• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2431-2449
• /
• 2024

As problems such as water pollution and fish species depletion have become serious, a land-based fish farming is receiving a great attention for ensuring stable productivity. In the fish farming, it is important to determine the timing of shipments, as one of key factors to increase net profit on the aquaculture. In this paper, we propose a system for predicting net profit to support decision of timing of shipment using fish farming-related statistical data. The prediction system consists of growth and farm-gate price prediction models, a cost statistics table, and a net profit estimation algorithm. The Gaussian process regression (GPR) model is exploited for weight prediction based on the analysis that represents the characteristics of the weight data of cultured fish under the assumption of Gaussian probability processes. Moreover, the long short-term memory (LSTM) model is applied considering the simple time series characteristics of the farm-gate price data. In the case of GPR model, it allows to cope with data missing problem of the weight data collected from the fish farm in the time and temperature domains. To solve the problem that the data acquired from the fish farm is aperiodic and small in amount, we generate the corresponding data by adopting a data augmentation method based on the Gaussian model. Finally, the estimation method for net profit is proposed by concatenating weight, price, and cost predictions. The performance of the proposed system is analyzed by applying the system to the Korean flounder data.

• Journal of Cadastre & Land InformatiX
• /
• v.47 no.1
• /
• pp.127-142
• /
• 2017

The purpose of this study is to examine the status of urbanization of Namyangju-Si from 2001 till 2008, analyze the correlation of the change of surrounding land use according to the change of accessibility and analyze the correlation of the change of land use. Based on the result from correlation analysis, I simulated from the view point of interactions between agents of land use and transportation accessibility by using MAS. I tried to forecast, based on space, the change of surrounding land use caused by the change of accessibility. I conducted landscape analysis by using a land registration map. Also, I conducted GIS analysis statistical analysis simulation analysis of traffic data, land use data in order to analyze the correlation of the change of surrounding land use according to the change of accessibility. I could find out a certain pattern that new roads and railroads causes the within 500m adjacent land to change into urban land use, which led me to construct a system through which land use changing phenomenon can be expected according to the change of accessibility. It is expected that it can make the best use of selecting the location where new transportation facilities are constructed.

• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.463-471
• /
• 2008

The quality of orthoimages mainly depends on the elevation information and exterior orientation (EO) parameters. Since LiDAR data directly provides the elevation information over the earth's surface including buildings and trees, the concept of true orthorectification has been rapidly developed and implemented. If a LiDAR-driven digital surface model (DSM) is used for orthorectification, the displacements caused by trees and buildings are effectively removed when compared with the conventional orthoimages processed with a digital elevation model (DEM). This study utilized LiDAR data to generate orthorectified digital aerial images. Experimental orthoimages were produced using digital terrain model (DTM) and DSM. For the preparation of orthorectification, EO components, one of the inputs for orthorectification, were adjusted with the ground control points (GCPs) collected from the LiDAR point data, and the ground points were extracted by a filtering method used in a previous research. The orthoimage generated by DSM corresponded more closely to non-ground LiDAR points than the orthoimage produced by DTM.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.3
• /
• pp.11-19
• /
• 2014

This study is analyze future climate and land cover change affects behaviors for amount of streamflow and sediment discharge within basin. We used the climate forecast data in RCP 4.5 and 8.5 (2011-2100) which is opposite view for each other among RCP scenarios that are discussed for 5th report for IPCC. Land cover map built based on a social economic storyline in RCP 4.5/8.5 using Logistic Regression model. In this study we set three scenarios: one scenario for climate change only, one for land cover change only, one for Last both climate change and land cover change. It simulated amount of streamflow and sediment discharge and the result showed a very definite change in the seasonal variation both of them. For climate change, spring and winter increased the amount of streamflow while summer and fall decreased them. Sediment showed the same pattern of change steamflow. Land cover change increases the amount of streamflow while it decreases the amount of sediment discharge, which is believed to be caused by increase of impervious Surface due to urbanization. Although land cover change less affects the amount of streamflow than climate change, it may maximize problems related to the amount of streamflow caused by climate change. Therefore, it's required to address potential influence from climate change for effective water resource management and prepare suitable measurement for water resource.

• Journal of Forest and Environmental Science
• /
• v.40 no.1
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.4
• /
• pp.71-80
• /
• 2011

A simple and an improved methods for the assessment of flood damage were used in previous studies, and the Multi-Dimensional Flood Damage Assessment (MD-FDA) has been applied since 2004 in Korea. This study evaluated flood damage of dam downstream using considering MD-FDA method based on GIS data. Firstly, flood water level with FLDWAV (Flood Wave routing) model was input into cross section layer based on enforcement drainage algorithm, water depth grid data were created through spatial calculation with DEM data. The value of asset of building and agricultural land according to local government was evaluated using building layer from digital map and agricultural land map from landcover map. Also, itemized flood damage was calculated by unit price to building shape, evaluated value of housewares to urban type, unit cost to crop, tangible and inventory asset of company connected with building, agricultural land, flooding depth layer. Flood damage in rainfall frequency of 200 year showed 1.19, 1.30 and 1.96 times to flood damage in rainfall frequency of 100 year, 50 year and 10 year respectively by flood damage analysis.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.49 no.5
• /
• pp.67-77
• /
• 2007

