Toward a rapid probabilistic seismic vulnerability assessment using satellite and ground-based remote sensing

Pittore, Massimiliano; Wieland, Marc

doi:10.1007/s11069-012-0475-z

Cited by 60 publications

(55 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Especially when tackling a rather difficult classification task on noisy data with high training costs, feature selection and parameter tuning are crucial to improve the results. For the given experimental setup it can be concluded that given The results of this study will be used as base-level stratification to further characterize the exposed building stock (Wieland et al 2015) and to infer its vulnerability (Pittore and Wieland 2013) as input for a seismic risk assessment of the larger urban agglomeration of Port-au-Prince. Traditionally, the seismic vulnerability assessment is performed within samples which are selected by the risk analyst according to their knowledge of the study area.…”

Section: Discussionmentioning

confidence: 99%

Object-based urban structure type pattern recognition from Landsat TM with a Support Vector Machine

Wieland

Torres

Pittore

et al. 2016

International Journal of Remote Sensing

Self Cite

View full text Add to dashboard Cite

This study evaluates the potential of object-based image analysis in combination with supervised machine learning to identify urban structure type patterns from Landsat Thematic Mapper (TM) images. The main aim is to assess the influence of several critical choices commonly made during the training stage of a learning machine on the classification performance and to give recommendations for classifier-dependent intelligent training. Particular emphasis is given to assess the influence of size and class distribution of the training data, the approach of training data sampling (user-guided or random) and the type of training samples (squares or segments) on the classification performance of a Support Vector Machine (SVM). Different feature selection algorithms are compared and segmentation and classifier parameters are dynamically tuned for the specific image scene, classification task and training data. The performance of the classifier is measured against a set of reference datasets from manual image interpretation and furthermore compared on the basis of landscape metrics to a very high-resolution reference classification derived from Light Detection And Ranging (LiDAR) measurements. The study highlights the importance of a careful design of the training stage and dynamically tuned classifier parameters, especially when dealing with noisy data and small training datasets. For the given experimental set-up the study concludes that given optimized feature space and classifier parameters, training a SVM with segment-shaped samples that were sampled in a guided manner and are balanced between the classes provided the best classification results. If square-shaped samples are used, a random sampling provided better results than a guided selection. Equally balanced sample distributions outperformed unbalanced training sets.

show abstract

Section: Discussionmentioning

confidence: 99%

Object-based urban structure type pattern recognition from Landsat TM with a Support Vector Machine

Wieland

Torres

Pittore

et al. 2016

International Journal of Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…(c) The proposed methodology relies on detailed geospatial data which are prone to be outdated, fragmented, and limited in detail. Users have to identify the most comprehensive data set or make use of promising data capturing tools available (e.g., Pittore and Wieland, 2013;Wieland et al, 2012). (d) The road network is considered a fully functional relational network, the potential failure/disruption of accessibility due to debris cover or damages.…”

Section: Discussionmentioning

confidence: 99%

Open space suitability analysis for emergency shelter after an earthquake

Anhorn

Khazai

2015

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract.In an emergency situation shelter space is crucial for people affected by natural hazards. Emergency planners in disaster relief and mass care can greatly benefit from a sound methodology that identifies suitable shelter areas and sites where shelter services need to be improved. A methodology to rank suitability of open spaces for contingency planning and placement of shelter in the immediate aftermath of a disaster is introduced. The Open Space Suitability Index uses the combination of two different measures: a qualitative evaluation criterion for the suitability and manageability of open spaces to be used as shelter sites and another quantitative criterion using a capacitated accessibility analysis based on network analysis. For the qualitative assessment implementation issues, environmental considerations and basic utility supply are the main categories to rank candidate shelter sites. A geographic information system is used to reveal spatial patterns of shelter demand. Advantages and limitations of this method are discussed on the basis of an earthquake hazard case study in the Kathmandu Metropolitan City. According to the results, out of 410 open spaces under investigation, 12.2 % have to be considered not suitable (Category D and E) while 10.7 % are Category A and 17.6 % are Category B. Almost two-thirds (59.55 %) are fairly suitable (Category C).

show abstract

“…New, rapid methods for large-scale damage estimation are becoming more readily available. These practices are based on statistical analysis or data mining of urban data derived from satellite remote sensing (Saito and Spence 2011) or national census databases (Pittore and Wieland 2013;Riedel et al 2014Riedel et al , 2015Guettiche et al 2017).…”

Section: Human Losses Considering Building Damagementioning

confidence: 99%

Economic and Human Loss Empirical Models for Earthquakes in the Mediterranean Region, with Particular Focus on Algeria

Guettiche

Guéguen

Mimoune

2017

Int J Disaster Risk Sci

View full text Add to dashboard Cite

In this study, loss estimation models were developed for reasonably accurate assessment of economic and human losses from seismic events in the Mediterranean region, based on damage assessment at an urban scale. Data were compiled from existing worldwide databases, and completed with earthquake information from regional studies. Economic data were converted to a single common currency unit (2015 USD value) and the wealth of the areas affected by 65 earthquakes of the region from 1900 to 2015 was assessed. Reduced-form models were used to determine economic and human losses, with earthquake magnitude and intensity as hazard-related variables, and gross domestic product of the affected area and the affected population as exposure-related variables. Damage to buildings was also used as a hazard-related variable to predict economic and human losses. Finally, site-specific regression models were proposed for economic and human losses due to earthquakes in the Mediterranean region, and more specifically, in Algeria. We show that by introducing the damage variable into the models, prediction error can be reduced, and that accuracy of loss model estimation is site dependent and requires regional data on earthquake losses to improve. A case study for Constantine, Algeria shows the improvements needed for increased accuracy.

show abstract

Toward a rapid probabilistic seismic vulnerability assessment using satellite and ground-based remote sensing

Cited by 60 publications

References 20 publications

Object-based urban structure type pattern recognition from Landsat TM with a Support Vector Machine

Object-based urban structure type pattern recognition from Landsat TM with a Support Vector Machine

Open space suitability analysis for emergency shelter after an earthquake

Economic and Human Loss Empirical Models for Earthquakes in the Mediterranean Region, with Particular Focus on Algeria

Contact Info

Product

Resources

About