• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.09a
• /
• pp.383-383
• /
• 2005

• 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.

• Korean Journal of Environmental Agriculture
• /
• v.40 no.4
• /
• pp.248-259
• /
• 2021

BACKGROUND: Contaminated water was a major source of food-borne pathogens in various recent fresh produce-related outbreaks. This study was conducted to investigate the microbial contamination level and correlations between the level of sanitary indicator bacteria and the detection ratio of pathogens in agricultural water by logistic regression analysis. METHODS AND RESULTS: Agricultural water was collected from 457 sites including surface water (n=300 sites) and groundwater (n=157 sites) in South Korea from 2018 to 2020. Sanitary indicator bacteria (total coliform, fecal coliform, and Escherichia coli) and food-borne pathogens (pathogenic E. coli, E. coli O157:H7, Salmonella spp., and Listeria monocytogenes) were analyzed. In surface water, the coliform, fecal coliform, and E. coli were 3.27±0.89 log CFU/100 mL, 1.90±1.19 log CFU/100 mL, and 1.39±1.26 log CFU/100 mL, respectively. For groundwater, three kinds of sanitary indicators ranged in the level from 0.09 - 0.57 log CFU/100 mL. Pathogenic E. coli, Salmonella and Listeria monocytogenes were detected from 3%-site, 1.5%- site, and 0.6%-site water samples, respectively. According to the results of correlations between the level of sanitary indicator bacteria and the detection ratio of pathogens by logistic regression analysis, the probability of pathogen detection increased individually by 1.45 and 1.34 times as each total coliform and E. coli concentration increased by 1 log CFU/100mL. The accuracy of the model was 70.4%, and sensitivity and specificity were 81.5% and 51.7%, respectively. CONCLUSION(S): The results indicate the need to manage the microbial risk of agricultural water to enhance the safety of fresh produce. In addition, logistic regression analysis is useful to analyze the correlation between the level of sanitary indicator bacteria and the detection ratio of pathogens in agricultural water.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.58 no.3
• /
• pp.47-56
• /
• 2016

Superabsorbent Polymers (SAPs) are hydrophilic synthetic polymers which could absorb water by hundreds of their own weight. They are used for multiple purpose including hygienic goods, soil conditioners, and hospital supplies. It is necessary to investigate the standard of their use including the amendment rate for soil application in agricultural fields. It is also important to understand their effects on the soil water content and engineering characteristics. The objective of this study is to find the water absorbing capacity and reusability of SAPs, and the characteristics of water release and effect of them on soil water content and engineering characteristics. In the result, SAPs per unit weight (1 g) used for this research could absorb about 200 g of water in max. The water absorbing capacity decreased after SAPs were used repeatedly. Released water of SAPs could provide the soils with about 9 % of the soil water content. Soil water content increased with decreasing distance from the SAPs. The distance of release was spreaded out with increasing water absorbed of SAPs. Finally, when a drainage and the capacity of soil water content were considered, it is recommended to amend the SAPs with soil by less than 0.25 %.

• Proceedings of the Korean Society of Rural Planning Conference
• /
• 1998.10a
• /
• pp.16-18
• /
• 1998

Fresh water lake was developed as a result of tidal land reclamation of the Sukmoon area. Water quality of lake has been monitored before and after sea-dike construction. Water quality degradation has been observed after Sukmoon sea-dike construction. In this paper observed water quality of the Sukmoon lake is presented and possible measures to improve water quality are also discussed.

• Journal of Soil and Groundwater Environment
• /
• v.27 no.2
• /
• pp.24-35
• /
• 2022

This study was conducted to estimate groundwater demand and supply for agricultural activities in a frequent-drought area that requires implementation of optimal distribution plan utilizing the well-network system (WNS). The WNS has been considered as a viable strategic way of supplying groundwater to farmlands by connecting groundwater wells physically or virtually. The study area heavily relied on groundwater resources for irrigation up to 53% due to a lack of surface water resources. Two kinds of methods, HOMWRS software and FAO approach, were used for estimating irrigation water requirements for paddy and upland fields, respectively. During the latest 10 years (2010~2019), the water requirements was estimated to be 1,106 m³/day. The requirements notably increased to 1,121~4,004 m³/day during active farming season (May to September), which exceeded the total yield capacity of pre-existing groundwater wells (2,356 m³/day) in the area. Detailed and definite determination for groundwater demand and supply helped to determine optimal scale parameters of WNS. The WNS has achieved more balanced distribution of groundwater resources for irrigation over the study area.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.314-314
• /
• 2022

