• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.295-295
• /
• 2021

수자원 관리 및 계획 수립에 있어 강우 유출 분석은 가장 중요하며, 기본적인 분석이다. 기존의 강우 유출 분석은 일반적으로 수문 모형을 이용한다. 강우 유출 분석은 강수와 증발산 과정, 즉 물순환에 있어 복잡한 상호 작용을 고려해야한다. 본 연구에서는 기존의 수문 모형과 데이터간의 관계를 포착할 수 있는 딥러닝 기법을 이용한 강우 유출분석 수행하였다. 우리나라의 유역 중, 비교적 풍부한 수문데이터를 보유하고 있는 IHP (International Hydrological Program)의 청미천 유역을 연구대상지역으로 연구를 수행하였다. 수문 모형으로는 SWAT (Soil and Water Assessment Tool)을 이용하였으며, 딥러닝 기법은 시계열 분석에 있어 주로 사용되는 RNN(Recurrent Neural Network) 중 LSTM (Long Short-Term Memory) 네트워크를 이용하였다. 분석결과 수문 모형의 성능 지표인 상관계수와 NSE (Nash-Sutcliffe Efficiency)는 LSTM 네트워크에서 더 높은 성능을 확인 할 수 있었다. 일반적으로 LSTM 네트워크는 보정 기간이 길수록 더욱 좋은 성능을 나타낸다. 즉, 과거 수문데이터가 충분히 확보된 유역에서 LSTM 네트워크와 같은 데이터 기반 모델은 다양한 지형 및 기상데이터를 필요하는 수문 모델보다 유용할 것이라 사료된다.

• Journal of Korea Water Resources Association
• /
• v.52 no.12
• /
• pp.1033-1046
• /
• 2019

To evaluate the utilization suitability of solar radiation models, estimated solar radiation from 13 solar radiation models were verified by comparing with measured solar radiation at 5 study stations in South Korea. Furthermore, for the evaluation of evaporation estimates according to solar radiation models, 5 different evaporation estimation equations based on Penman's combination approach were applied, and evaporation estimates were compared with pan evaporation. Some solar radiation models require only meteorological data; however, some other models require not only meteorological data but also geographical data such as elevation. The study results showed that solar radiation model based on the ratio of the duration of sunshine to the possible duration of sunshine, maximum temperature, and minimum temperature provided the estimated solar radiation that most closely match measured solar radiation. Accuracy of estimated solar radiation also greatly improved when Angstrőm-Prescott model coefficients are adjusted to the study stations. Therefore, when choosing the solar radiation model for evaporation estimation, both data availability and model capability should be considered simultaneously. When applying measured solar radiation for estimating evaporation, evaporation estimates from Penman, FAO Penman-Monteith, and KNF equations are most close to pan evaporation rates in Jeonju and Jeju, Seoul and Mokpo, and Daejeon respectively.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.2B
• /
• pp.219-231
• /
• 2010

The Reference Evapotranspiration Calculator Software (REF-ET) supports computational guidelines for the reference evapotranspiration using seventeen FAO Penman-Monteith (PM) equations simultaneously such as the ASCE and FAO standardized forms. The REF-ET can conveniently consider missing data predictions and regional site characterizations, when reference ET is computed on monthly, daily, and hourly time steps. The applicability of the REF-ET was estimated to simulate the reference ET using hourly weather data from Seoul weather station for 29 years. The result found that the FAO24-Rd and 1957-Makk equations closely concerned with solar radiation parameter which were the most highly correlated to reference ET computed by pan coefficient. In addition, the 1957-Makk equation was identified as the most correct computational method for reference ET by analysis of bias and root mean square error. The 1957-Makk equation could predict the reference ET within the error of less than 1.06 mm/day, though all the other equations tended toward overestimation of predicting the reference ET in comparison with refecence ET of pan. The results of this study suggest that the REF-ET will be applicable to support reference ET estimation for a variety of field condition and time-scale.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.2B
• /
• pp.187-197
• /
• 2008

