• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.4
• /
• pp.51-57
• /
• 2024

This study was conducted on how to simulate runoff, which was done using existing physical models, using an LSTM (Long Short-Term Memory) model based on deep learning. Tancheon, the first tributary of the Han River, was selected as the target area for the model application. To apply the model, one water level observatory and four rainfall observatories were selected, and hourly data from 2020 to 2023 were collected to apply the model. River water level of the outlet of the Tancheon basin was simulated by inputting precipitation data from four rainfall observation stations in the basin and average preceding 72-hour precipitation data for each hour. As a result of water level simulation using 2021 to 2023 data for learning and testing with 2020 data, it was confirmed that reliable simulation results were produced through appropriate learning steps, reaching a certain mean absolute error in a short period time. Despite the short data period, it was found that the mean absolute percentage error was 0.5544~0.6226%, showing an accuracy of over 99.4%. As a result of comparing the simulated and observed values of the rapidly changing river water level during a specific heavy rain period, the coefficient of determination was found to be 0.9754 and 0.9884. It was determined that the performance of LSTM, which aims to simulate river water levels, could be improved by including preceding precipitation in the input data and using precipitation data from various rainfall observation stations within the basin.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.31-31
• /
• 2023

During December 2022, the northeast monsoon, which dominates the south and the Gulf of Thailand, had significant rainfall that impacted the lower southern region, causing flash floods, landslides, blustery winds, and the river exceeding its bank. The Golok River, located in Narathiwat, divides the border between Thailand and Malaysia was also affected by rainfall. In flood management, instruments for measuring precipitation and water level have become important for assessing and forecasting the trend of situations and areas of risk. However, such regions are international borders, so the installed measuring telemetry system cannot measure the rainfall and water level of the entire area. This study aims to predict 72 hours of water level and evaluate the situation as information to support the government in making water management decisions, publicizing them to relevant agencies, and warning citizens during crisis events. This research is applied to machine learning (ML) for water level prediction of the Golok River, Lan Tu Bridge area, Sungai Golok Subdistrict, Su-ngai Golok District, Narathiwat Province, which is one of the major monitored rivers. The eXtreme Gradient Boosting (XGBoost) algorithm, a tree-based ensemble machine learning algorithm, was exploited to predict hourly water levels through the R programming language. Model training and testing were carried out utilizing observed hourly rainfall from the STH010 station and hourly water level data from the X.119A station between 2020 and 2022 as main prediction inputs. Furthermore, this model applies hourly spatial rainfall forecasting data from Weather Research and Forecasting and Regional Ocean Model System models (WRF-ROMs) provided by Hydro-Informatics Institute (HII) as input, allowing the model to predict the hourly water level in the Golok River. The evaluation of the predicted performances using the statistical performance metrics, delivering an R-square of 0.96 can validate the results as robust forecasting outcomes. The result shows that the predicted water level at the X.119A telemetry station (Golok River) is in a steady decline, which relates to the input data of predicted 72-hour rainfall from WRF-ROMs having decreased. In short, the relationship between input and result can be used to evaluate flood situations. Here, the data is contributed to the Operational support to the Special Water Resources Management Operation Center in Southern Thailand for flood preparedness and response to make intelligent decisions on water management during crisis occurrences, as well as to be prepared and prevent loss and harm to citizens.

• Journal of Environmental Science International
• /
• v.10 no.5
• /
• pp.323-327
• /
• 2001

A new method is developed to estimate the evaporation of water from a surface with high accuracy and resolution. The principle of new method is to detect a weight change of buoyant weight according to a change in water level of Class A Pan mesured by the use of a strain-gauge load cell. Field test of evaporation recording new instrument was carried out at Suwon for 10 days July 1999. It is possible in field observation to measure hourly evaporation amount by newly developed evaporation recording instrument in Class A Pan against strong solar radiation. Present study provide a possibility of domestic high accuracy instrument development below than 0.1mm water level measurement accuracy. If there is low humidity and high wind speed conditions which is possible to evaporate from water surface during night time. And it needs continuous study to understand between meteorological elements and latent heat effect at ground level by field observation study using high accuracy evaporation recording instrument.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.42
• /
• pp.24-30
• /
• 2000

