• Computers and Concrete
• /
• v.11 no.4
• /
• pp.337-350
• /
• 2013

The sensitivity of compressive strength of no-slump concrete to its ingredient materials and proportions, necessitate the use of robust models to guarantee both estimation and generalization features. It was known that the problem of compressive strength prediction owes high degree of complexity and uncertainty due to the variable nature of materials, workmanship quality, etc. Moreover, using the chemical and mineral additives, superimposes the problem's complexity. Traditionally this property of concrete is predicted by conventional linear or nonlinear regression models. In general, these models comprise lower accuracy and in most cases they fail to meet the extrapolation accuracy and generalization requirements. Recently, artificial intelligence-based robust systems have been successfully implemented in this area. In this regard, this paper aims to investigate the use of optimized support vector machine (SVM) to predict the compressive strength of no-slump concrete and compare with optimized neural network (ANN). The results showed that after optimization process, both models are applicable for prediction purposes with similar high-qualities of estimation and generalization norms; however, it was indicated that optimization and modeling with SVM is very rapid than ANN models.

• Structural Engineering and Mechanics
• /
• v.83 no.3
• /
• pp.401-413
• /
• 2022

The collapse of civil infrastructure due to natural disasters results in financial losses and many casualties. In particular, the recent increase in earthquake activities has highlighted on the importance of assessing the seismic performance and predicting the seismic risk of a structure. However, the nonlinear behavior of a structure and the uncertainty in ground motion complicate the accurate seismic response prediction of a structure. Artificial intelligence can overcome these limitations to reasonably predict the nonlinear behavior of structures. In this study, a deep learning-based algorithm was developed to estimate the time-history seismic response of bridge structures. The proposed deep neural network was trained using structural and ground motion parameters. The performance of the seismic response prediction algorithm showed the similar phase and magnitude to those of the time-history analysis in a single-degree-of-freedom system that exhibits nonlinear behavior as a main structural element. Then, the proposed algorithm was expanded to predict the seismic response and fragility prediction of a bridge system. The proposed deep neural network reasonably predicted the nonlinear seismic behavior of piers and bearings for approximately 93% and 87% of the test dataset, respectively. The results of the study also demonstrated that the proposed algorithm can be utilized to assess the seismic fragility of bridge components and system.

• Magazine of the Korea Concrete Institute
• /
• v.10 no.6
• /
• pp.149-159
• /
• 1998

The reasonable prediction of time-dependent deformation of prestressed concrete(PSC) box girder bridges is very important for accurate construction as well as good serviceability. The long-term behavior is mostly influenced by the probabilistic characteristic of creep and shrinkage. This paper presents a method of statistical analysis and sensitivity analysis of creep and shrinkage effects in PSC box been taken into account - model uncertainty, parameter variation and environmental condition. The statistical and sensitivity analyses are performed by using the numerical simulation of Latin Hypercube sampling. For each sample, the time-dependent structural analysis is performed to produce response data, which are then statistically analyzed. The probabilistic prediction of the confidence limits on long-term effects of creep and shrinkage is then expressed. Three measure are examined to quantify the sensitivity of the outputs of each of the input variables. These are rank correlation coefficient(RCC), partical rank correlation coefficient(PRCC) and standardiozed rank regression coefficient(SRRC) computed on the ranks of the observations. Three creep and shrinkage models - i. e., ACI model. CEB-FIP model and the model in Korea Highway Bridge Specification - are studied. The creep model uncertainy factor and the relative humidity appear to be the most dominant factors with regard to the model output uncertainty.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.149-153
• /
• 2006

