Master

Fakultät 08
Large-scale automated earthquake risk modelling with Earth Observation and Machine Learning Techniques in Chile
Kategorie:
Abschlussarbeit
Studiengang:
Status:
abgeschlossen
BetreuerIn:
Extern/e BetreuerIn:
Dr. Christian Geiß
Extern/e AutorIn:
Stefan Bauer
Jahr:
2021

Groß angelegte automatisierte Erdbebenrisikomodellierung mit Erdbeobachtungs- und Machine-Learning-Techniken in Chile


Through global urbanization and the growth of population, our planet undergoes radical changes. Through the last century, urban areas evolved from spare settled areas to agglomerations of millions of dwellers. Therefore, a systematic characterization of these built habitats is an essential step for a fundamental understanding of urban habitat. This knowledge, in turn, will contribute to large-scale, yet specific applications like vulnerability or exposition analysis. For all these studies, an urban characterization is essential, and fundamental properties of urban morphology is information of great value. Among the relevant morphologic features, built-up density is of high relevance due to its simplicity, and yet its high potential of information. To get a full morphological description of built-up areas, we also argue for the use of the built-up height as a proxy of the vertical dimension of urban areas. Earth observation data proved to be a beneficial source of information to assess built-up height and density.


In this aim, we used TanDEM-X data as support of our morphological characterization. These data provide elevation information as DSM data of 0.4 arcseconds of resolution. Our study is part of the RIESGOS project, which covers Chile, Peru, and Ecuador. In this frame, the work discussed here focus solely on Chile. Therefore, the area covered in this study is more consequent than the limitation of free TanDEM-X data per scientific project (100 000 km2). Additionally, the surface of our study site is too large to rely on VHR multispectral data, as this type of data is expensive. For this reason, we propose here an application of new methods enabling us to overcome the scarcity of TanDEM-X data by combining it with Sentinel-2 data. This technique is based on a regression approach between DSM data of the TDM mission and the optical data of Sentinel-2 (Figure 1).

Figure 1: Workflow of proposed methodology
Figure 1: Workflow of proposed methodology


This thesis aims to develop and test a large-scale automated morphologic characterization of urban areas with earth observation and machine learning techniques. That characterization is a key factor to assess vulnerability regarding natural hazards, like earthquakes or tsunamis. Chiles’s coast is right next to the boundary zones of different tectonic plates and is thereby vulnerable to earthquakes and tsunamis caused by earthquakes. These hazards could affect millions of people living on the coast or near it. Therefore, we developed a method featuring TanDEM-X and Sentinel-2 data to evaluate the morphologic characteristics with free and globally available data. Because TanDEM-X data is not completely available for free, we developed an approach that reduces the amount of TanDEM-X data needed through an ensemble regression approach. Thereby only selected areas, where TanDEM-X and Sentinel-2 data are, are used to train the multi ensemble regression. The learned regression model is then used in all other areas and predicts the urban morphological characteristics - built-up height and density- on regions where only Sentinel-2 data is present. Our approach provides relatively accurate results (Figure 2) that are close to the existent urban morphological characteristics, with a slight overestimation of the built-up height and density. The possibility of a large-scale automated calculation of the built-up height and density opens a variety of options for vulnerability assessment regarding different natural hazards, which were not possible before.


This study was conducted at the Earth Observation Center (EOC) within the German Aerospace Center in Oberpfaffenhofen and co-supervised by Dr. Christian Geiß (DLR-EOC).


Figure 2: Built-up height and density for the middle part of Chile
Figure 2: Built-up height and density for the middle part of Chile

Suche

Suchen Sie
... Abschlussarbeiten, Projekte oder Publikationen zu einem bestimmten Thema? Dann verwenden Sie das Suchformular.

... oder von einem bestimmten Autor oder Betreuer? Dann können Sie auch auf den persönlichen Seiten nachsehen.