A system for evaluating streamflow data (KORSAS) was developed, and is operated using PC based Windows to help the hydrological observation practitioner's working in Korea Water Resources Corporation (KOWACO). This system has modules including; DB access and data management, flow measurement arranging, H-Q relation deriving, area rainfall calculating, flow calculating, and flow evaluating modules. Evaluation of observed streamflow is accomplished through the following processes. First, hourly streamflow data is calculated from water level data stored in a DB server by applying the rating relationship between water level and flow rates derived from the past flow measurements. Second, hourly areal rainfal data is calculated from point data stored in the DB server by applying Thiessen networks. Third, hydrographs are displayed on a daily, weekly, monthly, or seasonal duration basis, and are compared to hydrographs of reservoir inflow, hydrographs at water level observation stations and hydrographs derived from simulated results using models.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.4 no.4
• /
• pp.197-202
• /
• 2002

A new method is used to estimate the amount of water evaporation from Class A Pan with higher precision and accuracy. The principle of method is to detect the weight change of a buoyant sinker resulting from a change in water level of Class A Pan. A strain-gauge load cell is used to measure the weight change. Field observation of evaporation was done at Pohang Meteorological Station from June 24 to August 4, 2002. By using this new method, it is possible to measure hourly evaporation accurately even under a strong solar radiation and wind disturbance, enabling a direct comparison of evaporation with other meteorological elements. At night, under low humidity and high wind speed conditions, more evaporation was recorded than during daytime. Maximum evaporation rates observed during this period exceed 1.0 mm/hour under the sunny and windy conditions with low humidity. To understand relationships between meteorological elements and latent heat flux at ground level, we suggest intensive held experiments using high accuracy evaporation recording instruments with hourly time interval.

• Korean Journal of Agricultural Science
• /
• v.47 no.4
• /
• pp.1029-1037
• /
• 2020

The machine learning algorithm has been widely used in water-related fields such as water resources, water management, hydrology, atmospheric science, water quality, water level prediction, weather forecasting, water discharge prediction, water quality forecasting, etc. However, water quality prediction studies based on the machine learning algorithm are limited compared to other water-related applications because of the limited water quality data. Most of the previous water quality prediction studies have predicted monthly water quality, which is useful information but not enough from a practical aspect. In this study, we predicted the dissolved oxygen (DO) using recurrent neural network with long short-term memory model recurrent neural network long-short term memory (RNN-LSTM) algorithms with hourly- and daily-datasets. Bugok Bridge in Oncheoncheon, located in Busan, where the data was collected in real time, was selected as the target for the DO prediction. The 10-month (temperature, wind speed, and relative humidity) data were used as time prediction inputs, and the 5-year (temperature, wind speed, relative humidity, and rainfall) data were used as the daily forecast inputs. Missing data were filled by linear interpolation. The prediction model was coded based on TensorFlow, an open-source library developed by Google. The performance of the RNN-LSTM algorithm for the hourly- or daily-based water quality prediction was tested and analyzed. Research results showed that the hourly data for the water quality is useful for machine learning, and the RNN-LSTM algorithm has potential to be used for hourly- or daily-based water quality forecasting.