Precipitation is the most important component and critical to the study of water and energy cycle. This study investigates the propagation of precipitation retrieval uncertainty in the simulation of hydrologic variables for varying spatial resolution on two different vegetation cover. We explore two remotely sensed rain retrievals (space-borne IR-only and radar rainfall) and three spatial grid resolutions. An offline Community Land Model (CLM) was forced with in situ meteorological data In turn, radar rainfall is replaced by the satellite rain estimates at coarser resolution $(0.25^{\circ},\;0.5^{\circ}\;and\;1^{\circ})$ to determine their probable impact on model predictions. Results show how uncertainty of precipitation measurement affects the spatial variability of model output in various modelling scales. The study provides some intuition on the uncertainty of hydrologic prediction via interaction between the land surface and near atmosphere fluxes in the modelling approach.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.4
• /
• pp.1651-1664
• /
• 2013

Precise analysis on deterioration processes of road pavements is not so simple matter due to severe uncertainty originated from a lot of explanatory variables engaged in. For those reasons, most analytical models for pavement deterioration prediction have often preferred to probabilistic approaches than deterministic models. However, the general probabilistic approaches that treat overall characteristics of population or entire sample would not be suitable for providing detail or localized information on their changing process. Considering the aspects, this paper aimed to suggest a stochastic disaggregation method to analyze the localized deterioration speeds and its variances changed by time and condition states. In addition, life expectancies and their uncertainty were estimated by probabilistic algorithm using the disaggregated stochastic process. For an empirical study, pavement inspection data (crack) accumulated from 2003 to 2010 from Korean national highway network was applied. This study can contribute to securing reliability of life cycle cost analysis, which is one of the primary analyses in road asset management, with much advanced deterioration forecasting functions. In addition, it would be meaningful trials as fundamental research for preventive maintenance strategy that demands essential understanding on changing process of the deterioration speed of pavement.

• Fire Science and Engineering
• /
• v.33 no.3
• /
• pp.112-120
• /
• 2019

To improve the reliability of a safety assessment using a fire simulation in domestic PBD, the evaluation method of ASET considering the uncertainties of the input parameters and numerical model of fire simulation was carried out. To this end, a cinema and officetel were selected as the representative fire spaces. The main results were as follows. Considering the uncertainty of the heat release rate, which has the greatest effect on the major physical quantities presented in the life safety standard, significant changes in temperature, CO, and visibility occurred. In addition, when the bias factors reflecting the uncertainty of the numerical model were applied, there were no significant changes in temperature and CO concentration. On the other hand, the visibility was increased considerably due to the low prediction performance of smoke concentration in FDS. Finally, the reason why the physical quantity determining the ASET in domestic PBD is mainly visibility was discussed, and the application of uncertainty of the input parameters and numerical model in a fire simulation was suggested for an accurate ASET evaluation.

• Asian Journal of Atmospheric Environment
• /
• v.8 no.4
• /
• pp.212-224
• /
• 2014

There are several studies on the effects of emissions of highly reactive volatile organic compounds (HRVOC) from the industrial sources in the Houston-Galveston-Brazoria (HGB) area on the high ozone events during the Texas Air Quality Study (TexAQS) in summer of 2000. They showed that the modeled atmosphere lacked reactivity to produce the observed high ozone event and suggested "imputation" of HRVOC emissions from the base inventory. Byun et al. (2007b) showed the imputed inventory leads to too high ethylene concentrations compared to the measurements at the chemical super sites but still too little aloft compared to the NOAA aircraft. The paper suggested that the lack of reactivity in the modeled Houston atmosphere must be corrected by targeted, and sometimes of episodic, increase of HRVOC emissions from the large sources such as flares in the Houston Ship Channel (HSC) distributed into the deeper level of the boundary layer. We performed retrospective meteorological and air quality modeling to achieve better air quality prediction of ozone by comparison with various chemical and meteorological measurements during the Texas Air Quality Study periods in August-September 2006 (TexA QS-II). After identifying several shortcomings of the forecast meteorological simulations and emissions inputs, we prepared new retrospective meteorological simulations and updated emissions inputs. We utilized assimilated MM5 inputs to achieve better meteorological simulations (detailed description of MM5 assimilation can be found in F. Ngan et al., 2012) and used them in this study for air quality simulations. Using the better predicted meteorological results, we focused on the emissions uncertainty in order to capture high peak ozone which occasionally happens in the HGB area. We described how the ozone predictions are affected by emissions uncertainty in the air quality simulations utilizing different emission inventories and adjustments.

