• Korean Journal of Agricultural and Forest Meteorology
• /
• v.12 no.4
• /
• pp.289-297
• /
• 2010

Common practice of Soil Water Assessment Tool (SWAT) model validation is to use a single variable (i.e., streamlfow) to calibrate SWAT model due to the paucity of actual hydrological measurement data in Korea. This approach, however, often causes errors in the simulated results because of numerous sources of uncertainty and complexity of SWAT model. We employed multi-variables (i.e., streamflow, evapotranspiration, and soil moisture), which were measured at mixed forest in Seolmacheon catchment ($8.54\;km^2$), in order to assess the performance and reduce the uncertainties of SWAT model output. Meteorological and surface topographical data of the catchment were obtained as basic input variables and SWAT model was calibrated using daily data of streamflow (Jan. - Dec.), evapotranspiration (Sep. - Dec.), and soil moisture (Jun. - Dec.) collected in 2007. The model performance was assessed by comparing its results with the observation (i.e., streamflow of 2003 to 2008 and evapotranspiration and soil moisture of 2008). When the multi-variable measurements were used to calibrate the SWAT model, the model results showed better agreement with the measurements compared to those using a single variable measurement by showing increases in coefficient of determination ($R^2$) from 0.72 to 0.76 for streamflow, from 0.49 to 0.59 for soil moisture, and from 0.52 to 0.59 for evapotranspiration. The findings highlight the importance of reliable and accurate collective observation data for improving performance of SWAT model and promote its facilitation for estimating more realistic hydrological cycles at catchment scale.

• Journal of Korea Water Resources Association
• /
• v.51 no.6
• /
• pp.503-514
• /
• 2018

In recent, the hydrological regime of the Mekong river is changing drastically due to climate change and haphazard watershed development including dam construction. Information of hydrologic feature like streamflow of the Mekong river are required for water disaster prevention and sustainable water resources development in the river sharing countries. In this study, runoff simulations at the Kratie station of the lower Mekong river are performed using SWAT (Soil and Water Assessment Tool), a physics-based hydrologic model, and LSTM (Long Short-Term Memory), a data-driven deep learning algorithm. The SWAT model was set up based on globally-available database (topography: HydroSHED, landuse: GLCF-MODIS, soil: FAO-Soil map, rainfall: APHRODITE, etc) and then simulated daily discharge from 2003 to 2007. The LSTM was built using deep learning open-source library TensorFlow and the deep-layer neural networks of the LSTM were trained based merely on daily water level data of 10 upper stations of the Kratie during two periods: 2000~2002 and 2008~2014. Then, LSTM simulated daily discharge for 2003~2007 as in SWAT model. The simulation results show that Nash-Sutcliffe Efficiency (NSE) of each model were calculated at 0.9(SWAT) and 0.99(LSTM), respectively. In order to simply simulate hydrological time series of ungauged large watersheds, data-driven model like the LSTM method is more applicable than the physics-based hydrological model having complexity due to various database pressure because it is able to memorize the preceding time series sequences and reflect them to prediction.

• Water for future
• /
• v.25 no.3
• /
• pp.105-113
• /
• 1992

The purpose of this paper is to introduce and to apply the artificial neural network theory to real hydrologic system for forecasting daily streamflows during flood periods. The hydrologic dynamic process of rainfall-runoff is identified by the iterated estimation of system parameters that are determined by adjusting the weights of the network according to the non-linear response characteristics which is formed the model. Back propagation algorithm of neural network model is applied for the estimation of system parameters with past daily rainfall and runoff series data, and streamflows are forecasted using the parameters. The forecasted results are analyzed by statistical methods for the comparison with the observed.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.37 no.5
• /
• pp.81-89
• /
• 1995