• Journal of Korea Water Resources Association
• /
• v.48 no.12
• /
• pp.1051-1064
• /
• 2015

Currently, the H purification plant determines the hourly water intake amount based on operator experience and skill. Therefore, inevitably, there are deviations among operators. While meeting time-varying demand and maintaining the proper water level in the clean water reservoir, the methodology for minimizing electricity cost, when dealing with different electricity rate time zones, is a very complicated problem, which is beyond an operator's capability. To solve this problem, a linear programming (LP) model is proposed, which can determine the optimal hourly water intake amount for minimizing the daily electricity cost. It is shown that an inaccurate estimate for the hourly water usage in the demand areas causes the water level constraint to be violated, which is the weak point of the proposed LP method. However, several examples with real-field data show that we can practically and safely solve this problem with safety margins. It is also shown that the safety margin method still works effectively whether the estimate is accurate or not. The operators need not attend the site at all times under the proposed LP method, and we can additionally expect reductions in labor costs.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.147-147
• /
• 2018

In this article, we use an open source software library: TensorFlow, developed for the purposes of conducting very complex machine learning and deep neural network applications. However, the system is general enough to be applicable in a wide variety of other domains as well. The proposed model based on a deep neural network model, LSTM (Long Short-Term Memory) to predict the river water level at Okcheon Station of the Guem River without utilization of rainfall - forecast information. For LSTM modeling, the input data is hourly water level data for 15 years from 2002 to 2016 at 4 stations includes 3 upstream stations (Sutong, Hotan, and Songcheon) and the forecasting-target station (Okcheon). The data are subdivided into three purposes: a training data set, a testing data set and a validation data set. The model was formulated to predict Okcheon Station water level for many cases from 3 hours to 12 hours of lead time. Although the model does not require many input data such as climate, geography, land-use for rainfall-runoff simulation, the prediction is very stable and reliable up to 9 hours of lead time with the Nash - Sutcliffe efficiency (NSE) is higher than 0.90 and the root mean square error (RMSE) is lower than 12cm. The result indicated that the method is able to produce the river water level time series and be applicable to the practical flood forecasting instead of hydrologic modeling approaches.

• The Journal of the Korea Contents Association
• /
• v.16 no.4
• /
• pp.604-613
• /
• 2016

The sea level of the Earth is rising approximately 2.0mm per year (global average value) due to thermal expansion of sea water, melting of glaciers and other causes by global warming. However, when it comes to design a river, the standard of design water level is decided by analyzing four largeness tide value and harmonic constant with observed tidal water level. Therefore, it seems the external water level needs to consider an increasing speed of the seawater level which corresponds to a design frequency. In the present study, the hourly observed tidal water level targeting 47 tidal stations operated by Korea Hydrographic and Oceanographic Administration (KHOA) from beginning of observation to 2015 per hour has been collected. The variation of monthly and yearly and increasing ratio have been performed divided 4 seas such as the Southern, East, Western, and Jeju Sea. Also, the external water level existing design for rivers nearby a coast was been reviewed. The current study could be used to figure out the cause of local seawater rise and reflect the external water level as basic data.

• Journal of Environmental Science International
• /
• v.18 no.3
• /
• pp.309-314
• /
• 2009

A accurate reservoir inflow is very important as providing information for decision making about the water balance and the flood control, as well as for dam safety. The methods to calculate the inflow were divided by the directed method to measure streamflow from upstream reservoirs and the indirected method to estimate using the correlation of reservoir water level and release. Currently, the inflow of multi-purpose dam is being calculated by the indirect method and the reservoir water level to calculate the storage capacity is being used by centimeters(cm) units. Corresponding to the storage volume of 1cm according to scale and water level of multi-purpose dam comes up to from several 10 thousand tons to several million tons. If it converts to inflow during 1 hour, and it comes to several hundred $m^3/sec$(CMS). Therefore, the inflow calculated on the hourly is largely deviated along the water level changes and is occurred minus value as the case. In this research, the water level gage has been developed so that it can measure a accurate water level for the improvement for the error and derivation of inflow, even though there might be various hydrology and meteorologic considerations to analyse the water balance of reservoir. Also, it is confirmed that the error and the standard derivation of data observed by the new gage is decreased by 89,6% and 1/3 & 87% and 2/3 compared to that observed by the existing gage of Daecheong and Juam multi-purpose dam.