• Journal of Korean Society of Disaster and Security
• /
• v.14 no.4
• /
• pp.17-27
• /
• 2021

Streamflow prediction is a very vital disaster mitigation approach for effective flood management and water resources planning. Lately, torrential rainfall caused by climate change has been reported to have increased globally, thereby causing enormous infrastructural loss, properties and lives. This study evaluates the contribution of rainfall to streamflow prediction in normal and peak rainfall scenarios, typical of the recent flood at Piney Resort in Vernon, Hickman County, Tennessee, United States. Daily streamflow, water level, and rainfall data for 20 years (2000-2019) from two USGS gage stations (03602500 upstream and 03599500 downstream) of the Piney River watershed were obtained, preprocesssed and fitted with Long short term memory (LSTM) model. Tensorflow and Keras machine learning frameworks were used with Python to predict streamflow values with a sequence size of 14 days, to determine whether the model could have predicted the flooding event in August 21, 2021. Model skill analysis showed that LSTM model with full data (water level, streamflow and rainfall) performed better than the Naive Model except some rainfall models, indicating that only rainfall is insufficient for streamflow prediction. The final LSTM model recorded optimal NSE and RMSE values of 0.68 and 13.84 m³/s and predicted peak flow with the lowest prediction error of 11.6%, indicating that the final model could have predicted the flood on August 24, 2021 given a peak rainfall scenario. Adequate knowledge of rainfall patterns will guide hydrologists and disaster prevention managers in designing efficient early warning systems and policies aimed at mitigating flood risks.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1295-1303
• /
• 2022

As the role of water distribution networks (WDNs) becomes more important, identifying abnormal events (e.g., pipe burst) rapidly and accurately is required. Since existing approaches such as field equipment-based detection methods have several limitations, model-based methods (e.g., machine learning based detection model) that identify abnormal events using hydraulic simulation models have been developed. However, no previous work has examined the impact of data uncertainties on the results. Thus, this study compares the effects of measurement error-induced pressure data uncertainty in WDNs. An artificial neural network (ANN) is used to predict nodal pressures and measurement errors are generated by using cumulative density function inverse sampling method that follows Gaussian distribution. Total of nine conditions (3 input datasets × 3 output datasets) are considered in the ANN model to investigate the impact of measurement error size on the prediction results. The results have shown that higher data uncertainty decreased ANN model's prediction accuracy. Also, the measurement error of output data had more impact on the model performance than input data that for a same measurement error size on the input and output data, the prediction accuracy was 72.25% and 38.61%, respectively. Thus, to increase ANN models prediction performance, reducing the magnitude of measurement errors of the output pressure node is considered to be more important than input node.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.54 no.1
• /
• pp.27-38
• /
• 2012

This study is to analyse the hydrological behavior of agricultural reservoir using CAT (Catchment hydrologic cycle Assessment Tool). The CAT is a water cycle analysis model in order to quantitatively assess the characteristics of the short/long-term changes in watershed. It supports the effective design of water cycle improvement facilities by supplementing the strengths and weaknesses of existing conceptual parameter-based lumped hydrologic models and physical parameter-based distributed hydrologic models. The CAT especially supports the analysis of runoff processes in paddy fields and reservoirs. To evaluate the impact of agricultural reservoir operation and irrigation water supply on long-term rainfall-runoff process, the CAT was applied to Idong experimental catchment, operated for research on the rural catchment characteristics and accumulated long term data by hydrological observation equipments since 2000. From the results of the main control points, Idong, Yongdeok and Misan reservoirs, the daily water levels of those points are consistent well with observed water levels, and the Nash-Sutcliffe model efficiencies were 0.32~0.89 (2001~2007) and correlation coefficients were 0.73~0.98.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 1999.10c
• /
• pp.708-714
• /
• 1999

For the assessment of the level of stream pollution, SWAT-WASP model linked with GIS was applied to a respresentative rural watershed and evaluated for its applicability through calibration and verfication using observed data. Using daily water yields, sediment yields and nutrient discharge simulated by SWAT model, WASP input file was build. Point source pollutant and water quality change in stream was considered in WASP model. For the model applicatiion , digital maps were constructed for watershed boundary, ladn-use , soil series , digital elevation, and topographic data of Bok-Ha watershed using GRASS. The model application results showed that the simulated runoff was in a good agreement with the observed data and indicated reasonable applicability of the model.

• 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 Korean Society on Water Environment
• /
• v.23 no.5
• /
• pp.591-599
• /
• 2007

The quality of water released from a stratified reservoir is dependent on various factors such as the location and shape of intake facility, structure of reservoir stratification, profile of water quality constituent, and withdrawal flux. Sometimes, selective withdrawal capabilities can provide the operational flexibility to meet the water quality demands both in-reservoir and downstream. The objective of this study was to evaluate the performance of a one-dimensional reservoir selective withdrawal model (SELECT) as a tool for supporting downstream water quality management for Daecheong and Imha reservoirs. The simulated water quality variables including water temperature, dissolved oxygen (DO), conductivity, turbidity were compared with the field data measured in tailwater. The model showed fairly satisfactory results and high reliability in simulating observations. The coefficients of determinant between simulated and observed turbidity values were 0.93 and 0.95 for Daecheong and Imha reservoirs, respectively. The outflow water quality was significantly influenced by water intake level under fully stratified condition, while the effect of intake amount was minor. In conclusion, the SELECT is simple but effective tool for supporting downstream water quality prediction and management for both reservoirs.