One of the most difficult problem to estimate the flood inflow is how to understand the effective rainfall. The effective rainfall is absolutely influenced by the condition of soil moisture in the watershed just before the storm event. DAWAST model developed to simulate the daily streamflow considering the meteologic and geographic characteristics in the Korean watersheds was applied to understand the soil moisture and estimate the effective rainfall rather accurately through the daily water balance in the watershed. From this soil moisture and effective rainfall, concentration time, dimensionless hydrograph, and addition of baseflow, the rainfall-runoff model for flood flow was developed by converting the concept of long-term runoff into short-term runoff. And, real-time flood forecasting model was also developed to forecast the flood-inflow hydrograph to the river and reservoir, and called RETFLO model. According to the model verification, RETFLO model can be practically applied to the medium and small river and reservoir to forecast the flood hydrograph with peak discharge, peak time, and volume. Consequently, flood forecasting and warning system in the river and the reservoir can be greatly improved by using personal computer.

• Korean Journal of Agricultural Science
• /
• v.38 no.3
• /
• pp.513-524
• /
• 2011

To evaluate the applicability of inflow runoff model to reservoir operation in Korea, DAWAST model and TPHM model which are conceptual lumped daily runoff model and were developed in Korea, were selected and applied to simulate inflows to Daecheong multipurpose dam with watershed area of 4,134 $km^2$, and water storages in Geryong reservoir with watershed area of 15.1 $km^2$ and total water storage of 3.4 M $m^3$. Evaluating inflows on an yearly, monthly, ten-day, and daily basis, inflows by DAWAST model showed balanced scatters around equal value line. But inflow by TPHM model showed high in high flows. Annual mean water balance by DAWAST model was rainfall of 1,159.9 mm, evapotranspiration of 622.1 mm, and inflow of 644.6 mm, from which rainfall was 104.8 mm less than sum of evapotranspiration and inflow, and showed unbalanced result. Water balance by TPHM model showed satisfactory result. Reservoir water storages were shown to simulate on a considerable level from applying DAWAST and TPHM models to simulate inflows to Geryong reservoir. But it was concluded to be needed to improve DAWAST and TPHM model together from imbalance of water balance and low estimation in high flow.

• Journal of Korean Society on Water Environment
• /
• v.23 no.6
• /
• pp.973-984
• /
• 2007

This study developed and calculated alternative evaluation index (AEI) from the effectiveness analyses of alternatives for rehabilitation of distorted hydrologic cycle. The feasible alternatives for the poor-conditioned region in the Anyangcheon watershed were proposed and quantitatively analyzed using continuous water quantity/quality simulation model, Hydrological Simulation Program-Fortran (HSPF). The effectiveness analyses include 355th flow and 275th flow of flow duration curve and number of increased days to satisfy the target monthly flow for water quantity and BOD average concentration, total daily loads and number of increased days to satisfy the target concentration and total daily loads. The feasible alternatives are restoration of covered stream, prevention of streamflow loss through sewers, redevelopment of existing reservoir, reuse of treated wastewater, use of groundwater collected by subway stations and construction of small wastewater treatment plant. Therefore, alternative priority ranking was derived from AEIs. It will be effective to make an integrated watershed management for sustainable development.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.156-156
• /
• 2019

In this study, a gated recurrent unit (GRU) network is constructed based on a deep neural network (DNN) with the aim of restoring the missing daily flow data in river basins. Lai Chau hydrological station is located upstream of the Da river basin (Vietnam) is selected as the target station for this study. Input data of the model are data on observed daily flow for 24 years from 1961 to 1984 (before Hoa Binh dam was built) at 5 hydrological stations, in which 4 gauge stations in the basin downstream and restoring - target station (Lai Chau). The total available data is divided into sections for different purposes. The data set of 23 years (1961-1983) was employed for training and validation purposes, with corresponding rates of 80% for training and 20% for validation respectively. Another data set of one year (1984) was used for the testing purpose to objectively verify the performance and accuracy of the model. Though only a modest amount of input data is required and furthermore the Lai Chau hydrological station is located upstream of the Da River, the calculated results based on the suggested model are in satisfactory agreement with observed data, the Nash - Sutcliffe efficiency (NSE) is higher than 95%. The finding of this study illustrated the outstanding performance of the GRU network model in recovering the missing flow data at Lai Chau station. As a result, DNN models, as well as GRU network models, have great potential for application within the field of hydrology and hydraulics.

