in 2019 compared to 2017. Both and the Jawoon were analyzed to have decreased. However, the amount of precipitation also decreased by about 27%, so it was judged that the effect of the reduction project was not significant. As a result of the detailed investigation of abatement facilities, about 86% of the 793 facilities installed in the management area were evaluated as ‘good’. As a result of a detailed investigation by subwatersheds, subwatersheds 105 and 106 in the Mandae were analyzed as apprehensive subwatersheds. appeared to fall. In addition, it was analyzed that the effect of reducing muddy water in the Mandae district was insufficient due to the high ratio of leased farmers, lack of efforts to reduce turbid water in leased farmland, conversion to annual crops, and neglect of bare land. In the case of Gaa district, although the abatement facilities are concentrated in the upstream, muddy water was also found to be severe.
A Study on Soil Moisture Estimates Performance Using Various Land Surface Models
장예근 Jang Ye-geun , 신승훈 Sin Seoung-hun , 이태화 Lee Tae-hwa , 장원석 Jang Won-seok , 신용철 Shin Yong-chul , 장근창 Jang Keun-chang , 천정화 Chun Jung-hwa , 김종건 Kim Jong-gun
A Study on Soil Moisture Estimates Performance Using Various Land Surface Models
장예근 Jang Ye-geun , 신승훈 Sin Seoung-hun , 이태화 Lee Tae-hwa , 장원석 Jang Won-seok , 신용철 Shin Yong-chul , 장근창 Jang Keun-chang , 천정화 Chun Jung-hwa , 김종건 Kim Jong-gun
Soil moisture is significantly related to crop growth and plays an important role in irrigation management. To predict soil moisture, various process-based model has been developed and used in the world. Various models (Land surface model) may have different performance depending on the model parameters and structures that causes the different model output for the same modeling condition. In this study, the three land surface models (Noah Land Surface Model, Soil Water Atmosphere Plant, Community Land Model) were used to compare the model performance (soil moisture prediction) and develop the multi-model simulation. At first, the genetic algorithm was used to estimate the optimal soil parameters for each model, and the parameters were used to predict soil moisture in the study area. Then, we used the multi-model approach based on Bayesian model averaging (BMA). The results derived from this approach showed a better match to the measurements than the results from the original single land surface model. In addition, identifying the strengths and weaknesses of the single model and utilizing multi-model methods can help to increase the accuracy of soil moisture prediction.
Evaluation of Shear Strength at Interface Between Geotextile and Cementitious Binder Materials
Multi-layered geotextile tubes may have problems on its stability when used as cofferdam. This study presents the shear strength characteristics at the interface between geotextiles and a cementitious binder material to improve the stability of the multi-layered geotextile tubes. In this study, two different types of geotextiles are used. After mixing with a rapid setting cement, fly ash, sand, accelerator, and water, the cementitious binder material is prepared at the interface between two geotextile samples and cured under water for a desired period. The specimen is placed on upper and lower direct shear boxes by using clamping systems. A series of direct shear tests for two different geotextiles are performed along the curing time under three vertical stresses. Experimental results show that the shear strength at the interface between the cementitious binder material and geotextiles is greater than that at the interface between two geotextiles. For two types of geotextiles, apparent cohesion occurs at the interface between the cementitious binder material and geotextiles. In addition, the friction angles for any curing time are improved, compared to the interface between two geotextiles. The cementitious binder material suggested for the interface between two geotextiles may be useful for the reinforcement of multi-layered geotextile tubes.
Investigation on Generation and Emission of Particulate Matters and Ammonia from Mechanically-ventilated Layer House
장동화 Jang Dong-hwa , 양가영 Yang Ka-young , 권경석 Kwon Kyeong-seok , 김종복 Kim Jong-bok , 하태환 Ha Tae-hwan
In this study, the generation and emission characteristics of particulate matter and gaseous matter in a mechanically ventilated layer house were evaluated. Each concentration of PM10, PM2.5, inhalable dust, respirable dust, and NH3 was measured and compared with occupational limit considering seasons and respiratory disorder. CAPPS (Clean Air Policy Support System) of the Ministry of Environment proposes the emission factors of PM10, PM2.5, and NH3 for a layer houses however, emission factors are still calculated from foreign factors such as CONINAIR values. As a result, it is urgent to develop national emission factors for domestic layer house. Emission coefficients of the studied mechanically-ventilated layer house in a summer season were calculated as 0.052 kg/head/year for PM10, about 12% lower than that of CAPSS, and 0.0068±0.0038 kg/head/year for PM2.5, showing no significant difference. Emission factor of NH3 was calculated as 0.159±0.031 kg/head/year, about 51% lower than that of CAPSS.
