Earthquake Hazard Safety Assessment of Existing Buildings Using Optimized Multi-Layer Perceptron Neural Network

Harirchian, Ehsan; Lahmer, Tom; Rasulzade, Shahla

doi:10.3390/en13082060

Cited by 36 publications

(23 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, remote sensing imagery contains geospatial data in terms of the bounding box of the images and the spatial reference system; however, in this case no explicit locations or objects are identified beforehand [21]. Most commonly, remotely sensed data are used to classify damage, but also other sources of geospatial data can be used as predictors, such as information on building structures [22][23][24][25]. Harirchian, Lahmer and Rasulzade [24] developed an artificial neural network (ANN) that uses buildings' damage-inducing parameters, such as number of floors, to predict the actual observed damage.…”

Section: Previous Researchmentioning

confidence: 99%

“…Most commonly, remotely sensed data are used to classify damage, but also other sources of geospatial data can be used as predictors, such as information on building structures [22][23][24][25]. Harirchian, Lahmer and Rasulzade [24] developed an artificial neural network (ANN) that uses buildings' damage-inducing parameters, such as number of floors, to predict the actual observed damage. The objective of the ANN model is not to be used in operational conditions after an earthquakes strikes but to identify earthquake-susceptible buildings for disaster risk management programs.…”

Section: Previous Researchmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Hazard and Spatial Transferability of a CNN for Automated Building Damage Assessment

et al. 2020

View full text Add to dashboard Cite

Automated classification of building damage in remote sensing images enables the rapid and spatially extensive assessment of the impact of natural hazards, thus speeding up emergency response efforts. Convolutional neural networks (CNNs) can reach good performance on such a task in experimental settings. How CNNs perform when applied under operational emergency conditions, with unseen data and time constraints, is not well studied. This study focuses on the applicability of a CNN-based model in such scenarios. We performed experiments on 13 disasters that differ in natural hazard type, geographical location, and image parameters. The types of natural hazards were hurricanes, tornadoes, floods, tsunamis, and volcanic eruptions, which struck across North America, Central America, and Asia. We used 175,289 buildings from the xBD dataset, which contains human-annotated multiclass damage labels on high-resolution satellite imagery with red, green, and blue (RGB) bands. First, our experiments showed that the performance in terms of area under the curve does not correlate with the type of natural hazard, geographical region, and satellite parameters such as the off-nadir angle. Second, while performance differed highly between occurrences of disasters, our model still reached a high level of performance without using any labeled data of the test disaster during training. This provides the first evidence that such a model can be effectively applied under operational conditions, where labeled damage data of the disaster cannot be available timely and thus model (re-)training is not an option.

show abstract

Section: Previous Researchmentioning

confidence: 99%

Section: Previous Researchmentioning

confidence: 99%

Multi-Hazard and Spatial Transferability of a CNN for Automated Building Damage Assessment

et al. 2020

View full text Add to dashboard Cite

show abstract

“…As macro-averaging is the average of model performance for each class, Ecuador shows the least macro-average percentage (76%) with an efficiency of only 53% in classifying test samples belonging to the class 3. The proposed method results show a significant improvement in RVS methods such as RVS based on multi-criteria decision-making [19] or Multi-Layer Perceptron [13] where the accuracies were around 37% and 52%, respectively. Additionally, the area under the curve (AUC) is also used for model performance evaluation as a summarized intelligence model.…”

Section: Resultsmentioning

confidence: 89%

“…A substantial literature has been published in the attempts of integrating several methods from various domains with RVS, for instance, statistical methods [11,12], Artificial Neural Network (ANN) [13][14][15][16][17], multi-criteria decision making [18,19], and type-1 [20][21][22][23] and type-2 [24,25] fuzzy logic systems are frequently assimilated within RVS for increasing the interface and efficacy of seismic vulnerability screening. However, there are methods developed to evaluate the damage and change detection of buildings by remote sensing and image analysis [26,27].…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Framework for Assessing Seismic Hazard Safety of Reinforced Concrete Buildings