The images of MODerate resolution Imaging Spectroradiometer (MODIS) that provide wider swath and shorter revisit frequency than Land Satellite (Landsat) and Satellite Pour I' Observation de la Terre (SPOT) has been used fer land cover classification with better spatial resolution than National Oceanic and Atmosphere Administration/Advanced Very High Resolution Radiometer (NOAA/AVHRR)'s images. Due to the advantages of MODIS, several researches have conducted, however the results for the land cover classification using MODIS images have less accuracy of classification in small areas because of low spatial resolution. In this study, uncertainty of paddy fields classification using MODIS images was conducted in the region of Gyeonggi-do and the relation between this uncertainty of estimating paddy fields and topographical factors was also explained. The accuracy of classified paddy fields was compared with the land cover map of Environmental Geographic Information System (EGIS) in 2001 classified using Landsat images. Uncertainty of paddy fields classification was analyzed about the elevation and slope from the 30m resolution Digital Elevation Model (DEM) provided in EGIS. As a result of paddy classification, user's accuracy was about 41.5% and producer's accuracy was 57.6%. About 59% extracted paddy fields represented over 50 uncertainty in one hundred scale and about 18% extracted paddy fields showed 100 uncertainty. It is considered that several land covers mixed in a MODIS pixel influenced on extracted results and most classified paddy fields were distributed through elevation I, II and slope A region.

• Journal of Ecology and Environment
• /
• v.40 no.2
• /
• pp.107-119
• /
• 2016

Background: Previous studies on the biological integrity on habitat and landuse patterns demonstrated ecological stream health in the view of regional or macrohabitat scale, thus ignored the mesoscale habitat patterns of pool, riffle, and runs in the stream health analysis. The objective of this study was to analyze influences on the mesohabitat structures of pool, riffle, and run reaches on the fish guilds and biological integrity in Geum-River Watershed. Results: The mesohabitat structures of pool, riffle, and run reaches influenced the ecological stream health along with some close relations on the fish trophic and tolerance guilds. The mesoscale components altered chemical water quality such as nutrients (TN, TP) and BOD and these, then, determined the primary productions, based on the sestonic chlorophyll-a. The riffle-reach had good chemical conditions, but the pool-reach had nutrient enrichments. The riffle-reach had a predominance of insectivores, while the pool-reach has a predominance of omnivores. Also, the riffle-reach had high proportions of sensitive fish and insectivore fish, and the pool-reach had high proportions of tolerant species in the community composition. The intermediate fish species in tolerance and omnivorous fish species in the food linkage dominated the community in the watershed, and the sensitive and insectivorous fishes decreased rapidly with a degradation of the water quality. All the habitat patterns were largely determined by the land-use patterns in the watershed. Conclusions: Trophic guilds and tolerance guilds of fish were determined by land-use pattern and these determined the stream health, based on the Index of Biological Integrity. This study remarks the necessity to include additional variables to consider information provided by mesohabitats and land-use distributions within the selected stream stretch. Overall, our data suggest that land-use pattern and mesohabitat distribution are important factors to be considered for the trophic and tolerance fish compositions and chemical gradients as well as ecological stream health in the watershed.

• The Journal of Engineering Geology
• /
• v.31 no.3
• /
• pp.269-281
• /
• 2021

Land creeping is the imperceptibly slow, steady, downward movement o f slope-forming soil or rock. Because creep-related failures occur frequently on a large scale without notice, they can be hazardous to both property and human life. Korea Forest Service has operated the prevention and response system from land creeping which has been on the rise since 2018. We categorized and proposed three survey steps (e.g., preliminary, regional, detailed) for investigation of creeping susceptibility site with a focus on geophysical mapping of a selected test site, Yongheung-dong, Pohang, Korea. The combination of geophysical (dipole-dipole electrical resistivity tomography and reciprocal seismic refraction technique, well-logging), geotechnical studies (standard penetrating test, laboratory tests), field mapping (tension cracks, uplift, fault), and comprehensive interpretation of their results provided the reliable information of the subsurface structures including the failure surface. To further investigate the subsurface structure including the sliding zone, we performed high-resolution geophysical mapping in addition to the regional survey. High-resolution seismic velocity structures are employed for stability analysis because they provided more simplified layers of weathering rock, soft rock, and hard rock. Curved slip plane of the land creeping is effectively delineated with a shape of downslope sliding and upward pushing at the apex of high resistive bedrock in high-resolution electrical resistivity model with clay-mineral contents taken into account. Proposed survey steps and comprehensive interpretation schemes of the results from geological, geophysical, and geotechnical data should be effective for data sets collected in a similar environment to land-creeping susceptibility area.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.1
• /
• pp.21-36
• /
• 2023

Activity-based modeling systems have increasingly been developed to address the limitations of widely used traditional four-step transportation demand forecasting models. Accordingly, this paper introduces the Activity-BAsed Traveler Analyzer (ABATA) system. This system consists of multiple components, including an hourly total population estimator, activity profile constructor, hourly activity population estimator, spatial activity population estimator, and origin/destination estimator. To demonstrate the proposed system, the emission impact of land use changes in the 5-1 block Sejong smart city is evaluated as a case study. The results indicate that the land use with the scenario of work facility dispersed plan produced more emissions than the scenario of work facility centralized plan due to the longer travel distance. The proposed ABATA system is expected to provide a valuable tool for simulating the impacts of future changes in population, activity schedules, and land use on activity populations and travel demands.