• Earthquakes and Structures
• /
• v.9 no.3
• /
• pp.673-698
• /
• 2015

This paper investigates inelastic seismic demands of the normal component of near-fault pulse-like ground motions, which differ considerably from those of far-fault ground motions and also parallel component of near-fault ones. The results are utilized to improve the nonlinear static procedure (NSP) called Displacement Coefficient Method (DCM). 96 near-fault and 20 far-fault ground motions and the responses of various single degree of freedom (SDOF) systems constitute the dataset. Nonlinear Dynamic Analysis (NDA) is utilized as the benchmark for comparison with nonlinear static analysis results. Considerable influences of different faulting mechanisms are observed on inelastic seismic demands. The demands are functions of the strength ratio and also the pulse period to structural period ratio. Simple mathematical expressions are developed to consider the effects of near-fault motion and fault type on nonlinear responses. Modifications are presented for the DCM by introducing a near-fault modification factor, $C_N$. In locations, where the fault type is known, the modifications proposed in this paper help to obtain a more precise estimate of seismic demands in structures.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.224-224
• /
• 2015

The East Asia monsoon is one of the most complex atmospheric phenomena caused by Land-Sea thermal contrast. It plays essential role in fulfilling the water needs of the region but also poses stern consequences in terms of flooding and droughts. This study analyzed the influence of Global Sea Surface Temperature Anomalies (SSTA) on occurrence of droughts in the East Asia monsoon region ($20^{\circ}N-50^{\circ}N$, $103^{\circ}E-149^{\circ}E$). Standardized Precipitation Index (SPI) was employed to characterize the droughts over the region using 30-year (1978-2007) gridded rainfall dataset at $0.5^{\circ}$ grid resolution. Due to high variability in intensity and spatial extent of monsoon rainfall the East Asia monsoon region was divided into the homogeneous rainfall zones using cluster analysis method. Seven zones were delineated that showed unique rainfall regimes over the region. The influence of SSTA was assessed by using lagged-correlation between global gridded SSTA ($0.2^{\circ}$ grid resolution) and SPI of each zone. Sea regions with potential influence on droughts in different zones were identified based on significant positive and negative correlation between SSTA and SPI with a lag period of 3-month. The results showed that SSTA have the potential to be used as predictor variables for prediction of droughts with a reasonable lead time. The findings of this study will assist to improve the drought prediction over the region.

• Korean Journal of Remote Sensing
• /
• v.37 no.1
• /
• pp.111-122
• /
• 2021

Building footprint extraction is an active topic in the domain of remote sensing, since buildings are a fundamental unit of urban areas. Deep convolutional neural networks successfully perform footprint extraction from optical satellite images. However, semantic segmentation produces coarse results in the output, such as blurred and rounded boundaries, which are caused by the use of convolutional layers with large receptive fields and pooling layers. The objective of this study is to generate visually enhanced building objects by directly extracting the vertices of individual buildings by combining instance segmentation and keypoint detection. The target keypoints in building extraction are defined as points of interest based on the local image gradient direction, that is, the vertices of a building polygon. The proposed framework follows a two-stage, top-down approach that is divided into object detection and keypoint estimation. Keypoints between instances are distinguished by merging the rough segmentation masks and the local features of regions of interest. A building polygon is created by grouping the predicted keypoints through a simple geometric method. Our model achieved an F1-score of 0.650 with an mIoU of 62.6 for building footprint extraction using the OpenCitesAI dataset. The results demonstrated that the proposed framework using keypoint estimation exhibited better segmentation performance when compared with Mask R-CNN in terms of both qualitative and quantitative results.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.166-166
• /
• 2023

Compound hazards (CHs) are two or more extreme climate events combined which occur simultaneously in the same region at the same time. Compared to individual hazards, the combination of hazards that cause CHs can result in greater economic losses and deaths. While several extreme climate events have been recorded across Asia for the past decades, many studies have only focused on a single hazard. In this study, we assess the spatiotemporal pattern of dry compound hazards which includes drought, heatwave, fire and wind across Asia for the last 42 years (1980-2021) using the historical data from ERA5 Reanalysis dataset. We utilize a daily spatial data of each climate event to assess the occurrence of such compound hazards on a daily basis. Heatwave, fire and wind hazard occurrences are analyzed using daily percentile-based thresholds while a pre-defined threshold for SPI is applied for drought occurrence. Then, the occurrence of each type of compound hazard is taken from overlapping the map of daily occurrences of a single hazard. Lastly, a multivariate assessment are conducted to quantify the occurrence frequency, hotspots and trends of each type of compound hazard across Asia. By conducting a multivariate analysis of the occurrence of these compound hazards, we identify the relationships and interactions in dry compound hazards including droughts, heatwaves, fires, and winds, ultimately leading to better-informed decisions and strategies in the natural risk management.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.156-156
• /
• 2022

