• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.100-100
• /
• 2018

본 연구에서는 집중호우에 대한 레이더기반 초단기 강우예측 시스템의 정확도를 향상시키기 위해 초기장 개선 연구를 수행하였다. 집중호우에 적합한 강우를 추정하기 위해 층운형, 대류형, 열대형의 Z-R관계식과 반사도 조건에 따라 층운형과 적운형을 구분하여 Z-R 관계식을 적용하였으며, 이를 초단기 강우예측 시스템의 초기장으로 활용하였다. 또한 2016년 10월 5일 태풍 차바(Chaba)에 의한 집중호우 사례에 대해 지상관측 강우자료와 레이더 추정 및 예측 강우자료와의 비교를 통해 정확도를 정성적 정량적으로 평가하였다. 레이더 강우추정에 대한 분석 결과, 복합형 타입의 Z-R 관계식의 상관계수와 평균제곱근오차가 비슬산레이더의 경우 각각 0.8207, 9.22 mm/hr, 면봉산 레이더의 경우 각각 0.8001, 10.53 mm/hr로 가장 좋은 성능을 보였다. 강우 예측에 대한 분석 결과, 집중호우 사례에 대해 강우강도 공간분포 및 이동 패턴은 평균적으로 잘 모의하였으며, 초단기 강우예측 결과의 평균적으로 POD는 0.97이상, FAR는 0.21 이하로 다소 정확하게 예측하는 것으로 분석되었다. 정량적 평가 결과, 비슬산 레이더의 경우 상관계수가 예측시간 60분까지 0.545이상, 면봉산 레이더의 경우 0.379 이상으로 비교적 좋은 상관성을 보였으며, Z-R관계식 유형에 따른 차이는 작은 것으로 확인되었다. 평균제곱근오차의 경우 열대형과 복합형의 Z-R관계식이 높은 정확도를 가지는 것으로 확인되었다. 본 연구 결과, 초기장 정확도의 개선을 통한 레이더 기반 초단기 강우예측 모형의 정확도 개선 가능성을 확인할 수 있었으며, 향후 지속적인 사례연구 및 검증을 통하여 강우추정 및 강우예측 알고리즘 개선의 노력이 필요하다.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.1
• /
• pp.145-159
• /
• 2019

A good number of drought indices have been introduced and applied in different regions for monitoring drought conditions, but some of those are region-specific and have limitations for use under other climatic conditions because of the inherently complex characteristics of drought phenomenon. Standardized Precipitation Index (SPI) indices are widely used all over the world, including Bangladesh. Although newly developed, studies have demonstrated The Effective Drought Index (EDI) to perform better compared to SPIs in some areas. This research examined the performance of EDI to the SPI for detecting drought events throughout 35 years (1981 to 2015) in Bangladesh. Rainfall data from 27 meteorological stations across Bangladesh were used to calculate the EDI and SPI values. Results suggest that the EDI can detect historical records of actual events better than SPIs. Moreover, EDI is more efficient in assessing both short and long-term droughts than SPIs. Results also indicate that SPI3 and the EDI indices have a better capability of detecting drought events in Bangladesh compared to other SPIs; however, SPI1 produced erroneous estimates. Therefore, EDI is found to be more responsive to drought conditions and can capture the real essence of the drought situation in Bangladesh. Outcomes from this study bear policy implications on mitigation measures to minimize the loss of agricultural production in drought-prone areas. Information on severity level and persistence of drought conditions will be instrumental for resource managers to allocate scarce resources optimally.

• Korean Journal of Agricultural Science
• /
• v.49 no.2
• /
• pp.193-202
• /
• 2022

The recurrent neural network (RNN) algorithm has been widely used in water-related research areas, such as water level predictions and water quality predictions, due to its excellent time series learning capabilities. However, studies on water quality predictions using RNN algorithms are limited because of the scarcity of water quality data. Therefore, most previous studies related to water quality predictions were based on monthly predictions. In this study, the quality of the water in a reservoir in Nonsan, Chungcheongnam-do Republic of Korea was predicted using the RNN-LSTM algorithm. The study was conducted after constructing data that could then be, linearly interpolated as daily data. In this study, we attempt to predict the water quality on the 7th, 15th, 30th, 45th and 60th days instead of making daily predictions of water quality factors. For daily predictions, linear interpolated daily water quality data and daily weather data (rainfall, average temperature, and average wind speed) were used. The results of predicting water quality concentrations (chemical oxygen demand [COD], dissolved oxygen [DO], suspended solid [SS], total nitrogen [T-N], total phosphorus [TP]) through the LSTM algorithm indicated that the predictive value was high on the 7th and 15th days. In the 30th day predictions, the COD and DO items showed R² that exceeded 0.6 at all points, whereas the SS, T-N, and T-P items showed differences depending on the factor being assessed. In the 45th day predictions, it was found that the accuracy of all water quality predictions except for the DO item was sharply lowered.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.145-145
• /
• 2022