et al. 2020

Self Cite

View full text Add to dashboard Cite

Although averting a seismic disturbance and its physical, social, and economic disruption is practically impossible, using the advancements in computational science and numerical modeling shall equip humanity to predict its severity, understand the outcomes, and equip for post-disaster management. Many buildings exist amidst the developed metropolitan areas, which are senile and still in service. These buildings were also designed before establishing national seismic codes or without the introduction of construction regulations. In that case, risk reduction is significant for developing alternatives and designing suitable models to enhance the existing structure’s performance. Such models will be able to classify risks and casualties related to possible earthquakes through emergency preparation. Thus, it is crucial to recognize structures that are susceptible to earthquake vibrations and need to be prioritized for retrofitting. However, each building’s behavior under seismic actions cannot be studied through performing structural analysis, as it might be unrealistic because of the rigorous computations, long period, and substantial expenditure. Therefore, it calls for a simple, reliable, and accurate process known as Rapid Visual Screening (RVS), which serves as a primary screening platform, including an optimum number of seismic parameters and predetermined performance damage conditions for structures. In this study, the damage classification technique was studied, and the efficacy of the Machine Learning (ML) method in damage prediction via a Support Vector Machine (SVM) model was explored. The ML model is trained and tested separately on damage data from four different earthquakes, namely Ecuador, Haiti, Nepal, and South Korea. Each dataset consists of varying numbers of input data and eight performance modifiers. Based on the study and the results, the ML model using SVM classifies the given input data into the belonging classes and accomplishes the performance on hazard safety evaluation of buildings.

show abstract

“…An SPI value that exceeds 20 shall be categorized as High priority building. Moreover, some new rapid seismic hazard assessment methods have been carried out by implementing the machine learning techniques such as multilayer perceptron [25,26] and support vector machine [27] or used soft computing techniques such as type-2 fuzzy logic [28]. However, some of the proposed methods are data-dependent.…”

Section: Rapid Visual Screeningmentioning

confidence: 99%

A Comparative Study of MCDM Methods Integrated with Rapid Visual Seismic Vulnerability Assessment of Existing RC Structures

et al. 2020

Self Cite

View full text Add to dashboard Cite

Recently, the demand for residence and usage of urban infrastructure has been increased, thereby resulting in the elevation of risk levels of human lives over natural calamities. The occupancy demand has rapidly increased the construction rate, whereas the inadequate design of structures prone to more vulnerability. Buildings constructed before the development of seismic codes have an additional susceptibility to earthquake vibrations. The structural collapse causes an economic loss as well as setbacks for human lives. An application of different theoretical methods to analyze the structural behavior is expensive and time-consuming. Therefore, introducing a rapid vulnerability assessment method to check structural performances is necessary for future developments. The process, as mentioned earlier, is known as Rapid Visual Screening (RVS). This technique has been generated to identify, inventory, and screen structures that are potentially hazardous. Sometimes, poor construction quality does not provide some of the required parameters; in this case, the RVS process turns into a tedious scenario. Hence, to tackle such a situation, multiple-criteria decision-making (MCDM) methods for the seismic vulnerability assessment opens a new gateway. The different parameters required by RVS can be taken in MCDM. MCDM evaluates multiple conflicting criteria in decision making in several fields. This paper has aimed to bridge the gap between RVS and MCDM. Furthermore, to define the correlation between these techniques, implementation of the methodologies from Indian, Turkish, and Federal Emergency Management Agency (FEMA) codes has been done. The effects of seismic vulnerability of structures have been observed and compared.

show abstract

Earthquake Hazard Safety Assessment of Existing Buildings Using Optimized Multi-Layer Perceptron Neural Network

Cited by 36 publications

References 39 publications

Multi-Hazard and Spatial Transferability of a CNN for Automated Building Damage Assessment

Multi-Hazard and Spatial Transferability of a CNN for Automated Building Damage Assessment

A Machine Learning Framework for Assessing Seismic Hazard Safety of Reinforced Concrete Buildings

A Comparative Study of MCDM Methods Integrated with Rapid Visual Seismic Vulnerability Assessment of Existing RC Structures

Contact Info

Product

Resources

About