This study is to assess the impact of future land use change on hydrology and water quality in Gyungan-cheon watershed ($255.44km^2$) using SWAT (Soil and Water Assessment Tool) model. Using the 5 past Landsat TM (1987, 1991, 1996, 2004) and $ETM^+$ (2001) satellite images, time series of land use map were prepared, and the future land uses (2030, 2060, 2090) were predicted using CA-Markov technique. The 4 years streamflow and water quality data (SS, T-N, T-P) and DEM (Digital Elevation Model), stream network, and soil information (1:25,000) were prepared. The model was calibrated for 2 years (1999 and 2000), and verified for 2 years (2001 and 2002) with averaged Nash and Sutcliffe model efficiency of 0.59 for streamflow and determination coefficient of 0.88, 0.72, 0.68 for Sediment, T-N (Total Nitrogen), T-P (Total Phosphorous) respectively. The 2030, 2060 and 2090 future prediction based on 2004 values showed that the total runoff increased 1.4%, 2.0% and 2.7% for 0.6, 0.8 and 1.1 increase of watershed averaged CN value. For the future Sediment, T-N and T-P based on 2004 values, 51.4%, 5.0% and 11.7% increase in 2030, 70.5%, 8.5% and 16.7% increase in 2060, and 74.9%, 10.9% and 19.9% increase in 2090.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.5B
• /
• pp.459-469
• /
• 2010

This study is to develop a grid-based daily runoff model considering seasonal vegetation canopy condition. The model simulates the temporal and spatial variation of runoff components (surface, interflow, and baseflow), evapotranspiration (ET) and soil moisture contents of each grid element. The model is composed of three main modules of runoff, ET, and soil moisture. The total runoff was simulated by using soil water storage capacity of the day, and was allocated by introducing recession curves of each runoff component. The ET was calculated by Penman-Monteith method considering MODIS leaf area index (LAI). The daily soil moisture was routed by soil water balance equation. The model was evaluated for 930 $km^2$ Yongdam watershed. The model uses 1 km spatial data on landuse, soil, boundary, MODIS LAI. The daily weather data was built using IDW method (2000-2008). Model calibration was carried out to compare with the observed streamflow at the watershed outlet. The Nash-Sutcliffe model efficiency was 0.78~0.93. The watershed soil moisture was sensitive to precipitation and soil texture, consequently affected the streamflow, and the evapotranspiration responded to landuse type.

• Journal of Korea Water Resources Association
• /
• v.41 no.4
• /
• pp.413-422
• /
• 2008

It is essential to locally adjust the Hargreaves parameter for estimating reference evapotranspiration with short data as a substitute of Penman-Monteith equation. In this study, evaluation of daily-based reference evapotranspiration is computed with Hargreaves equation. in Gyeonggi bay area including Ganghwa, Incheon, Suwon, Seosan, and Cheonan station for the time period of 1997-2004. Hargreaves coefficient is adjusted to give the best fit with Penman-Monteith evapotranspiration, being regarded as a reference. Then, the preferred parameters are validated for the same stations for the time period of 2005-2006. The optimization-based correction in calibration for 1997-2004 shows improved performance of the Hargreaves equation, giving 0.68-0.77 to 0.92-0.98 in Nash-Sutcliffe coefficient of efficiency (NSC) and 14.63-23.30 to 5.23-11.75 in RMSE. The validation for 2005-2006 shows improved performance of the Hargreaves equation, giving 0.43-0.85 to 0.93-0.97 in NSC and 14.43-26.81 to 6.48-9.09 in RMSE.

• Journal of Korea Water Resources Association
• /
• v.48 no.5
• /
• pp.409-423
• /
• 2015

