• 한국농공학회논문집
• /
• 제65권1호
• /
• pp.15-26
• /
• 2023

This study aimed to evaluate the performance of water level classification from CCTV images in agricultural facilities such as reservoirs. Recently, the CCTV system, widely used for facility monitor or disaster detection, can automatically detect and identify people and objects from the images by developing new technologies such as a deep learning system. Accordingly, we applied the ResNet-50 deep learning system based on Convolutional Neural Network and analyzed the water level of the agricultural reservoir from CCTV images obtained from TOMS (Total Operation Management System) of the Korea Rural Community Corporation. As a result, the accuracy of water level detection was improved by excluding night and rainfall CCTV images and applying measures. For example, the error rate significantly decreased from 24.39 % to 1.43 % in the Bakseok reservoir. We believe that the utilization of CCTVs should be further improved when calculating the amount of water supply and establishing a supply plan according to the integrated water management policy.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2006년 창립20주년기념 정기학술대회 및 국제워크샵
• /
• pp.253-256
• /
• 2006

This paper shows the study on application of the law temperature energy in the deep seawater. Deep, cold seawater has long been recognized as a valuable ocean energy resource. Recently, research and experimentation has been conducted on energy systems using deep seawater: deep seawater air conditioning system, ice-making device, salt and fresh-water manufacturing system and the Spray freeze drying system for extracting valuable material of the deep seawater. They are technically and economically feasible today: once installed, the energy is inexhaustible and there are no adverse environmental impacts. Because of the economy of scale in the air conditioning system, the seawater A/C system is most appropriate for supplying multiple buildings or hotels in a coastal area.

• 한국수자원학회논문집
• /
• 제54권spc1호
• /
• pp.1061-1069
• /
• 2021

최근 이상 기후로 인해 극한 호우 및 국지성 호우의 규모 및 빈도가 증가하여 하천 주변의 홍수 피해가 증가하고 있다. 이에 따라 하천 또는 유역 내 수문학적 시스템의 비선형성이 증가하고 있으며, 기존의 물리적 기반의 수문 모형을 활용하여 홍수위를 예측하기에는 선행시간이 부족한 한계점이 존재한다. 본 연구에서는 Deep Neural Network (DNN) 및 Long Short-Term Memory (LSTM)기반의 딥러닝 기법을 적용하여 울산시(태화교) 지점의 수위를 0, 1, 2, 3, 6, 12시간에 대해 선행 예측을 수행하였고 예측 정확도를 비교 분석하였다. 그 결과 sliding window 개념을 적용한 DNN 모형이 선행시간 12시간까지 상관계수 0.97, RMSE 0.82 m로 가장 높은 정확도를 보이고 있음을 확인하였다. 향후 DNN 모형을 활용하여 딥러닝 기반의 수위 예측을 수행한다면 기존의 물리적 모형을 통한 홍수위 예측보다 향상된 예측 정확도와 충분한 선행시간을 확보할 수 있을 것으로 판단된다.

• 한국해양공학회지
• /
• 제22권2호
• /
• pp.34-41
• /
• 2008

As a basic study for developing a forecasting/estimating system that predicts water quality changes when Deep Sea Water (DSW) drains to the ocean after using it, this study was carried out as follows: 1) numerical simulation of the present state at DSW developing region in the East sea using SWEM, 2) numerical prediction of water quality changes by effluent DSW, 3) analysis of influence degree 'With defined DEI (DSW effect index) at F station. On the whole, when DSW drained to the ocean, Chl-a, COD and water-temperature were decreased and DIN, DIP and DO were increased by effluent DSW, and Salinity was steady. According to analysis of influence degree, the influence degree of DIN was the highest and it was high in order of Chl-a, COD, Water-temperature, DO, DIP and Salinity. The influence degree classified by DSW effluent position was predicted that suiface outflow was lower than bottom outflow. Ad When DSW discharge increased 10 times, the influence degree increased about $5{\sim}14$ times.

• 한국가시화정보학회지
• /
• 제19권2호
• /
• pp.41-47
• /
• 2021

River and stream are the important water supply source in our lives. Eutrophication causes excessive green algae growth including microcystis, which makes harmful to ecosystem and human health. Therefore, the water purification process to remove green algae is essential. In Korea, green algae alarm system exists depending on the concentration of green algae cells in river or stream. To maintain the growth amount under control, green algae monitoring system is being used. However, the unmanned, small and automatic monitoring system would be preferable. In this study, we developed the 3D printed device to measure the concentration of green algae cell using microfluidic droplet generator and deep learning. Deep learning network was trained by using transfer learning through pre-trained deep learning network. This newly developed microfluidic cell counter has sufficient accuracy to be possibly applicable to green algae alarm system.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1993년도 Proceedings of International Conference for Agricultural Machinery and Process Engineering
• /
• pp.994-1002
• /
• 1993

Soil deep loosening technique can improve the soil structure and increase the air permeability and water permeability of soil. It can increase the yield of crops in a large scale, particularly the plants with deep root system. This paper introduced the study on the deep loosening technique of sugarcance in Jinpen Farm where the soil is heavy caly with high ground water table. The implement and method of deep loosing, the experiments and results are include in this paper. The experimental results showed that the yield of sugarcane increased more than 20% after deep loosing.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2004년도 학술대회지
• /
• pp.7-12
• /
• 2004

