• Steel and Composite Structures
• /
• v.49 no.6
• /
• pp.645-666
• /
• 2023

Due to the steadily declining supply of natural coarse aggregates, the concrete industry has shifted to substituting coarse aggregates generated from byproducts and industrial waste. Oil palm shell is a substantial waste product created during the production of palm oil (OPS). When considering the usage of OPSC, building engineers must consider its uniaxial compressive strength (UCS). Obtaining UCS is expensive and time-consuming, machine learning may help. This research established five innovative hybrid AI algorithms to predict UCS. Aquila optimizer (AO) is used with methods to discover optimum model parameters. Considered models are artificial neural network (AO - ANN), adaptive neuro-fuzzy inference system (AO - ANFIS), support vector regression (AO - SVR), random forest (AO - RF), and extreme gradient boosting (AO - XGB). To achieve this goal, a dataset of OPS-produced concrete specimens was compiled. The outputs depict that all five developed models have justifiable accuracy in UCS estimation process, showing the remarkable correlation between measured and estimated UCS and models' usefulness. All in all, findings depict that the proposed AO - XGB model performed more suitable than others in predicting UCS of OPSC (with R², RMSE, MAE, VAF and A_15-index at 0.9678, 1.4595, 1.1527, 97.6469, and 0.9077). The proposed model could be utilized in construction engineering to ensure enough mechanical workability of lightweight concrete and permit its safe usage for construction aims.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.307-312
• /
• 1998

The paper first describes the atmospheric correction algorithm for the Ocean Color and Temperature Scanner (OCTS) visible band data used at Earth Observation Center (EOC) of National Space Development Agency of Japan (NASDA). It uses 10 candidate aerosol models including "Asian dust model" introduced in consideration of the unique feature of aerosols over the east Asian waters. Based on the observations at 670 and 865 nm bands where the reflectance of the water body can be discarded, the algorithm selects a pair of aerosol models that accounts best for the observed spectral reflectances to synthesize the aerosol reflectance in other bands. The paper also evaluates the performance of the algorithm by comparing the satellite estimates of water-leaving radiance and chlorophyll-a concentration with selected buoy-and ship-measured data. In comparison with the old CZCS-type atmospheric correction algorithm where the aerosol reflectance is as-sumed to be spectrally independent, the OCTS algorithm records factor 2-3 less error in estimating the normalized water-leaving radiances. In terms of chlorophyll-a concentration estimation, however, the accuracy stays vey similar compared to that of the CZCS-type algorithm. This is considered to be due to the nature of in-water algorithm which relies on spectral ratio of water-leaving radiances.

• Korean Journal of Remote Sensing
• /
• v.14 no.3
• /
• pp.262-276
• /
• 1998

The paper first describes the atmospheric correction algorithm for the Ocean Color and Temperature Scanner (OCTS) visible band data used at Earth Observation Center (EOC) of National Space Development Agenrr of japan (NASDA). It uses 10 candidate aerosol models including "Asian dust model" introduced in consideration of the unique feature of aerosols over the east Asian waters. Based on the observations at 670 and 865 nm bands where the reflectance of the water body can be discarded, the algorithm selects a pair of aerosol models that accounts best for the observed spectral reflectances to synthesize the aerosol reflectance in other bands. The paper also evaluates the performance of the algorithm by comparing the satellite estimates of water-leaving radiance and chlorophyll-a concentration with selected buoy- and ship-measured data. In comparison with the old CZCS-type atmospheric correction algorithm where the aerosol reflectance is assumed to be spectrally independent, the OCTS algorithm records factor 2-3 less error in estimating the normalized water-leaving radiances. In terms of chlorophyll-a concentration estimation, however, the accuracy stays very similar compared to that of the CZCS-type algorithm. This is considered to be due to the nature of in-water algorithm which relies on spectral ratio of water-leaving radiances.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.10
• /
• pp.49-60
• /
• 2010

Unsaturated permeability function is an important factor in the design and analysis of various unsaturated soil structures. Generally the permeability characteristics decrease as the mat ric suction increases and the trend is similar to water retention characteristics of a soil. The permeability of unsaturated soils can be obtained directly by laboratory tests or indirectly by estimation methods from other soil properties. For unsaturated soils sampled from 7 areas in KOREA, SWCCs and unsaturated permeability functions were obtained by experimental tests. The unsaturated permeability results were also compared with the unsaturated permeability functions derived from the SWCCs theoretically. However, the current estimation models of unsaturated permeability function did not express the unsaturated permeability characteristics. Therefore, the FXK-M permeability function was modified to predict more accurate permeability functions for Korean weathered soils using a correction factor that can be calculated from the air-entry value of SWCC. The new estimation model resulted in good agreements for all tested soils.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.32 no.E
• /
• pp.88-94
• /
• 1990

Several models physically based to predict the evolution of the snowpack have been proposed. Validity of these models for hourly estimation is, however, questionable, since they have been tested only on a daily basis. A computational model to predict the amount of snowpack on an hourly basis in terms of snowload from a set of meterological measurements was developed and investigated the rapid snowmelt conditions during Fohn events in the Takada plain.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2006.11a
• /
• pp.209-212
• /
• 2006

