A GIS System Integrated with Earthquake Vulnerability Assessment of RC Building

Ningthoujam, M.C.; Nanda, Radhikesh Prasad

doi:10.1016/j.istruc.2018.07.013

Cited by 14 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A rapid visual screening (RVS) method for reinforced concrete buildings is developed, implemented, and managed in the GIS in [70], exploiting data gathered during an intensive field survey, to elaborate a vulnerability scenario in terms of damage grade for a building stock in an urban area.…”

Section: State Of the Art About Gis-based Building Inventory For The ...mentioning

confidence: 99%

GIS Multisource Data for the Seismic Vulnerability Assessment of Buildings at the Urban Scale

2022

View full text Add to dashboard Cite

The paper presents a methodology of extraction, integration and elaboration of data from different sources using the geographic information system (GIS), to realize a georeferenced building database (GBD) useful for the seismic vulnerability assessment of existing buildings on a large scale. Three levels of GIS entities have been defined and equipped with the related information: census section (CS), urban block (UB), and individual building (IB), depending on the level of detail of dataset. Additional information about the typological and structural features has been extracted by CARTIS catalogue, to refine the data associated with each building. The data have been validated using detailed information gathered on a proper sample of buildings, which have been filed and analyzed one-by-one. The alphanumeric format of data allows for the automatic implementation of different methods available in the literature, which provide a qualitative seismic vulnerability index at different scales (whole urban district, an urban block, and a single building). Finally, the 3D representation of data and results have been elaborated, providing a tool easily searchable and constantly implementable. An application has been developed for a case study in Puglia, Italy: Bisceglie, for which 3726 IB have been assessed. The work addresses the issue of the lack of information typical of large-scale applications, exploiting all the available data sources to achieve nearly complete knowledge of existing building stock finalized to a rapid but extensive evaluation of the seismic vulnerability on an urban scale with very low computational efforts and the use of limited resources in terms of time and cost.

show abstract

Section: State Of the Art About Gis-based Building Inventory For The ...mentioning

confidence: 99%

GIS Multisource Data for the Seismic Vulnerability Assessment of Buildings at the Urban Scale

2022

View full text Add to dashboard Cite

show abstract

“…Similarly, Torres et al (2019) estimated the MBTs of buildings in Lorca, Spain based on calculated building attributes such as roof slope, building height, footprint area, and shape complexity. Instead of classifying buildings according to their MBTs, Ningthoujam & Nanda (2018) implemented a multiple regression analysis on the footprints in their test study area to estimate the damage grade of the existing reinforced concrete buildings which have already been mapped. The independent variables such as building age, number of storeys, construction quality, and maintenance condition were used to estimate the damage grade of each footprint which were then projected in a GIS to produce a vulnerability map.…”

Section: Building Vulnerability Estimationmentioning

confidence: 99%

“…Moreover, machine learning methods provide a means to automate data creation. Related studies have demonstrated how machine learning can be used for seismic vulnerability estimation (Geiß et al, 2015;Torres et al, 2019;Ningthoujam & Nanda, 2018). With LiDAR and machine learning combined, DRRM operations can be streamlined so that the resourceintensive mapping process of exposed and vulnerable infrastructures may be partially automated.…”

Section: Introductionmentioning

confidence: 99%

“…Geiß et al (2015),Torres et al (2019), andNingthoujam & Nanda (2018) reported the capability of machine learning methods for this specific purpose.Following their works, this study has conducted MBT prediction by implementing SVM, logistic regression, and RF classification. ; 'Low rise' = 1 to 2 storeys, 'Mid-rise' = 3 to 5 storeys, and 'High rise' = >5 storeys COMPLEXITY Shape complexity index (SCI); values range from 0 to 1 where SCI approaches 1 as the shape becomes more complex MBT Model building type classification; Reinforced concrete or masonry Shape_Length Perimeter of the building (in meters)…”

mentioning

confidence: 99%

See 1 more Smart Citation

Gis-Based Rapid Earthquake Exposure and Vulnerability Mapping Using Lidar Dem and Machine Learning Algorithms: Case of Porac, Pampanga