Desalination system of revers osmosis(RO) membrane has been proven to be the most economical not only for the desalination of water containing salts, but also for the concentration of solute. RO membranes were traditionally made of inorganic polymers such. as cellulose acetate(CA), Polyamide(PA). To retain more minerals in deep ocean water, a new hybrid membrane composed of tourmaline film as organic material onto inorganic layer of CA polymer in asymmetric structure was developed for RO membrane process. The performance tests were carried out in the permeability of pure water and the rejection of NaCl solution to evaluate the adaptability for DOW desalination. The results of these basic tests show possibility to apply the new hybrid RO membrane for the desalination with function control.

• 자원환경지질
• /
• 제33권6호
• /
• pp.469-489
• /
• 2000

The hydrogeochemical and isotopic studies on deep groundwater (below a 550 m depth from the ground surface) in the Munkyeong area, Kyeongbuk province were carried out. Two types of deep groundwater (${CO_2}$-rich groundwater and alkali groundwater) occur together in the Munkywong area. ${CO_2}$-rich groundwater (Ca-${HCO_3}$ type) is characterized by low pH (5.8~6.5) and high TDS (up to 2,682 mg/L.), while alkali groundwater (Na-${HCO_3}$ type) shows a high pH (9.1~10.4) and relatively low TDS (72~116 mg/L). ${CO_2}$-rich water may have evolved by ${CO_2}$ added at depth during groundwater circulation. This process leads to the dissolution of surrounding rocks and Ca, Na, Mg, K and ${HCO_3}$ concentrations are eniched. The low $Pco_2$ ($10^{-6.4}$atm) of alkali groundwaters seems to result from the dissolution of silicate minerals without a supply of ${CO_2}$. The ${\delta}^{18}O$ and ${\delta}^D$values and tritium data indicate that two types of deep groundwater were both derived from pre-thermonuclear meteoric water and have evolved through prolonged water-rock interaction. The carbon isotope data show that dissolved carbon in the ${CO_2}$-rich water was possibly derived from deep-seated ${CO_2}$ gas, although further studies are needed. The ${\delta}^{34}S$ values of dissolved sulfate show that sulfate reduction occurred at great depths. The application of various chemical geothermometers on ${CO_2}$-rich groundwater shows that the calculated deep reservoir temperature is about 130~$l75^{\circ}C$. Based on the geological setting, water chemistry and environmental isotope data, each of the two types of deep groundwater represent distinct hydrologic and hydrogeochemical evolution at depth and their movement is controlled by the local fracture system.

• Ocean Systems Engineering
• /
• 제8권1호
• /
• pp.33-39
• /
• 2018

The paper presents a numerical underwater channel model developed in MATLAB for estimating the optical link budget between a light emitting diode (LED) based optical transmitter and a photo diode (PD) receiver when operated in the harbor, coastal and deep waters locations in the Bay of Bengal. The water samples are collected at different locations in the Bay of Bengal using a water sampler during an offshore research cruise. The optical attenuation, the main inherent parameter determining the range of the optical communication link is identified for the different waters using an underwater irradiance measurement system in the laboratory. The identified parameters are applied to the numerical model and found that a 10 W LED and a photo diode based system can provide the optical budget required for a horizontal underwater communication range of about 0.5, 14 and 35 m in the harbor, coastal and deep waters locations respectively. By increasing the transmitter power to 50 W, the operating range of the communication link could be increased up to 53 m in deep water locations in the Bay of Bengal.

• 생명과학회지
• /
• 제18권3호
• /
• pp.381-386
• /
• 2008

동해에서 취수한 해양심층수의 암예방 효능을 얄아보고자 암발생 억제물질의 생화학적 표식자(biochemical markers)인 CYP 1A2 활성, phase II 효소인 QR과 GST의 활성, GSH 함량 및 ODC 활성에 미치는 영향을 살펴보았다. 해양심층수는 암의 개시단계(initiation)를 유발시키는 것으로 알려진 CYP 1A2 활성을 경도의존적으로 저해시켰다. 해양심층수를 Hepa 1clc7 세포에 경도별$(100{\sim}1,000)$로 처리하였을 때 phase II 생체 해독효소인 QR과 GST의 활성은 최대 20%의 증가를 나타내었고, 외부의 독성물질이나 대사산물로부터 세포를 보호하는 역할을 하는 GSH의 함량은 $26{\sim}40%$의 증가를 나타내었다. 그리고 발암과정의 촉진/진행단계에 관여하는 ODC의 활성은 해양심층수의 경도 800과 1,000에서 20%와 35%의 저해율을 나타내었으며, 경도 1,000을 처리한 군에서는 양성대조군인 DFMO와 같은 저해율을 나타내었다. 그러므로 본 연구 결과에 의하면 동해 해양심층수는 발암과정과 관련된 개시 및 촉진/진행단계를 저해시켜 암예방 효능을 나타낼 것으로 사료된다.