• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.145-145
• /
• 2018

Small islands rely heavily on groundwater resources in addition to rainwater as the source of freshwater since surface water bodies are often absent. The groundwater resources are vulnerable to sea level rise, coastal flooding, saltwater intrusion, irregular pattern of precipitation resulting in long droughts and flash floods. Increase in population increases the demand for the limited groundwater resources, thus aggravating the problem. In this study, the effects of climate change on Tongatapu Island, Kingdom of Tonga, a small island in Pacific Ocean, are investigated using a sharp interface transient groundwater flow model. Twenty nine downscaled General Circulation Model(GCM) predictions are input to a water balance model to estimate the groundwater recharge. The temporal variation in recharge is predicted over the period of 2010 to 2099. A set of GCM models are selected to represent the ensemble of 29 models based on cumulative recharge at the end of the century. This set of GCM model predictions are then used to simulate a total of six climate scenarios, three each (2010-2039, 2040-2069, and 2070-2099) under RCP 4.5 and RCP 8.5. The impacts of predicted climate change on groundwater resources is evaluated in terms of freshwater volume changes and saltwater ratios in pumping wells compared to present conditions. Though the cumulative recharge at the end of the century indicates a wetter climate compared to the present conditions the large variability in rainfall pattern results in frequent periods of groundwater drought leading to saltwater intrusion in pumping wells. Thus for sustaining the limited groundwater resources in small islands, implementation of timely assessment and management practices are of utmost importance.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.4
• /
• pp.1-13
• /
• 2023

This study develops an optimal mobile-communication-based National Highway traffic volume estimation model using an ensemble-based machine learning algorithm. Based on information such as mobile communication data and VDS data, the LightGBM model was selected as the optimal model for estimating traffic volume. As a result of evaluating traffic volume estimation performance from 96 points where VDS was installed, MAPE was 8.49 (accuracy 91.51%). On the roads where VDS was not installed, traffic estimation accuracy was 92.6%.

• Geomechanics and Engineering
• /
• v.32 no.6
• /
• pp.583-600
• /
• 2023

The resilient modulus (M_R) of various pavement materials plays a significant role in the pavement design by a mechanistic-empirical method. The M_R determination is done by experimental tests that need time and money, along with special experimental tools. The present paper suggested a novel hybridized extreme gradient boosting (XGB) structure for forecasting the M_R of modified base materials subject to wet-dry cycles. The models were created by various combinations of input variables called deep learning. Input variables consist of the number of W-D cycles (WDC), the ratio of free lime to SAF (CSAFR), the ratio of maximum dry density to the optimum moisture content (DMR), confining pressure (σ₃), and deviatoric stress (σ_d). Two XGB structures were produced for the estimation aims, where determinative variables were optimized by particle swarm optimization (PSO) and black widow optimization algorithm (BWOA). According to the results' description and outputs of Taylor diagram, M1 model with the combination of WDC, CSAFR, DMR, σ₃, and σ_d is recognized as the most suitable model, with R² and RMSE values of BWOA-XGB for model M1 equal to 0.9991 and 55.19 MPa, respectively. Interestingly, the lowest value of RMSE for literature was at 116.94 MPa, while this study could gain the extremely lower RMSE owned by BWOA-XGB model at 55.198 MPa. At last, the explanations indicate the BWO algorithm's capability in determining the optimal value of XGB determinative parameters in M_R prediction procedure.

• Smart Media Journal
• /
• v.11 no.2
• /
• pp.9-17
• /
• 2022

The purpose of this study is to implement a predictive model to support decision-making to replace a starting pitcher before a crisis situation in a baseball game. To this end, using the Major League Statcast data provided by Baseball Savant, we implement a predictive model that preemptively replaces starting pitchers before a crisis situation. To this end, first, the crisis situation that the starting pitcher faces in the game was derived through data exploration. Second, if the starting pitcher was replaced before the end of the inning, learning was carried out by composing a label with a replacement in the previous inning. As a result of comparing the trained models, the model based on the ensemble method showed the highest predictive performance with an F1-Score of 65%. The practical significance of this study is that the proposed model can contribute to increasing the team's winning probability by replacing the starting pitcher before a crisis situation, and the coach will be able to receive data-based strategic decision-making support during the game.