Santos

Principe

2021

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Disaster risk reduction and management (DRRM) not only requires a thorough understanding of hazards but also knowledge of how much built-up structures are exposed and vulnerable to a specific hazard. This study proposed a rapid earthquake exposure and vulnerability mapping methodology using the municipality of Porac, Pampanaga as a case study. To address the challenges and limitations of data access and availability in DRRM operations, this study utilized Light Detection and Ranging (LiDAR) data and machine learning (ML) algorithms to produce an exposure database and conduct vulnerability estimation in the study area. Buildings were delineated through image thresholding and classification of the normalized Digital Surface Model (nDSM) and an exposure database containing building attributes was created using Geographic Information System (GIS). ML algorithms such as Support Vector Machine (SVM), logistic regression, and Random Forest (RF) were then used to predict the model building type (MBT) of delineated buildings to estimate seismic vulnerability. Results showed that the SVM model yielded the lowest accuracy (53%) while logistic regression and RF models performed fairly (72% and 78% respectively) as indicated by their F-1 scores. To improve the accuracy of the exposure database and vulnerability estimation, this study recommends that the proposed building delineation process be further refined by experimenting with more appropriate thresholds or by conducting point cloud classification instead of pixel-based image classification. Moreover, ground truth MBT samples should be used as training data for MBT prediction. For future work, the methodology proposed in this study can be implemented when conducting earthquake damage assessments.

show abstract

“…Some conventional assessment techniques have been developed based on empirical principles. Ningthoujam and Nanda proposed a robust and straightforward approach to evaluating the safety of concrete buildings against earthquakes in India, considering features such as whether the buildings are soft story, their age, whether they have substantial overhang, and so on [8]. Khan et al employed a rapid visual screening approach of FEMA P-154 to assess the seismic vulnerability of existing buildings in Malakand, a region with an elevated risk [9].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Assessment of Damage Grade for Post-Earthquake Buildings: A Three-Stage Approach Directly Handling Categorical Features

Li,

Jia,

Chen

et al. 2023

Sustainability

View full text Add to dashboard Cite

The rapid assessment of post-earthquake building damage for rescue and reconstruction is a crucial strategy to reduce the enormous number of human casualties and economic losses caused by earthquakes. Conventional machine learning (ML) approaches for this problem usually employ one-hot encoding to cope with categorical features, and their overall procedure is neither sufficient nor comprehensive. Therefore, this study proposed a three-stage approach, which can directly handle categorical features and enhance the entire methodology of ML applications. In stage I, an integrated data preprocessing framework involving subjective–objective feature selection was proposed and performed on a dataset of buildings after the 2015 Gorkha earthquake. In stage II, four machine learning models, KNN, XGBoost, CatBoost, and LightGBM, were trained and tested on the dataset. The best model was judged by comprehensive metrics, including the proposed risk coefficient. In stage III, the feature importance, the relationships between the features and the model’s output, and the feature interaction effects were investigated by Shapley additive explanations. The results indicate that the LightGBM model has the best overall performance with the highest accuracy of 0.897, the lowest risk coefficient of 0.042, and the shortest training time of 12.68 s due to its relevant algorithms for directly tackling categorical features. As for its interpretability, the most important features are determined, and information on these features’ impacts and interactions is obtained to improve the reliability of and promote practical engineering applications for the ML models. The proposed three-stage approach can provide a reference for the overall ML implementation process on raw datasets for similar problems.

show abstract

A GIS System Integrated with Earthquake Vulnerability Assessment of RC Building

Cited by 14 publications

References 9 publications

GIS Multisource Data for the Seismic Vulnerability Assessment of Buildings at the Urban Scale

GIS Multisource Data for the Seismic Vulnerability Assessment of Buildings at the Urban Scale

Gis-Based Rapid Earthquake Exposure and Vulnerability Mapping Using Lidar Dem and Machine Learning Algorithms: Case of Porac, Pampanga

Machine Learning Assessment of Damage Grade for Post-Earthquake Buildings: A Three-Stage Approach Directly Handling Categorical Features

Contact Info

Product

Resources

About