• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.1
• /
• pp.1-13
• /
• 2024

This study assessed the efficacy of improving the accuracy of reservoir water level prediction models by employing automated machine learning models and efficient cross-validation methods for time-series data. Considering the inherent complexity and non-linearity of time-series data related to reservoir water levels, we proposed an optimized approach for model selection and training. The performance of twelve models was evaluated for the Obong Reservoir in Gangneung, Gangwon Province, using the TPOT (Tree-based Pipeline Optimization Tool) and four cross-validation methods, which led to the determination of the optimal pipeline model. The pipeline model consisting of Extra Tree, Stacking Ridge Regression, and Simple Ridge Regression showed outstanding predictive performance for both training and test data, with an R² (Coefficient of determination) and NSE (Nash-Sutcliffe Efficiency) exceeding 0.93. On the other hand, for predictions of water levels 12 hours later, the pipeline model selected through time-series split cross-validation accurately captured the change pattern of time-series water level data during the test period, with an NSE exceeding 0.99. The methodology proposed in this study is expected to greatly contribute to the efficient generation of reservoir water level predictions in regions with high rainfall variability.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.312-316
• /
• 2002

Satellite radar interferometry data shows a strong coherent signal on oyster sea farms where artificial structures installed on the bottom. We obtained 21 highly coherent interferograms from eleven JERS-1 SAR data sets despite of large orbital baseline (~2 km) or large temporal baseline (~l year). The phases observed in sea farms are probably induced by double bouncing on sea surface, and consequently reveal a tide height variation. To restore the absolute sea level changes we counted the number of wrapping by exploiting the intensity of backscattering. Backscattering intensity is closely correlated with the change in water surface height, while interferometry gives the detailed variation within the limit of 2$\pi$ (or 15.3 cm). Comparing the radar measurements with the tide gauge records yielded a correlation coefficient of 0.96 and an ms error of 6.0 cm. The results demostrate that radar interferometry is promising to measure sea level.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.27 no.1
• /
• pp.56-62
• /
• 2015

The potential impact of water temperature on sea level and air temperature rise in response to recent global warming has been noticed. To predict the effect of temperature change on river water quality and aquatic environment, it is necessary to understand and predict the change of water temperature. Air-water temperature relationship was analyzed using air temperature data at Buan and water temperature data of Shinsi, Garyeok, Mangyeong and Dongjin. Maximum and minimum water temperature was predicted by neural network and the results show a very high correlation between measured and predicted water temperature.

• Journal of Ecology and Environment
• /
• v.31 no.3
• /
• pp.213-223
• /
• 2008

The increasing area of abandoned rice fields could provide new opportunities for wetland restoration in Asia. However, it is unknown how quickly or completely abandoned rice fields will recover from agricultural disturbances. We assessed water quality and plant community succession in abandoned rice fields with different hydrology in a mountain valley to understand the effects of hydrological regime on recovery. Water level, soil redox potential, water quality, plant composition, and primary production were measured. The sites, coded as D6, N13, and N16, had been recovering for 6, 13, and 16 years by 2006. N13 and N16 have been recovering naturally whereas D6 has been drained with a nearby dike and was tilled in 2001. The typical hydroperiods of D6, N13, and N16 were no surface water, permanently flooded, and seasonally flooded, respectively. The major change in vegetation structure of both D6 and N13 was the replacement of herbaceous species by woody species. Drawdown accelerated this change because Salix koreensis grew better in damp conditions than in flooded conditions. Phragmites japonica reduced plot-level plant species richness. The removal efficiency of $NH_4-N$, $NO_3-N$, and $PO_4-P$ from water varied seasonally, ranging between -78.8 to 44.3%, 0 to 97.5%, and -26.0 to 44.4%, respectively. In summary, abandoned rice fields quickly became suitable habitat for native wetland plant species and improved regional water quality. Variation among our sites indicates that it is likely possible to manage abandoned rice fields, mostly through controlling hydrology, to achieve site-specific restoration goals.