• Computers and Concrete
• /
• v.33 no.1
• /
• pp.55-75
• /
• 2024

The present study introduces an optimum performance soft computing model for predicting the compressive strength of high-performance concrete (HPC) by comparing models based on conventional (kernel-based, covariance function-based, and tree-based), advanced machine (least square support vector machine-LSSVM and minimax probability machine regressor-MPMR), and deep (artificial neural network-ANN) learning approaches using a common database for the first time. A compressive strength database, having results of 1030 concrete samples, has been compiled from the literature and preprocessed. For the purpose of training, testing, and validation of soft computing models, 803, 101, and 101 data points have been selected arbitrarily from preprocessed data points, i.e., 1005. Thirteen performance metrics, including three new metrics, i.e., a20-index, index of agreement, and index of scatter, have been implemented for each model. The performance comparison reveals that the SVM (kernel-based), ET (tree-based), MPMR (advanced), and ANN (deep) models have achieved higher performance in predicting the compressive strength of HPC. From the overall analysis of performance, accuracy, Taylor plot, accuracy metric, regression error characteristics curve, Anderson-Darling, Wilcoxon, Uncertainty, and reliability, it has been observed that model CS4 based on the ensemble tree has been recognized as an optimum performance model with higher performance, i.e., a correlation coefficient of 0.9352, root mean square error of 5.76 MPa, and mean absolute error of 4.1069 MPa. The present study also reveals that multicollinearity affects the prediction accuracy of Gaussian process regression, decision tree, multilinear regression, and adaptive boosting regressor models, novel research in compressive strength prediction of HPC. The cosine sensitivity analysis reveals that the prediction of compressive strength of HPC is highly affected by cement content, fine aggregate, coarse aggregate, and water content.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.479-487
• /
• 2021

In this paper, we propose an Sound Event Detection (SED) model using self-training based on a noisy student model. The proposed SED model consists of two stages. In the first stage, a mean-teacher model based on an Residual Convolutional Recurrent Neural Network (RCRNN) is constructed to provide target labels regarding weakly labeled or unlabeled data. In the second stage, a self-training-based noisy student model is constructed by applying different noise types. That is, feature noises, such as time-frequency shift, mixup, SpecAugment, and dropout-based model noise are used here. In addition, a semi-supervised loss function is applied to train the noisy student model, which acts as label noise injection. The performance of the proposed SED model is evaluated on the validation set of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 Challenge Task 4. The experiments show that the single model and ensemble model of the proposed SED based on the noisy student model improve F1-score by 4.6 % and 3.4 % compared to the top-ranked model in DCASE 2020 challenge Task 4, respectively.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.18 no.1
• /
• pp.42-54
• /
• 2016

It is highly anticipated that warming temperature resulting from global climate change will affect the phenological pattern of kiwifruit, which has been commercially grown in Korea since the early 1980s. Here, we present the potential impacts of climate change on the variations of flowering day of a gold kiwifruit cultivar, Haegeum, in the Jeonnam Province, Korea. By running six global climate models (GCM), the results from this study emphasize the uncertainty in climate change scenarios. To predict the flowering day of kiwifruit, we obtained three parameters of the 'Chill-day' model for the simulation of Haegeum: $6.3^{\circ}C$ for the base temperature (Tb), 102.5 for chill requirement (Rc), and 575 for heat requirement (Rh). Two separate validations of the resulting 'Chill-day' model were conducted. First, direct comparisons were made between the observed flowering days collected from 25 kiwifruit orchards for two years (2014-15) and the simulated flowering days from the 'Chill-day' model using weather data from four weather stations near the 25 orchards. The estimation error between the observed and simulated flowering days was 5.2 days. Second, the model was simulated using temperature data extracted, for the 25 orchards, from a high-resolution digital temperature map, resulting in the error of 3.4 days. Using the RCP 4.5 and 8.5 climate change scenarios from six GCMs for the period of 2021-40, the future flowering days were simulated with the 'Chill-day' model. The predicted flowering days of Haegeum in Jeonnam were advanced more than 10 days compared to the present ones from multi-model ensemble, while some individual models resulted in quite different magnitudes of impacts, indicating the multi-model ensemble accounts for uncertainty better than individual climate models. In addition, the current flowering period of Haegeum in Jeonnam Province was predicted to expand northward, reaching over Jeonbuk and Chungnam Provinces. This preliminary result will provide a basis for the local impact assessment of climate change as more phenology models are developed for other fruit trees.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.471-480
• /
• 2023