Availability of abundant water resources data in developing countries is a great concern that has hindered the adoption of deep learning techniques (DL) for disaster prevention and mitigation. On the contrary, over the last two decades, a sizeable amount of DL publication in disaster management emanated from developed countries with efficient data management systems. To understand the current state of DL adoption for solving water-related disaster management in developing countries, an extensive bibliometric review coupled with a theory-based analysis of related research documents is conducted from 2003 - 2022 using Web of Science, Scopus, VOSviewer software and PRISMA model. Results show that four major disasters - pluvial / fluvial flooding, land subsidence, drought and snow avalanche are the most prevalent. Also, recurrent flash floods and landslides caused by irregular rainfall pattern, abundant freshwater and mountainous terrains made India the only developing country with an impressive DL adoption rate of 50% publication count, thereby setting the pace for other developing countries. Further analysis indicates that economically-disadvantaged countries will experience a delay in DL implementation based on their Human Development Index (HDI) because DL implementation is capital-intensive. COVID-19 among other factors is identified as a driver of DL. Although, the Long Short Term Model (LSTM) model is the most frequently used, but optimal model performance is not limited to a certain model. Each DL model performs based on defined modelling objectives. Furthermore, effect of input data size shows no clear relationship with model performance while final model deployment in solving disaster problems in real-life scenarios is lacking. Therefore, data augmentation and transfer learning are recommended to solve data management problems. Intensive research, training, innovation, deployment using cheap web-based servers, APIs and nature-based solutions are encouraged to enhance disaster preparedness.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6D
• /
• pp.915-922
• /
• 2008

Impervious surface is an important index for the estimation of urbanization and the assessment of environmental change. In addition, impervious surface influences on short-term rainfall-runoff model during rainy season in hydrology. Recently, the necessity of impervious surface estimation is increased because the effect of impervious surface is increased by rapid urbanization. In this study, impervious surface estimation is performed by using remote sensing image such as Landsat-7 ETM+image with $30m{\times}30m$ spatial resolution and satellite image with $1m{\times}1m$ spatial resolution based on Jungnangcheon basin. A tasseled cap transformation and NDVI(normalized difference vegetation index) transformation are applied to Landsat-7 ETM+ image to collect various predict variables. Moreover, the training data sets are collected by overlaying between Landsat-7 ETM+ image and satellite image, and CART(classification and regression tree) is applied to the training data sets. As a result, impervious surface prediction model is consisted and the impervious surface map is generated for Jungnangcheon basin.

• Journal of Korea Water Resources Association
• /
• v.43 no.8
• /
• pp.721-731
• /
• 2010

The rainfall-runoff relationship is very difficult to predict because it is complicate factor affected by many temporal and spatial parameters of the basin. In recent, models which is based on artificial intelligent such as neural network, genetic algorithm fuzzy etc., are frequently used to predict discharge while stochastic or deterministic or empirical models are used in the past. However, the discharge data which are generally used for prediction as training and validation set are often estimated from rating curve which has potential error in its estimation that makes a problem in reliability. Therefore, in this study, water stage is predicted from antecedent rainfall and water stage data for short term using three models of neural network which trained by error back propagation algorithm and optimized by genetic algorithm and training error back propagation after it is optimized by genetic algorithm respectively. As the result, the model optimized by Genetic Algorithm gives the best forecasting ability which is not much decreased as the forecasting time increase. Moreover, the models using stage data only as the input data give better results than the models using precipitation data with stage data.

• Journal of the Korean earth science society
• /
• v.40 no.6
• /
• pp.572-583
• /
• 2019

In this study, the atmospheric vertical structure (AVS) associated with summertime (June, July, and August) heavy rainfall in Seoul was classified into three patterns (Loaded Gun: L, Inverted V: IV, and Thin Tube: TT) using rawinsonde soundings launched at Osan from 2009 to 2018. The characteristics of classified AVS and precipitation property were analyzed. Occurrence frequencies in each type were 34.7% (TT-type), 20.4% (IV-type), 20.4% (LG-type), and 24.5% (Other-type), respectively. The mean value of Convective Available Potential Energy (1131.1 J kg^-1) for LG-types and Storm Relative Helicity (357.6 ㎡s^-2) for TT-types was about 2 times higher than that of other types, which seems to be the difference in the mechanism of convection at the low level atmosphere. The composited synoptic fields in all cases showed a pattern that warm and humid southwesterly wind flows into the Korean Peninsula. In the cases of TT-type, the low pressure center (at 850 hPa) was followed by the trough in upper-level (at 500 hPa) as the typical pattern of a low pressure deepening. The TT-type was strongly influenced by the low level jet (at 850 hPa), showing a pattern of connecting the upper- and low-level jets. The result of analysis indicated that precipitation was intensified in the first half of all types. IV-type precipitation induced by thermal instability tended to last for a short term period with strong precipitation intensity, while TT-type by mechanical instability showed weak precipitation over a long term period.