• Environmental Engineering Research
• /
• v.14 no.1
• /
• pp.53-60
• /
• 2009

The main objective was to develop and assess a dynamic fate and transport model for lead in air, soil, sediment, water and vegetation. Daejeon was chosen as the study area for its relatively high contamination and emission levels. The model was assessed by comparing model predictions with measured concentrations in multi-media and atmospheric deposition flux. Given a lead concentration in air, the model could predict the concentrations in water and soil within a factor of five. Sensitivity analysis indicated that effective compartment volumes, rain intensity, scavenging ratio, run off, and foliar uptake were critical to accurate model prediction. Important implications include that restriction of air emission may be necessary in the future to protect the soil quality objective as the contamination level in soil is predicted to steadily increase at the present emission level and that direct discharge of lead into the water body was insignificant as compared to atmospheric deposition fluxes. The results strongly indicated that atmospheric emission governs the quality of the whole environment. Use of the model developed in this study would provide quantitative and integrated understanding of the cross-media characteristics and assessment of the relationships of the contamination levels among the multi-media environment.

• International Journal of Fluid Machinery and Systems
• /
• v.3 no.4
• /
• pp.285-291
• /
• 2010

To provide required flow rates of cooling or circulating water properly, approach flow conditions of vertical pump systems should be in compliance with state of the art acceptance criteria. The direct inflow should be vortex free, with low pre-rotation and symmetric velocity distribution. Physical model investigations are common practice and the best tool of prediction to evaluate, to optimize and to document flow conditions inside intake structures for vertical pumping systems. Optimization steps should be accomplished with respect to installation costs and complexity on site. The report shows evaluation of various approach flow conditions inside a compact waste water pumping station. The focus is on the occurrence of free surface vortices and the evaluation of air entrainment for various water level and flow rates. The presentation of the results includes the description of the investigated intake structure, occurring flow problems and final recommendations.

• Journal of Ocean Engineering and Technology
• /
• v.20 no.1 s.68
• /
• pp.55-62
• /
• 2006

Recently, pollution by development in coastal areas is going from bad to worse. The Korean government is attempting to make policies that prevent water pollution, but it is still difficult to say whether such measures are lowering pollution to an acceptable level. More specifically, the general investigation that has been done in KOREA does not accurately reflect the actual conditions of pollution in coastal areas. An investigation that quantitatively assesses water quality management using rational prediction technology must be attempted, and the ecosystem model, which incorporates both the 3-dimensional hydrodynamic and material cycle models, is the only one with a broad enough scope to obtain accurate results. The hydrodynamic model, which includes advection and diffusion, accounts for the ever-changing flow and (quality) of water in coastal areas, while the material cycle model accounts for pollutants and components of decomposition as sources of the carbon, phosphorus, and nitrogen cycles. In this paper, we simulated the rates of dissolved oxygen (DO), chemical oxygen demand (COD), total nitrogen(T-N) and total-phosphorous(T-P) in Korea's Ulsan Area. Using the ecosystem model, we did simulations using a specific set of parameters and did comparative analysis to determine those most appropriate for the actual environmental characteristics of Ulsan Area. The simulation was successful, making it now possible to predict the likelihood of coastal construction projects causing ecological damage, such as eutrophication and red tide. Our model can also be used in the environmental impact assessment (EIA) of future development projects in the ocean.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2002.05a
• /
• pp.257-262
• /
• 2002

Numerical model introduced in this study combines wave refraction-diffraction, breaking, bottom friction, lateral mixing, and critical shear stress and three sub-models for simulating waves, currents, and bottom change were briefly discussed. Simulations of beach processes and harbor sedimentation were also described at the coast neighboring Bangpo Harbor, Anmyundo, Chungnam, where the area has suffered from accumulation of drifting sand in a small fishing harbor with a wide tidal range. We also made model test for the case of a narrow tidal range at Nakdong river's estuary area to understand the effect of water level variation on the littoral drift. Simulations are conducted in terms of incident wave direction and tidal level. Characteristics of wave transformation, nearshore current, sediment transport, and bottom change are shown and analyzed. We found from the simulation that the tidal level impact to the sediment transport is very important and we should apply the numerical model with different water level to analyze sediment transport mechanism correctly. Although the model study gave reasonable description of beach processes and harbor sedimentation mechanism, it is necessary to collect lots of field observation data, including waves, tides and bottom materials, etc. for better prediction.