• Economic and Environmental Geology
• /
• v.56 no.1
• /
• pp.65-73
• /
• 2023

As one of the most vulnerable countries to floods, there should be an increased necessity for accurate and reliable flood forecasting in Indonesia. Therefore, a new prediction model using a machine learning algorithm is proposed to provide daily flood prediction in Indonesia. Data crawling was conducted to obtain daily rainfall, streamflow, land cover, and flood data from 2008 to 2021. The model was built using a Random Forest (RF) algorithm for classification to predict future floods by inputting three days of rainfall rate, forest ratio, and stream flow. The accuracy, specificity, precision, recall, and F1-score on the test dataset using the RF algorithm are approximately 94.93%, 68.24%, 94.34%, 99.97%, and 97.08%, respectively. Moreover, the AUC (Area Under the Curve) of the ROC (Receiver Operating Characteristics) curve results in 71%. The objective of this research is providing a model that predicts flood events accurately in Indonesian regions 3 months prior the day of flood. As a trial, we used the month of June 2022 and the model predicted the flood events accurately. The result of prediction is then published to the website as a warning system as a form of flood mitigation.

• Journal of Korea Water Resources Association
• /
• v.41 no.11
• /
• pp.1079-1094
• /
• 2008

This study is to evaluate the impact of varying spatial resolutions on the uncertainty of Soil and Water Assessment Tool (SWAT) predicted streamflow, non-point source (NPS) pollution loads transport in a small agricultural watershed (1.21 $km^2$) for three cases of model input; Case A is the combination of 2 m DEM, QuickBird land use, Case B is the combination of 10 m DEM, 1/25,000 land use, and Case C is the combination of 30 m DEM, Landsat land use, soil data is used 1/25,000 for three cases respectively. The model was calibrated for 2 years (1999-2000) using daily streamflow and monthly water quality records, and verified for another 2 years (2001-2002). The average Nash and Sutcliffe model efficiency was 0.59 for streamflow and RMSE were 2.08, 4.30 and 0.70 tons/yr for sediment, T-N and T-P respectively. The model was run for a small agricultural watershed with three cases of spatial input data. The hydrological results showed that output uncertainty was biggest by spatial resolution of land use. Streamflow increase the watershed average CN value of QucikBird land use was 0.4 and 1.8 higher than those of 1/25,000 and Landsat land use caused increase of streamflow. On the other hand, The NPS loadings from the model prediction showed that the sediment, T-N and T-P of QuickBird land use (Case A) showed 23.7 %, 43.3 % and 48.4 % higher value than 1/25,000 land use (Case B) and 50.6 %, 50.8 % and 56.9 % higher value than Landsat land use (Case C) respectively.

• Journal of Wetlands Research
• /
• v.26 no.2
• /
• pp.147-159
• /
• 2024

Lack of streamflow observations makes model calibration difficult and limits model performance improvement. Satellite-based remote sensing products offer a new alternative as they can be actively utilized to obtain hydrological data. Recently, several studies have shown that artificial intelligence-based solutions are more appropriate than traditional conceptual and physical models. In this study, a data-driven approach combining various recurrent neural networks and decision tree-based algorithms is proposed, and the utilization of satellite remote sensing information for AI training is investigated. The satellite imagery used in this study is from MODIS and SMAP. The proposed approach is validated using publicly available data from 25 watersheds. Inspired by the traditional regionalization approach, a strategy is adopted to learn one data-driven model by integrating data from all basins, and the potential of the proposed approach is evaluated by using a leave-one-out cross-validation regionalization setting to predict streamflow from different basins with one model. The GRU + Light GBM model was found to be a suitable model combination for target basins and showed good streamflow prediction performance in ungauged basins (The average model efficiency coefficient for predicting daily streamflow in 25 ungauged basins is 0.7187) except for the period when streamflow is very small. The influence of satellite remote sensing information was found to be up to 10%, with the additional application of satellite information having a greater impact on streamflow prediction during low or dry seasons than during wet or normal seasons.