• Journal of Korean Society of Forest Science
• /
• v.85 no.4
• /
• pp.634-646
• /
• 1996

This study was carried out to reveal the forest land effect on water purification in mountainous watersheds. Rainfall, throughfall, stemflow, soil and stream water were monitored by pH, electrical conductivity(EC), and dissolved oxygen(DO) in Daehan-Ri and Parkdal-Ri catchments. The results were summarized as follows; 1. Rainfall pH values of Parkdal-Ri and Daehan-Ri were 7.6 and 6.4, respectively. 2. Comparing stemflow and throughfall of Pinus densiflora with Pinus rigida, the pH values of Pinus densiflora were 4.32 and 4.22 and the pH of Pinus rigida were 3.34 and 4.81, respectively. The EC values of Pinus densiflora were $119.7{\mu}S/cm$ and $96.8{\mu}S/cm$ and EC of Pinus rigida were $230.0{\mu}S/cm$ and $82.0{\mu}S/cm$. 3. All pH values were decreased as the streamflow increased except long-term runoff in Daehan-Ri. The EC values also were increased as the streamflow increased, but EC of short-term runoff in Daehan-Ri was gradually decreased as the streamflow increased due to entrance of throughfall which has high EC values at the beginning of rainfall events. The DO concentrations of all experimental plots were elevated as the streamflow increased, because reaeration occurs at the surface of the stream as the increased discharge make turbulence. 4. pH of Stemflow and throughfall in Pinus densiflora were lower than in Quercus acutissima, but EC values were higher in Pinus densiflora. 5. Water purification was mostly influenced by forest soil in forest hydrological processes. 6. Stemflow and throughfall were more influenced by dry deposition and organic acid in crown and bark than those of wet deposition. During the stemflow and throughfall passed forest soil, these acidic stemflow and throughfall were neutralized, and stream water quality was neutral or slightly alkaline.

• Journal of Korea Water Resources Association
• /
• v.53 no.2
• /
• pp.97-105
• /
• 2020

Recently, Artificial Neural Network receives attention as a data prediction method. Among these, a Long Shot-term Memory (LSTM) model specialized for time-series data prediction was utilized as a prediction method of hydrological time series data. In this study, the LSTM model was constructed utilizing deep running open source library TensorFlow which provided by Google, to predict inflows of multipurpose dams. We predicted the inflow of the Yongdam Multipurpose Dam which is located in the upper stream of the Geumgang. The hourly flow data of Yongdam Dam from 2006 to 2018 provided by WAMIS was used as the analysis data. Predictive analysis was performed under various of variable condition in order to compare and analyze the prediction accuracy according to four learning parameters of the LSTM model. Root mean square error (RMSE), Mean absolute error (MAE) and Volume error (VE) were calculated and evaluated its accuracy through comparing the predicted and observed inflows. We found that all the models had lower accuracy at high inflow rate and hourly precipitation data (2006~2018) of Yongdam Dam utilized as additional input variables to solve this problem. When the data of rainfall and inflow were utilized together, it was found that the accuracy of the prediction for the high flow rate is improved.

• Journal of Korean Society of Forest Science
• /
• v.85 no.2
• /
• pp.210-224
• /
• 1996

The SLODSVAT consists of interrelated submodels that simulate : the transfer of radiation, water vapour, sensible heat, carbon dioxide and momentum in two canopy layers determined by environmental conditions and ecophysiological properties of the vegetation ; uptake and storage of water in the "root-stem-leaf" system of plants ; interception of rainfall by the canopy layers and infiltration and storage of rain water in the four soil layers. A comparison of the results of modeling experiments and field micro-climatic observations in a spruce forest(Picea abies [L].Karst) in the Soiling hills(Germany) shows, that the SLODSVAT can describe and simulate the short-term(diurnal) as well as the long-term(seasonal) variability of water vapour and sensible heat fluxes adequately to natural processes under different environmental conditions. It proves that it is possible to estimate and predict the transpiration and evapotranspiration rates for spruce forest ecosystems on the patch and landscape scales for one vegetation period, if certain meteorological, botanical and hydrological information for the structure of the atmospheric boundary layer, the canopy and the soil are available.