No abstract

Detailed information about seismic building structural types (SBSTs) is crucial for accurate earthquake vulnerability and risk modeling as it reflects the main load-bearing structures of buildings and, thus, the behavior under seismic load. However, for numerous urban areas in earthquake prone regions this information is mostly outdated, unavailable, or simply not existent. To this purpose, we present an effective approach to estimate SBSTs by combining scarce in situ observations, multi-sensor remote sensing data and machine learning techniques. In particular, an approach is introduced, which deploys a sequential procedure comprising five main steps, namely calculation of features from remote sensing data, feature selection, outlier detection, generation of synthetic samples, and supervised classification under consideration of both Support Vector Machines and Random Forests. Experimental results obtained for a representative study area, including large parts of the city of Padang (Indonesia), assess the capabilities of the presented approach and confirm its great potential for a reliable area-wide estimation of SBSTs and an effective earthquake loss modeling based on remote sensing, which should be further explored in future research activities.

Mapping of settlement areas from space is entering a new era. With the recently developed Global Urban Footprint (based on radar data from TanDEM-X) and the Global Human Settlement Layer (based on optical data), two new initiatives that promise to map complex settlement patterns at global scales and unprecedented spatial resolutions are about to enter the scientific and map user community. However, comparative studies on these layers' strengths and weaknesses, especially in terms of their potential added value with regard to existing lower resolution maps, as well as their assessed accuracy are still absent. In this regard, we introduce a multiscale cross-comparison framework that uses the best existing urban maps as a benchmark. To paint a complete picture, we simultaneously address several components of map accuracy including relative inter-map agreement, absolute accuracies and pattern-based classification differences. This framework is applied to present regionally representative results from two Central European test sites. In this, we find that the new base maps bring decisive advancements in preserving the small-scale complexity of global human settlement patterns beyond urban core areas. Relative inter-map comparison exposes low density settlement regions traditionally under-represented by lower resolution maps that are now recognized. Absolute metrics such as the Kappa coefficient of agreement (K) show that accuracies of the new high resolution layers (K = 0.56-0.58) nearly double those of existing products. Beyond, they feature substantial consistency between urban (K = 0.46-0.50) and rural landscapes (K = 0.41-0.45). Results from pattern-based exploration further reveal significant correlation of accuracies with physical pattern variations such as settlement density and mark a clear shift of accuracies from large to medium and small patch sizes. This differentiated view on classification accuracies shows that the new generation of urban maps constitutes a significantly enhanced spatial representation of large-scale settlement patterns.

No abstract

Remote sensing data and methods are widely deployed in order to contribute to the assessment of numerous components of earthquake risk. While for earthquake hazard related investigations the use of remotely sensed data is an established methodological element with a long research tradition, earthquake vulnerability centered assessments incorporating remote sensing data are increasing primarily in recent years. This goes along with a changing perspective of the scientific community which considers the assessment of vulnerability and its constituent elements as a pivotal part of a comprehensive risk analysis. Thereby, the availability of new sensors systems enables an appreciable share of remote sensing first. In this manner, a survey of the interdisciplinary conceptual literature dealing with the scientific perception of risk, hazard and vulnerability reveals the demand for a comprehensive description of earthquake hazards as well as an assessment of the present and future conditions of the elements exposed. A review of earthquake related remote sensing literature, realized both in a qualitative and quantitative manner, shows the already existing and published manifold capabilities of remote sensing contributing to assess earthquake risk. These include earthquake hazard related analysis such as detection and measurement of lineaments and surface deformations in pre-and post-event applications. Furthermore, pre-event seismic vulnerability centered assessment of the built and natural environment and damage assessments for post-event applications are presented. Based on the review and the discussion of current scientific foci and research projects first steps towards a roadmap for remote sensing is drawn, explicitly taking scientific, technical, multi-and transdisciplinary as well as political perspectives into account, which is intended to open possible future research activities.

This paper quantitatively evaluates the suitability of multi-sensor remote sensing to assess the seismic vulnerability of buildings for the example city of Padang, Indonesia. Features are derived from remote sensing data to characterize the urban environment and are subsequently combined with in situ observations. Machine learning approaches are deployed in a sequential way to identify meaningful sets of features that are suitable to predict seismic vulnerability levels of buildings. When assessing the vulnerability level according to a scoring method, the overall mean absolute percentage error is 10.6%, if using a supervised support vector regression approach. When predicting EMS-98 classes, the results show an overall accuracy of 65.4% and a kappa statistic of 0.36, if using a naive Bayes learning scheme. This study shows potential for a rapid screening assessment of large areas that should be explored further in the future.

This article was submitted to ISPRS Journal of Photogrammetry and Remote Sensing.Human settlement extent (HSE) information is a valuable indicator of worldwide urbanization as well as the resulting human pressure on the natural environment. Therefore, mapping HSE is critical for various environmental issues at local, regional, and even global scales. This paper presents a deep-learning-based framework to automatically map HSE from multi-spectral Sentinel-2 data using regionally available geo-products as training labels. A straightforward, simple, yet effective fully convolutional network-based architecture, Sen2HSE, is implemented as an example for semantic segmentation within the framework. The framework is validated against both manually labelled checking points distributed evenly over the test areas, and * the OpenStreetMap building layer. The HSE mapping results were extensively compared to several baseline products in order to thoroughly evaluate the effectiveness of the proposed HSE mapping framework. The HSE mapping power is consistently demonstrated over 10 representative areas across the world. We also present one regional-scale and one country-wide HSE mapping example from our framework to show the potential for upscaling. The results of this study contribute to the generalization of the applicability of CNN-based approaches for large-scale urban mapping to cases where no up-to-date and accurate ground truth is available, as well as the subsequent monitor of global urbanization.

In this letter, a new approach is proposed to classify tsunami-induced building damage into multiple classes using preand post-event high-resolution radar (TerraSAR-X) data. Buildings affected by the 2011 Tohoku earthquake and tsunami were the focus in developing this method. In synthetic aperture radar (SAR) data, buildings exhibit high backscattering caused by doublebounce reflection and layover. However, if the buildings are completely washed away or structurally destroyed by the tsunami, then this high backscattering might be reduced, and the post-event SAR data will show a lower sigma nought value than the pre-event SAR data. To exploit these relationships, a rapid method for classifying tsunami-induced building damage into multiple classes was developed by analyzing the statistical relationship between the change ratios in areas with high backscattering and in areas with building damage. The method was developed for the affected city of Sendai, Japan, based on the decision tree application of a machine learning algorithm. The results provided an overall accuracy of 67.4% and a kappa statistic of 0.47. To validate its transferability, the method was applied to the town of Watari, and an overall accuracy of 58.7% and a kappa statistic of 0.38 were obtained.