• Computers and Concrete
• /
• v.32 no.6
• /
• pp.615-623
• /
• 2023

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

• Journal of the Korean Geographical Society
• /
• v.48 no.3
• /
• pp.366-386
• /
• 2013

This paper analyzes the drought and restriction on water supply in Taebaek City during the winter season in 2008 using Actor-Network Theory. Actor-Network Theory emphasizes and brings into view the role and act of non-human actors as well as human actors in various environmental issues. The fact that only Taebaek experienced restriction on water supply for 88 days although the winter season drought in 2008 affected the whole nation, requires a synthetic analysis of both human and non-human actors and their relationships and networks embedded in Taebaek City at that time. This paper shows that both human and non-human actors including Taebaek City Hall, Korea Water Resource Corporation, Taebaek citizen, the water supply facilities, Gwangdongdam, obsolete water pipes, the topography of Taebaek, soil, the change of industry, and population interact one another transforming the geography of water in Taebaek. This study helps to understand the complex processes related to drought disasters at a specific local scale and to provide appropriate measures to drought.

• Korean Journal of Remote Sensing
• /
• v.15 no.2
• /
• pp.107-117
• /
• 1999

A comparison of a neural network approach with the conventional statistical methods, multiple regression and band ratio analyses, for the estimation of water quality parameters in presented in this paper. The Landsat TM image of Lake Daechung acquired on March 18, 1996 and the thirty in-situ sampling data sets measured during the satellite overpass were used for the comparison. We employed a three-layered and feedforward network trained by backpropagation algorithm. A cross validation was applied because of the small number of training pairs available for this study. The neural network showed much more successful performance than the conventional statistical analyses, although the results of the conventional statistical analyses were significant. The superiority of a neural network to statistical methods in estimating water quality parameters is strictly because the neural network modeled non-linear behaviors of data sets much better.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.62 no.3
• /
• pp.1-13
• /
• 2020

The management of agricultural water can be divided into management of agricultural infrastructure and operation to determine the timing and quantity of water supply. The target of water management is classified as water-supply facilities, such as reservoirs, irrigation water supply, sluice gate control, and farmland. In the case of agricultural drought, there is a need for water supply capacity in reservoirs and for drought assessment in paddy fields that receive water from reservoirs. Therefore, it is necessary to analyze the water supply amount from intake capacity to irrigation canal network. The analysis of the irrigation canal network should be considered for efficient operation and planning concerning optimized irrigation and water allocation. In this study, we applied a hydraulic analysis model for agricultural irrigation networks by adding the functions of irrigation canal network analysis using the SWMM (Storm Water Management Model) module and actual irrigation water supply log data from May to August during 2015-2019 years in Sinsong reservoir. The irrigation satisfaction of ponding depth in paddy fields was analyzed through the ratio of the number of days the target ponding depth was reached for each fields. This hydraulic model can assist with accurate irrigation scheduling based on its simulation results. The results of evaluating the irrigation efficiency of water supply can be used for efficient water distribution and management during the drought events.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.09b
• /
• pp.1458-1459
• /
• 2005

• Proceedings of the Korea Water Resources Association Conference
• /
• 2001.05b
• /
• pp.1189-1194
• /
• 2001

• Proceedings of the Korea Water Resources Association Conference
• /
• 1998.05a
• /
• pp.499-504
• /
• 1998

• Proceedings of the Korea Water Resources Association Conference
• /
• 1999.05a
• /
• pp.731-736
• /
• 1999

• Proceedings of the Korea Water Resources Association Conference
• /
• 2000.05a
• /
• pp.879-884
• /
• 2000

• Journal of the Korean Society of Industry Convergence
• /
• v.16 no.3
• /
• pp.61-68
• /
• 2013

Long-term runoff model can be used to establish the effective plan of water reources allocation and the determination of the storage capacity of reservoir. So this study aims at the development of monthly runoff model using artificial neural network technique. For this, it was selected multi-layer neural network(MLN) and radial basis function neural network(RFN) model. In this study, it was applied model to analysis monthly runoff process at the Wi stream basin in Nakdong river which is representative experimental river basin of IHP. For this, multi-layer neural network model tried to construct input 3, hidden 7, and output 1 for each number of layer. As the result of analysis of monthly runoff process using models connected with artificial neural network technique, it showed that these models were effective in the simulation of monthly runoff.