• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.2
• /
• pp.78-82
• /
• 2022

Phenology determines the timing of crop development, and the timing of phenological events is strongly influenced by the temperature during the growing season. In process-based model, leaf area is simulated dynamically by coupling of morphology and phenology module. Therefore, the prediction of leaf appearance rate and final leaf number affects the performance of whole crop model. The dataset for the model equation was collected from SPA R chambers with five different temperature treatments. Beta distribution function (proposed by Yan and Hunt (1999)) was used for describing the leaf appearance rate as a function of temperature. The optimum temperature and the critical value were estimated to be 26.0℃ and 35.3℃, respectively. For evaluation of the model, the accumulated number of onion leaves observed in a temperature gradient chamber was compared with model estimates. The model estimate is the result of accumulating the daily increase in the number of onion leaves obtained by inputting the daily mean temperature during the growing season into the temperature model. In this study, the coefficient of determination (R²) and RMSE value of the model were 0.95 and 0.89, respectively.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.247-247
• /
• 2012

기후변화로 나타나게 될 댐 저수지의 수질 및 생태환경 변화에 대한 분석은 국가 수자원관리 측면에서 우선적으로 대비해야할 중요한 문제로써, 수자원을 안정적이고 효과적으로 관리 및 활용하기 위해서 기후변화로 인한 댐 저수지의 수환경 변화의 정확한 분석과 취약성 평가가 필수적이다. 이러한 기후변화로 인한 신뢰성 있는 영향평가를 위해서는 기후변화시나리오 분석, 댐 유역의 오염물질 유출을 시 공간적으로 해석할 수 있는 유역 모델과 댐저수지로 유입된 이후 오염물질 거동 분석을 위한 저수지 모델이 필요하며, 특히 다양한 기후변화 시나리오하에서의 미래 전망과 발생가능한 취약성을 예측 및 평가하는 기술을 필요로 한다. 본 연구에서는 총 7개의 다목적댐 유역과 저수지에 대하여 기후변화로 인한 신뢰성이 있는 영향평가를 위해서 기후변화 시나리오의 상세화를 통한 상세지역의 기후예측, 댐 유역 모형에서의 유출, 토사 및 오염물질예측과 저수지모형을 통한 미래의 저수지내 오염/영양물질순환 및 분포예측을 통해 기후변화에 의한 다목적댐 취약성을 평가하고자 한다. 총 7개의 다목적댐 유역의 기후변화 시나리오 적용에 따른 유출변화 및 하천수질 전망을 위해 인공신경망 방법에 의해 상세화된 기후자료를 검보정된 SWAT 모형에 적용하였다. 이때, 기준년에 해당하는 Baseline 기간은 인공신경망 학습기간(1990-2010)과 동일하게 모의하였으며, 미래 분석기간 역시 마찬가지로 2011-2040, 2041-2070, 2071-2100의 3개 기간으로 구분하였다. 또한, 미래 전망결과에 대한 분석은 각 30년 일별 모의결과에 대한 월 평균, 계절 평균으로 분석하였다. 유출변화 전망은 댐유역별 월별 총유입량 변화와 함께 유황분석을 통해 미래 댐유입량에 대한 규모 및 변동성 분석을 실시하였으며, 하천수질 변화 전망을 위해 호소유입 하천의 Sediment, TN, TP 월별 오염부하량 변화 분석을 실시하였다. 또한 댐유입 총량에 대한 변동성을 분석한 후, 저수지수질모델의 입력경계조건에 해당하는 각 댐저수지 유입 하천의 미래 유출량 및 수질농도 변화를 분석하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.197-207
• /
• 2018

SMEs manufacturing Factory, which are small-scale production systems of various types, mass-produce and sell products in order to meet customer needs. This means that the company has an excessive amount of material supply to reduce the loss due to lack of inventory and high inventory maintenance cost. And the products that fail to respond to the demand are piled up in the management warehouse, which is the reality that the storage cost is incurred. To overcome this problem, this paper uses ARIMA model, a time series analysis technique, to predict demand in terms of seasonal factors. In this way, demand forecasting model based on economic order quantity model was developed to prevent stock shortage risk. Simulation is carried out to evaluate the effectiveness of the development model and to demonstrate the effectiveness of the development model as applied to SMEs in the future.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.350-350
• /
• 2022

