• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.2B
• /
• pp.199-213
• /
• 2008

The goal of this research is to develop and apply the integrational operation method (IOM) for the modeling of the monthly pan evaporation (PE) and the alfalfa reference evapotranspiration ($ET_r$). Since the observed data of the alfalfa $ET_r$ using lysimeter have not been measured for a long time in Republic of Korea, Penman-Monteith (PM) method is used to estimate the observed alfalfa $ET_r$. The IOM consists of the application of the stochastic and neural networks models, respectively. The stochastic model is applied to generate the training dataset for the monthly PE and the alfalfa $ET_r$, and the neural networks models are applied to calculate the observed test dataset reasonably. Among the considered six training patterns, 1,000/PARMA(1,1)/GRNNM-GA training pattern can evaluate the suggested climatic variables very well and also construct the reliable data for the monthly PE and the alfalfa $ET_r$. Uncertainty analysis is used to eliminate the climatic variables of input nodes from 1,000/PARMA(1,1)/GRNNM-GA training pattern. The sensitive and insensitive climatic variables are chosen from the uncertainty analysis of the input nodes. Finally, it can be to model the monthly PE and the alfalfa $ET_r$ simultaneously with the least cost and endeavor using the IOM.

• Journal of Korea Water Resources Association
• /
• v.49 no.2
• /
• pp.165-175
• /
• 2016

In order to examine the applicability, the evaporation estimation approaches based on solar radiation are classified into 3 different model groups (Model groups A, B, and C) in this study. Each group is tested in the 6 study stations (Seoul, Daejeon, Jeonju, Busan, Mokpo, and Jeju). The model parameters of each model group are estimated and verified with measured pan evaporation data. The applicability of verified model groups are compared with results of Penman (1948) combination approach. Nash-Sutcliffe (N-S) efficiency coefficients greater than 0.663 in all study stations indicate satisfactory estimates of evaporation. On the other hand, in the model verification process, N-S efficiency coefficients greater than 0.526 in all study stations indicate also satisfactory estimates of evaporation. However, N-S efficiency coefficients in all study cases except Model groups B and C in Busan are less than those of Penman (1948) combination approach. Therefore, it is concluded in this study that the evaporation estimation approaches based on solar radiation have capability to replace Penman (1948) combination approach for the estimation of evaporation in case that some meteorological data (wind speed, relative humidity) are missing or not measured.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.392-395
• /
• 2017

본 연구에서는 일 증발접시 증발량 산정을 위한 딥러닝 (deep learning) 모형의 적용성을 평가하였다. 본 연구에서 적용된 딥러닝 모형은 deep belief network (DBN) 기반 deep neural network (DNN) (DBN-DNN) 모형이다. 모형 적용성 평가를 위하여 부산 관측소에서 측정된 기상자료를 활용하였으며, 증발량과의 상관성이 높은 기상변수들 (일사량, 일조시간, 평균지상온도, 최대기온)의 조합을 고려하여 입력변수집합 (Set 1, Set 2, Set 3)별 모형을 구축하였다. DBN-DNN 모형의 성능은 통계학적 모형성능 평가지표 (coefficient of efficiency, CE; coefficient of determination, $r^2$; root mean square error, RMSE; mean absolute error, MAE)를 이용하여 평가되었으며, 기존의 두가지 형태의 ANN (artificial neural network), 즉 모형학습 시 SGD (stochastic gradient descent) 및 GD (gradient descent)를 각각 적용한 ANN-SGD 및 ANN-GD 모형과 비교하였다. 효과적인 모형학습을 위하여 각 모형의 초매개변수들은 GA (genetic algorithm)를 이용하여 최적화하였다. 그 결과, Set 1에 대하여 ANN-GD1 모형, Set 2에 대하여 DBN-DNN2 모형, Set 3에 대하여 DBN-DNN3 모형이 가장 우수한 모형 성능을 나타내는 것으로 분석되었다. 비록 비교 모형들 사이의 모형성능이 큰 차이를 보이지는 않았으나, 모든 입력집합에 대하여 DBN-DNN3, DBN-DNN2, ANN-SGD3 순으로 모형 효율성이 우수한 것으로 나타났다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1B
• /
• pp.47-62
• /
• 2009

The climate change caused by global warming may affect on the hydro-meteorologic factor such as evaporation (IPCC, 2001). Furthermore, it is also necessary that the effect of climate change according to geographical condition on evaporation should be studied. In this study, considering geographical and topographical conditions, the 6 evaporation equations that have been applied to simulate annual and monthly pan evaporation were compared. 56 climatologic stations were selected and classified, basing on the geographical and topographical characteristics (urbanization, topographical slope, proximity to coast, and area of water body). The evaporation equations currently being used are applied. These evaporation equations are Penman, Kohler-Nordenson-Fox (KNF), DeBruin-Keijman, Priestley-Taylor, Hargreaves, and Rohwer. Furthermore, Penman equation was modified by calibrating the parameters of wind function and was verified using relative error. The study results indicate that the KNF equation compared best with the pan: relative error was 8.72%. Penman equation provided the next-best values for evaporation relative to the pan: relative error was 8.75%. The mass-transfer method (Rohwer) provided the worst comparison showing relative error of 33.47%. In case that there is a close correlation between wind function and wind speed, modified Penman equation provided a better estimate of pan evaporation.