Line heating with water cooling is generally adapted process in the shipyards for the forming hull surface. The purpose of this paper is to develop a model of thermal deformation in water cooling process after the line heating. In order to simulate the cooling process, heat transfer analysis was performed by assuming the effects of water cooling as a negative heat-source. Experiment for the line heating with water cooling was performed for 9 models of plates in order to verify the cooling model. By using the suggested model for the water cooling process, it could be observed that the present method predict the plate deformations in the line heating more accurately.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.5
• /
• pp.565-574
• /
• 2009

The water vapor weighted vertically mean temperature(Tm) models, which were developed by the consideration of seasonal characteristics over the Korea, was used in the retrieval of precipitable water vapor (PWV) from GPS data which were observed at four GPS permanent stations. Since the weighted mean temperature relates to the water vapor pressure and temperature profile at a site, the accuracy of water vapor information which were estimated from GPS tropospheric wet delay is proportional to the accuracy of the weighted mean temperature. The adaption of Korean seasonal weighted mean temperature model, as an alternative to other formulae which are suggested from other nation, provides an improvement in the accuracy of the GPS PWV estimation. Therefore, it can be concluded that the seasonally appropriate weighted mean temperature model, which is used to convert actual zenith wet delay (ZWD) to the PWV, can be more reduced the relative biases of PWV estimated from GPS signal delays in the troposphere than other annual model, so that it would be useful for GPS PWV estimation with high accuracy.

• Journal of Wetlands Research
• /
• v.6 no.3
• /
• pp.47-54
• /
• 2004

A hydraulically and hydrologically based estimation method of pollutant delivery load for water quality modeling is proposed. The proposed method works on grid basis and routes overland flows from one cell to the next following the maximum downslope directions. The method is able to consider spatially-varied data of source pollutant, topography, land slopes, soil characteristics, land use and aspects, which can be extracted from geographic information systems (GIS) and from digital elevation models (DEMs). Because of this feature, the proposed method can be expected to be used for evaluating the impacts of various practices on watershed management for water quality.

• Journal of Korean Society of Water and Wastewater
• /
• v.24 no.5
• /
• pp.495-508
• /
• 2010

The aim of this study is to develop a quantified water loss Index to evaluate and manage leakage scientifically for the reduction of non-revenue water in water distribution systems. For the purpose, unavoidable background leakage suggested from UK water industry and IWA, and allowable water leakage in accord with the concept of allowable water loss are proposed by analyzing the inflow into two study water districts and the short-term water use of each customer in the districts. The study distribution areas are selected among the metered districts with good maintenance of leakage after improvement activities in Nonsan, medium sized city in Korea. Estimation models of allowable leakage are developed by metering and analyzing the minimum night flow at residential and commercial areas in the city. In the results of the investigation, it is estimated that background night flow in residential area was larger than that of commercial area where the types of business shows small water use characteristics. Meanwhile, night flow and background water loss on internal plumbing systems show great differences for each district which is influenced much by the water use characteristics and facilities scale. Based on metering water use data in various districts, leakage management criteria can be established under the consideration of domestic conditions in Korea by analyzing separated real water use and background leakage and it is possible to apply into presentation of optimal leakage level and reasonable time for working activities for leakage reduction.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.106-106
• /
• 2015

The information of flow regimes continues to be norm in water resource and watershed management, in that stream flow regime is a crucial factor influencing water quality, geomorphology, and the community structure of stream biota. The objectives of this study were to estimate Korean stream flows from landscape variables, classify stream flow gages using hydraulic characteristics, and then apply these methods to ungaged biological monitoring sites for effective ecological assessment. Here I used a linear modeling approach (MLR, PCA, and PCR) to describe and predict seasonal flow statistics from landscape variables. MLR models were successfully built for a range of exceedance discharges and time frames (annual, January, May, July, and October), and these models explained a high degree of the observed variation with r squares ranging from 0.555 (Q95 in January) to 0.899 (Q05 in July). In validation testing, predicted and observed exceedance discharges were all significantly correlated (p<0.01) and for most models no significant difference was found between predicted and observed values (Paired samples T-test; p>0.05). I classified Korean stream flow regimes with respect to hydraulic and hydrologic regime into four categories: flashier and higher-powered (F-HP), flashier and lower-powered (F-LP), more stable and higher-powered (S-HP), and more stable and lower-powered (S-LP). These four categories of Korean streams were related to with the characteristics of environmental variables, such as catchment size, site slope, stream order, and land use patterns. I then applied the models at 684 ungaged biological sampling sites used in the National Aquatic Ecological Monitoring Program in order to classify them with respect to basic hydrologic characteristics and similarity to the government's array of hydrologic gauging stations. Flashier-lower powered sites appeared to be relatively over-represented and more stable-higher powered sites under-represented in the bioassessment data sets.