R은 통계 및 빅데이터 분석에 널리 사용되는 오픈 소스 프로그래밍 언어로, 통계와 그래픽스에 관련된 기능을 확정할 수 있어 다양한 분야에 활용되고 있다. 특히, 수자원 분야의 연구에서 그 활용이 늘어나고 있으며, 최근 들어 다양한 수자원 관련 R 패키지가 발표되고 있다. 이중, 미국 지질조사국(U.S. Geological Survey, USGS)이 개발한 EGRET은 수질 및 유출량 자료의 장기 추세 변화 분석을 위한 패키지로 R 프로그래밍 언어를 기반으로 구동되며, 분석·처리한 데이터에 대하여 광범위한 그래픽 프리젠테이션을 제공하여 탐색적 자료 분석에 매우 효과적인 도구이다. 특히, EGRET 패키지는 농도와 유출 사이의 관계 특성, 수집된 자료의 계절성 존재 및 특성, 점진적 또는 급격한 경향의 존재를 검토할 수 있는 그래픽 결과를 제시하며, 가중 회귀(Weighted Regressions on Time, Discharge, and Season, 이하 WRTDS) 모델을 적용하여 농도와 부하의 상태와 경향을 특성화한다. 시간, 유량 및 계절에 대한 WRTDS 모델은 농도 및 부하의 상태와 경향을 특성화하는 데 사용할 수 있는 수질 데이터 세트의 분석 방법으로, 근본적으로 탐색적 데이터 분석 방법으로 다양한 유형의 트렌드 시나리오에 민감하도록 설계되었으며 선형 또는 2차 함수형에 맞지 않을 수 있는 시간적 추세를 탐지하여 설명할 수 있고, 불규칙한 간격의 자료를 사용하기에 적합한 장점이 있다. 본 연구에서는 북한강 상류의 지속적인 흙탕물 발생으로 문제가 되고 있는 자운지구의 자운천을 대상으로 흙탕물 발생 현황을 분석하기 R을 이용하여 탐색적 자료 분석을 실시하였다. 자료 분석은 EGRET 패키지를 사용하여 수집된 자료(2016년 4월 - 2021년 7월까지 수집된 191개의 SS 자료와 인근 유량측정망의 유량자료)의 유량과 SS 농도 간의 관계, 시간에 따른 SS 농도 분포, SS 농도의 월별 특성 분석 및 유황별 SS 농도 변화 등을 검토하였으며, WRTDS 모델로 SS와 부하량을 예측하고 검토하여 자운천 유역의 흙탕물 부하 특성을 검토하였다.

• Journal of Korea Water Resources Association
• /
• v.53 no.4
• /
• pp.273-283
• /
• 2020

Quantitative forecasting of groundwater levels for the assessment of groundwater variation and vulnerability is very important. To achieve this purpose, various time series analysis and machine learning techniques have been used. In this study, we developed a prediction model based on LSTM (Long short term memory), one of the artificial neural network (ANN) algorithms, for predicting the daily groundwater level of 11 groundwater wells in Hankyung-myeon, Jeju Island. In general, the groundwater level in Jeju Island is highly autocorrelated with tides and reflected the effects of precipitation. In order to construct an input and output variables based on the characteristics of addressing data, the precipitation data of the corresponding period was added to the groundwater level data. The LSTM neural network was trained using the initial 365-day data showing the four seasons and the remaining data were used for verification to evaluate the fitness of the predictive model. The model was developed using Keras, a Python-based deep learning framework, and the NVIDIA CUDA architecture was implemented to enhance the learning speed. As a result of learning and verifying the groundwater level variation using the LSTM neural network, the coefficient of determination (R²) was 0.98 on average, indicating that the predictive model developed was very accurate.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.2 no.2
• /
• pp.69-78
• /
• 1999

In this paper, a neural network approach to forecast Korean regional precipitation is presented. We first analyze the characteristics of the conventional models for time series prediction, and then propose a new model and its learning method for the precipitation forecast. The proposed model is a layered network in which the outputs of a layer are buffered within a given period time and then fed fully connected to the upper layer. This study adopted the dual connections between two layers for the model. The network behavior and learning algorithm for the model are also described. The dual connection structure plays the role of the bias of the ordinary Multi-Layer Perceptron(MLP), and reflects the relationships among the features effectively. From these advantageous features, the model provides the learning efficiency in comparison with the FIR network, which is the most popular model for time series prediction. We have applied the model to the monthly and seasonal forecast of precipitation. The precipitation data and SST(Sea Surface Temperature) data for several decades are used as the learning pattern for the neural network predictor. The experimental results have shown the validity of the proposed model.

