Refine
Document Type
- Article (3)
- Doctoral Thesis (1)
Language
- English (4)
Is part of the Bibliography
- yes (4) (remove)
Keywords
- data-mining (2)
- open data (2)
- Data-Mining (1)
- Hochwasserrisiko (1)
- Natural hazard (1)
- Rhine basin (1)
- Schadensmodellierung (1)
- continuous simulation (1)
- curves (1)
- damage model (1)
Institute
Technological progress allows for producing ever more complex predictive models on the basis of increasingly big datasets. For risk management of natural hazards, a multitude of models is needed as basis for decision-making, e.g. in the evaluation of observational data, for the prediction of hazard scenarios, or for statistical estimates of expected damage. The question arises, how modern modelling approaches like machine learning or data-mining can be meaningfully deployed in this thematic field. In addition, with respect to data availability and accessibility, the trend is towards open data. Topic of this thesis is therefore to investigate the possibilities and limitations of machine learning and open geospatial data in the field of flood risk modelling in the broad sense. As this overarching topic is broad in scope, individual relevant aspects are identified and inspected in detail.
A prominent data source in the flood context is satellite-based mapping of inundated areas, for example made openly available by the Copernicus service of the European Union. Great expectations are directed towards these products in scientific literature, both for acute support of relief forces during emergency response action, and for modelling via hydrodynamic models or for damage estimation. Therefore, a focus of this work was set on evaluating these flood masks. From the observation that the quality of these products is insufficient in forested and built-up areas, a procedure for subsequent improvement via machine learning was developed. This procedure is based on a classification algorithm that only requires training data from a particular class to be predicted, in this specific case data of flooded areas, but not of the negative class (dry areas). The application for hurricane Harvey in Houston shows the high potential of this method, which depends on the quality of the initial flood mask.
Next, it is investigated how much the predicted statistical risk from a process-based model chain is dependent on implemented physical process details. Thereby it is demonstrated what a risk study based on established models can deliver. Even for fluvial flooding, such model chains are already quite complex, though, and are hardly available for compound or cascading events comprising torrential rainfall, flash floods, and other processes. In the fourth chapter of this thesis it is therefore tested whether machine learning based on comprehensive damage data can offer a more direct path towards damage modelling, that avoids explicit conception of such a model chain. For that purpose, a state-collected dataset of damaged buildings from the severe El Niño event 2017 in Peru is used. In this context, the possibilities of data-mining for extracting process knowledge are explored as well. It can be shown that various openly available geodata sources contain useful information for flood hazard and damage modelling for complex events, e.g. satellite-based rainfall measurements, topographic and hydrographic information, mapped settlement areas, as well as indicators from spectral data. Further, insights on damaging processes are discovered, which mainly are in line with prior expectations. The maximum intensity of rainfall, for example, acts stronger in cities and steep canyons, while the sum of rain was found more informative in low-lying river catchments and forested areas. Rural areas of Peru exhibited higher vulnerability in the presented study compared to urban areas. However, the general limitations of the methods and the dependence on specific datasets and algorithms also become obvious.
In the overarching discussion, the different methods – process-based modelling, predictive machine learning, and data-mining – are evaluated with respect to the overall research questions. In the case of hazard observation it seems that a focus on novel algorithms makes sense for future research. In the subtopic of hazard modelling, especially for river floods, the improvement of physical models and the integration of process-based and statistical procedures is suggested. For damage modelling the large and representative datasets necessary for the broad application of machine learning are still lacking. Therefore, the improvement of the data basis in the field of damage is currently regarded as more important than the selection of algorithms.
Compound natural hazards likeEl Ninoevents cause high damage to society, which to manage requires reliable risk assessments. Damage modelling is a prerequisite for quantitative risk estimations, yet many procedures still rely on expert knowledge, and empirical studies investigating damage from compound natural hazards hardly exist. A nationwide building survey in Peru after theEl Ninoevent 2017 - which caused intense rainfall, ponding water, flash floods and landslides - enables us to apply data-mining methods for statistical groundwork, using explanatory features generated from remote sensing products and open data. We separate regions of different dominant characteristics through unsupervised clustering, and investigate feature importance rankings for classifying damage via supervised machine learning. Besides the expected effect of precipitation, the classification algorithms select the topographic wetness index as most important feature, especially in low elevation areas. The slope length and steepness factor ranks high for mountains and canyons. Partial dependence plots further hint at amplified vulnerability in rural areas. An example of an empirical damage probability map, developed with a random forest model, is provided to demonstrate the technical feasibility.
Hydrodynamic interactions, i.e. the floodplain storage effects caused by inundations upstream on flood wave propagation, inundation areas, and flood damage downstream, are important but often ignored in large-scale flood risk assessments. Although new methods considering these effects sometimes emerge, they are often limited to a small or meso scale. In this study, we investigate the role of hydrodynamic interactions and floodplain storage on flood hazard and risk in the German part of the Rhine basin. To do so, we compare a new continuous 1D routing scheme within a flood risk model chain to the piece-wise routing scheme, which largely neglects floodplain storage. The results show that floodplain storage is significant, lowers water levels and discharges, and reduces risks by over 50%. Therefore, for accurate risk assessments, a system approach must be adopted, and floodplain storage and hydrodynamic interactions must carefully be considered.
Large-scale flood risk assessments are crucial for decision making, especially with respect to new flood defense schemes, adaptation planning and estimating insurance premiums. We apply the process-based Regional Flood Model (RFM) to simulate a 5000-year flood event catalog for all major catchments in Germany and derive risk curves based on the losses per economic sector. The RFM uses a continuous process simulation including a multisite, multivariate weather generator, a hydrological model considering heterogeneous catchment processes, a coupled 1D-2D hydrodynamic model considering dike overtopping and hinterland storage, spatially explicit sector-wise exposure data and empirical multi-variable loss models calibrated for Germany. For all components, uncertainties in the data and models are estimated. We estimate the median Expected Annual Damage (EAD) and Value at Risk at 99.5% confidence for Germany to be euro0.529 bn and euro8.865 bn, respectively. The commercial sector dominates by making about 60% of the total risk, followed by the residential sector. The agriculture sector gets affected by small return period floods and only contributes to less than 3% to the total risk. The overall EAD is comparable to other large-scale estimates. However, the estimation of losses for specific return periods is substantially improved. The spatial consistency of the risk estimates avoids the large overestimation of losses for rare events that is common in other large-scale assessments with homogeneous return periods. Thus, the process-based, spatially consistent flood risk assessment by RFM is an important step forward and will serve as a benchmark for future German-wide flood risk assessments.