The Korean construction order volume in South Korea grew significantly from 91.3 trillion won in public orders in 2013 to a total of 212 trillion won in 2021, particularly in the private sector. As the size of the domestic and overseas markets grew, the scale and complexity of EPC (Engineering, Procurement, Construction) projects increased, and risk management of project management and ITB (Invitation to Bid) documents became a critical issue. The time granted to actual construction companies in the bidding process following the EPC project award is not only limited, but also extremely challenging to review all the risk terms in the ITB document due to manpower and cost issues. Previous research attempted to categorize the risk terms in EPC contract documents and detect them based on AI, but there were limitations to practical use due to problems related to data, such as the limit of labeled data utilization and class imbalance. Therefore, this study aims to develop an AI model that can categorize the contract terms based on the FIDIC Yellow 2017(Federation Internationale Des Ingenieurs-Conseils Contract terms) standard in detail, rather than defining and classifying risk terms like previous research. A multi-text classification function is necessary because the contract terms that need to be reviewed in detail may vary depending on the scale and type of the project. To enhance the performance of the multi-text classification model, we developed the ELECTRA PLM (Pre-trained Language Model) capable of efficiently learning the context of text data from the pre-training stage, and conducted a four-step experiment to validate the performance of the model. As a result, the ensemble version of the self-developed ITB-ELECTRA model and Legal-BERT achieved the best performance with a weighted average F1-Score of 76% in the classification of 57 contract terms.

• Journal of Korea Water Resources Association
• /
• v.47 no.9
• /
• pp.825-838
• /
• 2014

The stationary Markov chain model has been widely used as a daily rainfall simulation model. A main assumption of the stationary Markov model is that statistical characteristics do not change over time and do not have any trends. In other words, the stationary Markov chain model for daily rainfall simulation essentially can not incorporate any changes in mean or variance into the model. Here we develop a Non-stationary hidden Markov chain model (NHMM) based stochastic downscaling scheme for simulating the daily rainfall sequences, using general circulation models (GCMs) as inputs. It has been acknowledged that GCMs perform well with respect to annual and seasonal variation at large spatial scale and they stand as one of the primary sources for obtaining forecasts. The proposed model is applied to daily rainfall series at three stations in Nakdong watershed. The model showed a better performance in reproducing most of the statistics associated with daily and seasonal rainfall. In particular, the proposed model provided a significant improvement in reproducing the extremes. It was confirmed that the proposed model could be used as a downscaling model for the purpose of generating plausible daily rainfall scenarios if elaborate GCM forecasts can used as a predictor. Also, the proposed NHMM model can be applied to climate change studies if GCM based climate change scenarios are used as inputs.

• Atmosphere
• /
• v.25 no.1
• /
• pp.155-167
• /
• 2015

A dynamical seasonal prediction system for boreal winter utilizing cryospheric information was developed. Using the Community Atmospheric Model, version3, (CAM3) as a modeling system, newly developed snow depth initialization method and sea ice concentration treatment were implemented to the seasonal prediction system. Daily snow depth analysis field was scaled in order to prevent climate drift problem before initializing model's snow fields and distributed to the model snow-depth layers. To maximize predictability gain from land surface, we applied one-month-long training procedure to the prediction system, which adjusts soil moisture and soil temperature to the imposed snow depth. The sea ice concentration over the Arctic region for prediction period was prescribed with an anomaly-persistent method that considers seasonality of sea ice. Ensemble hindcast experiments starting at 1st of November for the period 1999~2000 were performed and the predictability gain from the imposed cryospheric informations were tested. Large potential predictability gain from the snow information was obtained over large part of high-latitude and of mid-latitude land as a result of strengthened land-atmosphere interaction in the modeling system. Large-scale atmospheric circulation responses associated with the sea ice concentration anomalies were main contributor to the predictability gain.