Explicitly spatially distributed and reliable data on industrial water demand is very much important for both policy makers and researchers in order to carry a region-specific analysis of water resources management. However, such type of data remains scarce particularly in underdeveloped and developing countries. Current research is limited in using different spatially available socio-economic, climate data and geographical data from different sources in accordance to predict industrial water demand at finer resolution. This study proposes a random forest regression (RFR) model to predict the industrial water demand at 0.50× 0.50 spatial resolution by combining various features extracted from multiple data sources. The dataset used here include National Polar-orbiting Partnership (NPP)/Visible Infrared Imaging Radiometer Suite (VIIRS) night-time light (NTL), Global Power Plant database, AQUASTAT country-wise industrial water use data, Elevation data, Gross Domestic Product (GDP), Road density, Crop land, Population, Precipitation, Temperature, and Aridity. Compared with traditional regression algorithms, RF shows the advantages of high prediction accuracy, not requiring assumptions of a prior probability distribution, and the capacity to analyses variable importance. The final RF model was fitted using the parameter settings of ntree = 300 and mtry = 2. As a result, determinate coefficients value of 0.547 is achieved. The variable importance of the independent variables e.g. night light data, elevation data, GDP and population data used in the training purpose of RF model plays the major role in predicting the industrial water demand.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.150-150
• /
• 2022

This study investigates the roles of decomposition methods on high accuracy in daily rainfall prediction from light gradient boosting machine (LightGBM) algorithm. Here, empirical mode decomposition (EMD) and singular spectrum analysis (SSA) methods were considered to decompose and reconstruct input time series into trend terms, fluctuating terms, and noise components. The decomposed time series from EMD and SSA methods were used as input data for LightGBM algorithm in two hybrid models, including empirical mode-based light gradient boosting machine (EMDGBM) and singular spectrum analysis-based light gradient boosting machine (SSAGBM), respectively. A total of four parameters (i.e., temperature, humidity, wind speed, and rainfall) at a daily scale from 2003 to 2017 is used as input data for daily rainfall prediction. As results from statistical performance indicators, it indicates that the SSAGBM model shows a better performance than the EMDGBM model and the original LightGBM algorithm with no decomposition methods. It represents that the accuracy of LightGBM algorithm in rainfall prediction was improved with the SSA method when using multivariate dataset.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.314-321
• /
• 2022

Depth information used in SLAM and visual odometry is essential in robotics. Depth information often obtained from sensors or learned by networks. While learning-based methods have gained popularity, they are mostly limited to RGB images. However, the limitation of RGB images occurs in visually derailed environments. Thermal cameras are in the spotlight as a way to solve these problems. Unlike RGB images, thermal images reliably perceive the environment regardless of the illumination variance but show lacking contrast and texture. This low contrast in the thermal image prohibits an algorithm from effectively learning the underlying scene details. To tackle these challenges, we propose multi-channel remapping for contrast. Our method allows a learning-based depth prediction model to have an accurate depth prediction even in low light conditions. We validate the feasibility and show that our multi-channel remapping method outperforms the existing methods both visually and quantitatively over our dataset.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.113-119
• /
• 2023

Most infrastructure structures were completed during periods of economic growth. The number of infrastructure structures reaching their lifespan is increasing, and the proportion of old structures is gradually increasing. The functions and performance of these structures at the time of design may deteriorate and may even lead to safety accidents. To prevent this repercussion, accurate inspection and appropriate repair are requisite. To this end, demand is increasing for computer vision and deep learning technology to accurately detect even minute cracks. However, deep learning algorithms require a large number of training data. In particular, label images indicating the location of cracks in the image are required. To secure a large number of those label images, a lot of labor and time are consumed. To reduce these costs as well as increase detection accuracy, this study proposed a learning structure based on mean teacher method. This learning structure was trained on a dataset of 900 labeled image dataset and 3000 unlabeled image dataset. The crack detection network model was evaluated on over 300 labeled image dataset, and the detection accuracy recorded a mean intersection over union of 89.23% and an F1 score of 89.12%. Through this experiment, it was confirmed that detection performance was improved compared to supervised learning. It is expected that this proposed method will be used in the future to reduce the cost required to secure label images.

• Earthquakes and Structures
• /
• v.7 no.2
• /
• pp.141-157
• /
• 2014

The Conditional Mean Spectrum represents a powerful link between the seismic hazard information and the selection of strong ground motion records at a particular site. The scope of the paper is to apply for the city of Bucharest for the first time the method to obtain the Conditional Mean Spectrum (CMS) presented by Baker (2011) and to select, on the basis of the CMS, a suite of strong ground motions for performing elastic and inelastic dynamic analyses of buildings and structures with fundamental periods of vibration in the vicinity of 1.0 s. The major seismic hazard for Bucharest and for most of Southern and Eastern Romania is dominated by the Vrancea subcrustal seismic source. The ground motion prediction equation developed for subduction-type earthquakes and soil conditions by Youngs et al. (1997) is used for the computation of the Uniform Hazard Spectrum (UHS) and the CMS. The disaggregation of seismic hazard is then performed in order to determine the mean causal values of magnitude and source-to-site distance for a particular spectral ordinate (for a spectral period T = 1.0 s in this study). The spectral period of 1.0 s is considered to be representative for the new stock of residential and office reinforced concrete (RC) buildings in Bucharest. The differences between the Uniform Hazard Spectrum (UHS) and the Conditional Mean Spectrum (CMS) are discussed taking into account the scarcity of ground motions recorded in the region of Bucharest and the frequency content characteristics of the recorded data. Moreover, a record selection based on the criteria proposed by Baker and Cornell (2006) and Baker (2011) is performed using a dataset consisting of strong ground motions recorded during seven Vrancea seismic events.