In the production of rice flour, wet milling is a method of milling rice after soaking it in water, and it takes a lot of time and cost from milling to drying. To overcome this problem, the floury type rice was developed for dry milling and it is known to have round starch granules, low content of damaged starch after milling, and a starch structure similar to wheat. Because of its unique properties different from normal rice, it is necessary to research on processing and characteristics of floury-type rice to expand its utility in the food industry. Therefore, this study aimed to prepare the pregelatinized floury type rice (Baromi2) by autoclave and investigate their physicochemical properties. As the heat treatment time increased, the brightness decreased from 83.8 to 76.8, however, both redness and yellowness increased from 0.57 to 4.5 and from 14.58 to 21.13, respectively. Despite of same treatment time, soaking in water (10 min) before autoclaving increased the solubility and swelling power of Baromi2 over 2 times. The peak viscosity of native Baromi2 was over 2000 RVU, on the other hand, there was a significantly decrease to less than 1000 RVU of pregelatinized Baromi2. Heat treatment without immersion caused partial gelatinization of starch, resulting that some starch granules maintaining their integrity. Whereas there were no starch granules in heat treatment with soaking in water due to complete gelatinization. This study would be helpful to the suggestion of using heat-treated floury-type rice as an intermediate material in the food industry in the future.

• Korean Journal of Agricultural Science
• /
• v.47 no.3
• /
• pp.597-604
• /
• 2020

Exposure to heat stress (HS) has negative effects on pig production and health. Plasma concentrations of amino acids (AAs) can be used as indicators of HS. Therefore, this study was conducted to evaluate the effect of acute HS on feed intake, water drink, and plasma AAs in pigs. A total of 6 growing pigs (n = 6, 3 boars and 3 gilts) were raised in thermal neutral (TN; 25℃) conditions for the 5-d adaptation period as a control. After the adaptation, pigs were exposed to HS at 33℃ (HS33) for 24 h. All the pigs were fed the same diet formulated to meet or exceed predicted requirements during the whole experimental period. Blood samples were collected after the adaptation and heat treatment to verify the AAs. Measurements were the average daily feed intake (ADFI), average daily water intake (ADWI), water loss, tumor necrosis factor (TNF)-α, nitrate, total nitric oxide, and AAs in the plasma samples. Data were analyzed using the PROC GLM of SAS. HS33 had a lower ADFI (p < 0.05) and a tendency for an increased ADWI and water loss compared to TN. The level of TNF-α was significantly decreased (p < 0.05) in HS33. HS33 had a lower concentration of histidine and sarcosine compared to TN; however, there were no differences in the levels of nitrates and total nitric oxide. In conclusion, the results of this study show the differential effect of HS on the plasma concentration of AAs. We expect that the changed AAs could be potential indicators of HS.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.5
• /
• pp.61-72
• /
• 2017

The purpose of this study is to establish an integrated management system for the efficient management of rural water, to improve current problems, and to lay the foundations for active use of rural water information. We proposed a plan for informatization with a focus on establishing a database that can be used to provide customized services to users by applying advanced IT technology and to strengthen the management system of cities and counties with poor information. Data linkage and integration, user service development and integration system, application of IT technology, advanced decision support for rural water management, strengthening of city and county management system And the details of the implementation of the key project were presented.

• Journal of Environmental Impact Assessment
• /
• v.25 no.5
• /
• pp.357-368
• /
• 2016

Cambodia is the representative of developing country in Southeast Asia region. As a view point of water resource, Cambodia has in abundance but public sanitation problems persist in rural areas due to unsafe drinking water and untreated human waste. The purpose of this research is to prepare and develop new strategies for the water aid program in Cambodia by assessing, reviewing, and analyzing the present situation of water pollution for rural areas and the existing water use cycle in these regions. Pproyap and Langthle regions in Pursat province are selected as research areas. Cambodian's rural population in research areas relies on surface water stored in drinking-detention swamps, rain-water jars, and unprotected wells. The two types of main measures, thermotolerant coliform(TTC) bacteria and general pollutants, were conducted to assess the quality of selected water samples for research areas. TTC is a bacterial indicator of waterborne fecal contamination. For the 26 water samples, only one of the samples met the WHO standard for safe drinking water of 0 TTC colony forming units/100 mL.