• Journal of Korea Water Resources Association
• /
• v.52 no.12
• /
• pp.1075-1086
• /
• 2019

Recently, as the incidence of climate warming and abnormal climate increases, the forecasting of hydrological factors such as precipitation and river flow is getting more complicated, and the risk of water shortage is also increasing. Therefore, this study aims to develop a model for predicting the amount of water intake in mid-term. To this end, the correlation between water intake and meteorological factors, including temperature and precipitation, was used to select input factors. In addition, the amount of water intake increased with time series and seasonal characteristics were clearly shown. Thus, the preprocessing process was performed using the time series decomposition method, and the support vector machine (SVM) was applied to the residual to develop the river intake prediction model. This model has an error of 4.1% on average, which is higher accuracy than the SVM model without preprocessing. In particular, this model has an advantage in mid-term prediction for one to two months. It is expected that the water intake forecasting model developed in this study is useful to be applied for water allocation computation in the permission of river water use, water quality management, and drought measurement for sustainable and efficient management of water resources.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2000.10a
• /
• pp.159-164
• /
• 2000

In order to clarify the seasonal variation of residual current and material transportation process in Hiroshima Bay, JAPAN, the real-time simulation of residual current and particle tracking by using Euler-Lagrange model were carried out. The calculated tidal current and water temperature and salinity showed good agreement with the observed ones. The residual currents showed the southward flow pattern at the upper layer, and the northward flow pattern at the lower layer. The flow structure of residual current in Hiroshima Bay is an estuarine circulation affected by density flow and wind driven current. The residual current plays an improtant role of material transportation in th bay.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.641-644
• /
• 2015

우리나라는 지난 40년간 급속한 경제 성장의 과정에서 에너지 소비가 급증하고 있으며, 이로 인해 온실가스 배출량은 1990년~2005년 사이 두 배 이상 증가하였고, 이는 OECD 국가 중 가장 높은 증가율이다. 2차 오염물질인 오존은 1990년부터 2012년까지 연평균 3% 상승하고 있으며, 반복 노출 시 폐에 피해를 줄 수 있는 오염 물질로 예방 대책이 필요하다. 이를 위해 본 논문에서는 계절성 특성을 지닌 오존농도 시계열 데이터를 바탕으로 SARIMA 모형을 활용하여 예측 모형을 구축 하였다.

• Journal of Korean Society of Environmental Engineers
• /
• v.27 no.8
• /
• pp.813-821
• /
• 2005

This paper presents a modeling study of thermal dynamics and turbid current in the Obong Lake, Kangreung. The lake formed by the artificial dam in 1983 for agricultural water supply, is currently under consideration of reconstruction in order to expand the volume of reservoir for water supply and flood control in downstream area. The US Army Corps of Engineers' CE-QUAL-W2, a two-dimensional laterally averaged hydrodynamic and water quality model, was applied to the lake after reconstruction as well as the present lake. The model calibration and verification were conducted against surface water levels and temperature of the lake measured during the years of 2001 and 2003. The model results showed a good agreement with fold measurements both in calibration and verification. Utilizing the validated model, an impact of dam reconstruction on vertical temperature and hydrodynamics were predicted. The model results showed that steep temperature gradient between epilimnion and hypolimnion would be formed during summer, along with extension of cold deep water after reconstruction. During winter and spring seasons, however, the vertical temperature profiles was predicted to be quite similar both before and after reconstruction. This results indicated that thermal stratification would become stronger during summer and stay longer after dam reconstruction. From the examination of predicted water movements, it was noticed that the upstream turbid current would infiltrate into the interface between metalimnion and hypolimnion and then suspended solids would slowly settle down to the bottom before reconstruction. After reconstruction, however, it was shown that the upstream turbid current would stay longer in metalimnion with similar density due to strong stratification. The model also predicted that dam reconstruction would make suspended solids near the dam location significantly decrease.