• Journal of Environmental Impact Assessment
• /
• v.20 no.2
• /
• pp.249-256
• /
• 2011

Causing by green house gas emission, global warming is being accelerated significantly. This global warming cause world climate to change quiet different than before and we call this phenomenon is Climate Change. Environmental Impact Assessment being implemented in Korea is to prevent predicted environmental impacts from deteriorating within the domestic information and situation. As the climate change is getting severe, new meteorological records can be occurred which is exceeded existing statistical data. According to KMA(Korea Meteorological Administration) data, maximum value of precipitation and temperature in many regions changed with new data within last decade. And these events accompanied with landslides and flooding, and these also affected on water quality in rivers and lakes. According to impacts by climate change, disasters and accidents from heavy rain are the most apprehensive parts. And water pollution caused by overflowed non-point sources during heavy rain fall, fugitive dust caused by long-term drought, and sea level rise and Tsunami may affect on seaside industrial complex should be worth consideration. In this review, necessity of mutual consideration with influences of climate change was considered adding on existing guideline.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.3
• /
• pp.51-55
• /
• 2019

The loss of safety for reservoirs brought about by climate change and facility aging leads to reservoir failures, which results in the loss of lives and property damage in downstream areas. Therefore, it is necessary to provide a Reservoir Failure Forecasting System for downstream residents to detect the early signs of failure (with sensors) in real-time and perform safety management to prevent and minimize possible damage. For the verification of established water level management criteria, 10 water level data up to reservoir capacity was selected. Weight factor and trend line were applied to dramatic increase section of water level in the 1 year period data. The results shows that water level criteria based on three even parts shows less than 7% of standard deviation and it is appropriate to verify management criteria.

• YAKHAK HOEJI
• /
• v.51 no.4
• /
• pp.277-284
• /
• 2007

Hepatoprotective effects of the water extract of Protaetia brevitarsis larva (PB) was investigated in carbon tetrachloride ($CCI_{4}$) treated male Sprague-Dawley rats. PB administration protected rats against ALT, AST and LDH elevations induced by $CCI_{4}$, as well as the severity of liver damage. PB recovered the decrease in serum level of high-density lipoprotein-cholesterol and the increase in serum level of low-density lipoprotein-cholesterol induced by $CCI_{4}$. In histopathological observation, massive fatty change and necrosis in the centrilobular area, degenerative change including pyknosis of nucleus and swelling of parenchymal cell induced by $CCI_{4}$ were clearly protected by PB. These histopathological findings paralleled with the serum biochemical results. The present results demonstrated that the water extract of PB may have the hepatoprotective effect against $CCI_{4}$-induced liver damage in vivo.

• Journal of the Korean housing association
• /
• v.21 no.2
• /
• pp.41-48
• /
• 2010

This study shows how the water space outside the housing impacts the indoor thermal environment. CFD simulation was used for this experiment to analyze the interior environment focusing on the effect of temperature control and the thermal comfort. A shape of perfect square, which creates the very basic space formation, was used and the simulation was processed looking at the size, distance, and the location of the water space. The results of the experiment are as follows. Firstly, introducing a water space with the same floor area size of the simulation model decreased the indoor temperature by 1 Celsius (3.72%). It was determined the interior environment was considered as a comfort zone when the water space was greater than 70% of the floor area. Secondly, there was not much influence to the level of thermal comfort of the interior environment when the distance to the water space from the housing was greater than 2 meters. Lastly, interpreting the location of water space, the effect of controlling the total areas' temperature was the greatest following with the surrounding of the formation. There barely was any change to the temperature considering the side and the rear of the area.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.21 no.5
• /
• pp.380-390
• /
• 2009

This study was conducted as a part of investigating pre-reclamation shorelines from aerial photographs to estimate coastal land area at reclaimed lands (Anjeong industrial complex, Myeongji residental complex, and Noksan industrial complex), southeastern coast of Korea. To assess how the shorelines were suitable for the calculation of coastal lands, we constructed shoreline change data. Secondary ground control points were used to accomplish triangulation for old aerial photographs. Two kinds of shorelines were mapped; one was the shoreline based on approximately highest high water level (AHHWL) and the other was the high water line based on wet/dry signiture. These shorelines were consistent at artificial coast. Shoreline change data were built with a variety of levels of error due to detailed differences in the photograph scale, quality of image, type of ground control point and type of shoreline. Thus assessment of the pre-reclamation shorelines at the level of qualitative analysis for the trend of shoreline changes was satisfactory. Most of shoreline changes before reclamation in this study were associated with coastal development. Investigation of shoreline attributes in relation to aerial photographs allowed us to understand the shoreline changes.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.84-89
• /
• 2023

In water resource management, data prediction is performed using artificial intelligence, and companies, governments, and institutions continue to attempt to efficiently manage resources through this. LSTM is a model specialized for processing time series data, which can identify data patterns that change over time and has been attempted to predict groundwater level data. However, groundwater level data can cause sen-sor errors, missing values, or outliers, and these problems can degrade the performance of the LSTM model, and there is a need to improve data quality by processing them in the pretreatment stage. Therefore, in pre-dicting groundwater data, we will compare the LSTM model with the MSE and the model after normaliza-tion through distribution, and discuss the important process of analysis and data preprocessing according to the comparison results and changes in the results.