• Journal of the Korean Geographical Society
• /
• v.44 no.3
• /
• pp.395-409
• /
• 2009

The objective of this paper is to illustrate that kriging can provide an effective framework both for integrating remote sensing data and for uncertainty modeling through a case study of sediment grain size mapping with remote sensing data. Landsat TM data which show reasonable relationships with grain size values are used as secondary information for sediment grain size mapping near the eastern part of Anmyeondo and Cheonsuman bay. The case study results showed that uncertainty attached to prediction at unsampled locations was significantly reduced by integrating remote sensing data through the analysis of conditional variance from conditional cumulative distribution functions. It is expected that the kriging-based approach presented in this paper would be efficient integration and analysis methodologies for any environmental thematic mapping using secondary information as well as sediment grain size mapping.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.55 no.4
• /
• pp.55-63
• /
• 2013

This study investigates the trends and uncertainty of the impacts of climate change on paddy rice production in the Geumho river basin. The Long Ashton Research Station stochastic Weather Generator (LARS-WG) was used to derive future climate data for the Geumho river basin from 15 General Circulation models (GCMs) for 3 Special Report on Emissions Scenarios (SRES) (A2, A1B and B1) included in the Intergovernmental Panel on Climate Change (IPCC) 4th assessment report. The Food and Agricultural Organization (FAO) AquaCrop, a water-driven crop model, was statistically calibrated for the 1982 to 2010 climate. The index of agreement (IoA), prediction efficiency ($R^2$), percent bias (PBIAS), root mean square error (RMSE) and a visual technique were used to evaluate the adjusted AquaCrop simulated yield values. The adjusted simulated yields showed RMSE, NSE, IoA and PBIAS of 0.40, 0.26, 0.76 and 0.59 respectively. The 5, 9 and 15 year central moving averages showed $R^2$ of 0.78, 0.90 and 0.96 respectively after adjustment. AquaCrop was run for the 2020s (2011-2030), 2050s (2046-2065) and 2090s (2080-2099). Climate change projections for Geumho river basin generally indicate a hotter and wetter future climate with maximum increase in the annual temperature of $4.5^{\circ}C$ in the 2090s A1B, as well as maximum increase in the rainfall of 45 % in the 2090s A2. The means (and ranges) of paddy rice yields are projected to increase by 21 % (17-25 %), 34 % (27-42 %) and 43 % (31-54 %) for the 2020s, 2050s and 2090s, respectively. The A1B shows the largest rice yield uncertainty in all time slices with standard deviation of 0.148, 0.189 and $0.173t{\cdot}ha^{-1}$ for the 2020s, 2050s and 2090s, respectively.

• Journal of Korean Society on Water Environment
• /
• v.36 no.6
• /
• pp.568-580
• /
• 2020

Calibrating a conceptual hydrologic model necessitates selection of a calibration period that produces the most reliable prediction. This often must be chosen randomly, however, since there is no objective guidance. Observation plays the most important role in the calibration or uncertainty evaluation of hydrologic models, in which the key factors are the length of the data and the hydro-climate conditions in which they were collected. In this study, we investigated the effect of the calibration period selected on the predictive performance and uncertainty of a model. After classifying the inflows of the Hapcheon Dam from 1991 to 2019 into four hydro-climate conditions (dry, wet, normal, and mixed), a conceptual hydrologic partitioning model was calibrated using data from the same hydro-climate condition. Then, predictive performance and post-parameter statistics were analyzed during the verification period under various hydro-climate conditions. The results of the study were as follows: 1) Hydro-climate conditions during the calibration period have a significant effect on model performance and uncertainty, 2) calibration of a hydrologic model using data in dry hydro-climate conditions is most advantageous in securing model performance for arbitrary hydro-climate conditions, and 3) the dry calibration can lead to more reliable model results.