• Journal of Korea Water Resources Association
• /
• v.40 no.1 s.174
• /
• pp.89-99
• /
• 2007

Uncertainty analysis is used to eliminate the climatic variables of input nodes and construct the model of an optimal type from COMBINE-GRNNM-GA(Type-1), which have been developed in this issue(2007). The input variable which has the lowest smoothing factor during the training performance, is eliminated from the original COMBINE-GRNNM-GA (Type-1). And, the modified COMBINE-GRNNM-GA(Type-1) is retrained to find the new and lowest smoothing factor of the each climatic variable. The input variable which has the lowest smoothing factor, implies the least useful climatic variable for the model output. Furthermore, The sensitive and insensitive climatic variables are chosen from the uncertainty analysis of the input nodes. The optimal COMBINE-GRNNM-GA(Type-1) is developed to estimate and calculate the PE which is missed or ungaged and the $ET_r$ which is not measured with the least cost and endeavor Finally, the PE and $ET_r$. maps can be constructed to give the reference data for drought and irrigation and drainage networks system analysis using the optimal COMBINE-GRNNM-GA(Type-1) in South Korea.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.1B
• /
• pp.29-36
• /
• 2011

Evapotranspiration (ET) from the various surfaces needs to be understood because it is a crucial hydrological factor to grasp interaction between the land surface and the atmosphere. A traditional way of estimating it, which is calculating it empirically using lysimeter and pan evaporation observations, has a limitation that the measurements represent only point values. However, these measurements cannot describe ET because it is easily affected by outer circumstances. Thus, remote sensing technology was applied to estimate spatial distribution of ET. In this study, we estimated major components of energy balance method (i.e. net radiation flux, soil heat flux, sensible heat flux, and latent heat flux) and ET as a map using Mapping Evapo-Transpiration with Internalized Calibration (METRIC) satellite-based image processing model. This model was run using Landsat imagery of Gyeongan watershed in Korea on Feb 1, 2003 and Sep 13, 2006. Basic statistical analyses were also conducted. The estimated mean daily ETs had respectively 22% and 11% of errors with pan evaporation data acquired from the Suwon Weather Station. This result represented similar distribution compared with previous studies and confirmed that the METRIC algorithm had high reliability in the watershed. In addition, ET distribution of each land use type was separately examined. As a result, it was identified that vegetation density had dominant impacts on distribution of ET. Seasonally, ET in a growing season represented significantly higher than in a dormant season due to more active transpiration. The ET maps will be useful to analyze how ET behaves along with the circumstantial conditions; land cover classification, vegetation density, elevation, topography.

• Journal of Korea Water Resources Association
• /
• v.39 no.3 s.164
• /
• pp.261-274
• /
• 2006

This study performs a daily long-term runoff analysis for 30 years to forecast medium- and long-term probabilistic reservoir inflows on the Soyang River basin. Snowmelt is computed by Anderson's temperature index snowmelt model and potenetial evaporation is estimated by Penman-combination method to produce input data for a rainfall-runoff model. A semi-distributed TOPMODEL which is composed of hydrologic rainfall-runoff process on the headwater-catchment scale based on the original TOPMODEL and a hydraulic flow routing model to route the catchment outflows using by kinematic wave scheme is used in this study It can be observed that the time variations of the computed snowmelt and potential evaporation are well agreed with indirect observed data such as maximum snow depth and small pan evaporation. Model parameters are calibrated with low-flow(1979), medium-flow(1999), and high-flow(1990) rainfall-runoff events. In the model evaluation, relative volumetric error and correlation coefficient between observed and computed flows are computed to 5.64% and 0.91, respectively. Also, the relative volumetric errors decrease to 17% and 4% during March and April with or without the snowmelt model. It is concluded that the semi-distributed TOPMODEL has well performance and the snowmelt effects for the long-term runoff computation are important on the study area.

• Journal of Korea Water Resources Association
• /
• v.36 no.2
• /
• pp.195-209
• /
• 2003

Spatial-Stochastic Neural Networks Model(SSNNM) is used to estimate long-term streamflow in the parallel reservoir groups. SSNNM employs two kinds of backpropagation algorithms, based on LMBP and BFGS-QNBP separately. SSNNM has three layers, input, hidden, and output layer, in the structure and network configuration consists of 8-8-2 nodes one by one. Nodes in input layer are composed of streamflow, precipitation, pan evaporation, and temperature with the monthly average values collected from Andong and Imha reservoir. But some temporal differences apparently exist in their time series. For the SSNNM training procedure, the training sets in input layer are generated by the PARMA(1,1) stochastic model and they covers insufficient time series. Generated data series are used to train SSNNM and the model parameters, optimal connection weights and biases, are estimated during training procedure. They are applied to evaluate model validation using observed data sets. In this study, the new approaches give outstanding results by the comparison of statistical analysis and hydrographs in the model validation. SSNNM will help to manage and control water distribution and give basic data to develop long-term coupled operation system in parallel reservoir groups of the Upper Nakdong River.