In this study the very short-term rainfall forecasting and storm water forecasting using the weather radar data were implemented in an urban stream basin. As forecasting time increasing, the very short-term rainfall forecasting results show that the correlation coefficient was decreased and the root mean square error was increased and then the forecasting model accuracy was decreased. However, as a result of the correlation coefficient up to 60-minute forecasting time is maintained 0.5 or higher was obtained. As a result of storm water forecasting in an urban area, the reduction in peak flow and outflow volume with increasing forecasting time occurs, the peak time was analyzed that relatively matched. In the application of storm water forecasting by radar rainfall forecast, the errors has occurred that we determined some of the external factors. In the future, we believed to be necessary to perform that the continuous algorithm improvement such as simulation of rapid generation and disappearance phenomenon by precipitation echo, the improvement of extreme rainfall forecasting in urban areas, and the rainfall-runoff model parameter optimizations. The results of this study, not only urban stream basin, but also we obtained the observed data, and expand the real-time flood alarm system over the ungaged basins. In addition, it is possible to take advantage of development of as multi-sensor based very short-term rainfall forecasting technology.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.14 no.4
• /
• pp.260-264
• /
• 2012

Accuracy of daily solar radiation estimated from a Mountain Microclimate Simulation Model (MT-CLIM) was assessed for seven observation sites with complex topography in Uiseong County. The coefficient of determination ($R^2$) between the observed and the estimated daily solar radiation was 0.52 for 7 sites for the study period from 1 August to 30 September 2009. Overall, the MT-CLIM overestimated the solar radiation with root mean square error (RMSE) of $3.83MJ\;m^{-2}$ which is about 25% of the mean daily solar radiation ($15.27MJ\;m^{-2}$) for the study period. Considering that the pyranometer's tolerance is ${\pm}5%$ of standard sensor, the RMSE of MT-CLIM was too large to accept for a direct application for agricultural sector. The reliability of solar radiation estimated by MT-CLIM must be improved by considering additional ways such as using a topography correction coefficient.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.953-966
• /
• 2022

Since aerosols adversely affect human health, such as deteriorating air quality, quantitative observation of the distribution and characteristics of aerosols is essential. Recently, satellite-based Aerosol Optical Depth (AOD) data is used in various studies as periodic and quantitative information acquisition means on the global scale, but optical sensor-based satellite AOD images are missing in some areas with cloud conditions. In this study, we produced gap-free GeoKompsat 2A (GK-2A) Advanced Meteorological Imager (AMI) AOD hourly images after generating a Random Forest based gap-filling model using grid meteorological and geographic elements as input variables. The accuracy of the model is Mean Bias Error (MBE) of -0.002 and Root Mean Square Error (RMSE) of 0.145, which is higher than the target accuracy of the original data and considering that the target object is an atmospheric variable with Correlation Coefficient (CC) of 0.714, it is a model with sufficient explanatory power. The high temporal resolution of geostationary satellites is suitable for diurnal variation observation and is an important model for other research such as input for atmospheric correction, estimation of ground PM, analysis of small fires or pollutants.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.207-221
• /
• 2023

This study suggests deep neural network models for estimating air temperature with Level 1B (L1B) datasets of GEO-KOMPSAT-2A (GK-2A). The temperature at 1.5 m above the ground impact not only daily life but also weather warnings such as cold and heat waves. There are many studies to assume the air temperature from the land surface temperature (LST) retrieved from satellites because the air temperature has a strong relationship with the LST. However, an algorithm of the LST, Level 2 output of GK-2A, works only clear sky pixels. To overcome the cloud effects, we apply a deep neural network (DNN) model to assume the air temperature with L1B calibrated for radiometric and geometrics from raw satellite data and compare the model with a linear regression model between LST and air temperature. The root mean square errors (RMSE) of the air temperature for model outputs are used to evaluate the model. The number of 95 in-situ air temperature data was 2,496,634 and the ratio of datasets paired with LST and L1B show 42.1% and 98.4%. The training years are 2020 and 2021 and 2022 is used to validate. The DNN model is designed with an input layer taking 16 channels and four hidden fully connected layers to assume an air temperature. As a result of the model using 16 bands of L1B, the DNN with RMSE 2.22℃ showed great performance than the baseline model with RMSE 3.55℃ on clear sky conditions and the total RMSE including overcast samples was 3.33℃. It is suggested that the DNN is able to overcome cloud effects. However, it showed different characteristics in seasonal and hourly analysis and needed to append solar information as inputs to make a general DNN model because the summer and winter seasons showed a low coefficient of determinations with high standard deviations.