The Netherlands has just finished implementing the Room for the Rivers program along the Rhine and Meuse Rivers in response to increasing river discharges. Recently, making more room for the river ...is, however, being challenged for future application because the flood defenses are assessed to be too weak and will need reinforcement anyway. To be able to decide on the most desirable policy for the remainder of the century, we require knowledge of all benefits and costs of individual interventions and strategic alternatives for flood mitigation. In this paper, we quantify some benefits of making more room for the rivers. We recognize and quantify two risk-reducing effects and provide results of analyses for the Rhine and Meuse Rivers in The Netherlands. Making room for rivers was originally advocated because it (1) reduces the consequences of flooding, as well as (2) reduces the probability of failure of the embankments. We have now quantified these effects allowing translation into risk reduction proper. Moreover, larger floodplain surface area may influence the relationship between discharge and flood level, which implies that rivers with widened floodplains are less sensitive to uncertainties about future river discharges. This does not reduce risk proper, but makes the river system more robust, as we shall argue in the discussion where we present risk reduction and robustness as complementary perspectives for assessing strategic alternatives for flood risk management.
Abstract
Societal efforts to understand and mitigate threats posed by hazards are often informed by complex disaster risk models. Despite research demonstrating the disproportionate effects of ...disasters on vulnerable groups, current risk modeling approaches lack robust methods to account for such equity concerns. Consequently, efforts to develop evidence-based disaster risk management interventions may lack awareness of differential risks in the settings where they are applied. Here, we draw on the relevant literature to develop a typology for characterizing current approaches to incorporating equity into risk modeling. Using this typology, we then evaluated 69 risk assessments conducted by major international development organizations. We found that only ~ 28% of risk models attempt a quantitative evaluation of the differential impacts of disasters and climate change. We then used an equity-sensitive approach to reconstruct a recent risk assessment and show that important elements are missed when equity is excluded in disaster risk modeling.
Global climate change and sea level rise are increasing the risks of flooding for coastal communities. Probabilistic coastal flood risk analysis at regional or global scales requires flood models ...with relatively low data requirements and low computational costs. Bathtub inundation models, which compute flood depth as the difference between water level and ground elevation, are well-suited for large-scale flood risk analysis. However, these models may overestimate floods because they do not capture some of the relevant underlying hydrodynamic processes that govern flood propagation on land.
We present Flow-Tub, a modified bathtub inundation model that integrates two hydrodynamic processes to improve the accuracy of the bathtub inundation model while retaining computational efficiency: hydraulic connectivity and path-based attenuation.1.Hydraulic connectivity ensures that inundation is restricted to areas connected to the water source.2.Path-based attenuation ensures that the modeled flood water depths are reduced along the flow paths to represent the effects of surface friction and the temporary nature of storm surges.
We validate the Flow-tub model against a hydrodynamic model. We also compare results of the bathtub model and the Flow-Tub model, highlighting the improved accuracy in the estimation of flood depths in the latter.
Display omitted
Reliable flood damage assessment is important for decision‐making in flood risk management. Flood damage assessment is often done with damage curves based only on water depth. These depth‐damage ...curves are usually developed based on data from a specific location and specific flood conditions. Such depth‐damage curves tend to be applied outside the scope of their validity. Validation studies show that in such cases depth‐damage curve are not very reliable, probably due to excluded influencing variables. The expectation is that the inclusion of more variables in a damage function will improve its transferability. We compare multi‐variable models based on Bayesian Networks and Random Forests developed on the basis of flood damage data sets from Germany and The Netherlands. The performance of the models is tested on a validation sub‐set of both countries' data. The models are also updated with data from the other country and then tested again. The results show that the German models (BN/RF‐FLEMOps) perform better in the Netherlands than the Dutch models (BN/RF‐Meuse) perform in Germany. This is probably because the FLEMOps models are based on more heterogeneous data than the Meuse models. The FLEMOps models, therefore, are better able to capture damages processes from other events and in other locations. Model performance improves via updating the models with data from the location to which the model is transferred to. The results show that there is high potential to develop improved damage models, by training multi‐variable models with heterogeneous data, for example from multiple flood events and locations.
Key Points
Multi‐variable flood damage models can be transferred between locations, provided the training data are similar
Flood damage collection efforts should focus on acquiring heterogeneous data, instead of collecting a large quantity of data only for a single event in one location
There is a high potential to develop more broadly applicable flood damage models, by training multi‐variable models with heterogeneous data from multiple flood events
Flood damage assessment is usually done with damage curves only dependent on the water depth. Several recent studies have shown that supervised learning techniques applied to a multi-variable data ...set can produce significantly better flood damage estimates. However, creating and applying a multi-variable flood damage model requires an extensive data set, which is rarely available, and this is currently holding back the widespread application of these techniques. In this paper we enrich a data set of residential building and contents damage from the Meuse flood of 1993 in the Netherlands, to make it suitable for multi-variable flood damage assessment. Results from 2-D flood simulations are used to add information on flow velocity, flood duration and the return period to the data set, and cadastre data are used to add information on building characteristics. Next, several statistical approaches are used to create multi-variable flood damage models, including regression trees, bagging regression trees, random forest, and a Bayesian network. Validation on data points from a test set shows that the enriched data set in combination with the supervised learning techniques delivers a 20 % reduction in the mean absolute error, compared to a simple model only based on the water depth, despite several limitations of the enriched data set. We find that with our data set, the tree-based methods perform better than the Bayesian network.
Increasing amounts of data, together with more computing power and better machine learning algorithms to analyse the data, are causing changes in almost every aspect of our lives. This trend is ...expected to continue as more data keep becoming available, computing power keeps improving and machine learning algorithms keep improving as well. Flood risk and impact assessments are also being influenced by this trend, particularly in areas such as the development of mitigation measures, emergency response preparation and flood recovery planning. Machine learning methods have the potential to improve accuracy as well as reduce calculating time and model development cost. It is expected that in the future more applications will become feasible and many process models and traditional observation methods will be replaced by machine learning. Examples of this include the use of machine learning on remote sensing data to estimate exposure and on social media data to improve flood response. Some improvements may require new data collection efforts, such as for the modelling of flood damages or defence failures. In other components, machine learning may not always be suitable or should be applied complementary to process models, for example in hydrodynamic applications. Overall, machine learning is likely to drastically improve future flood risk and impact assessments, but issues such as applicability, bias and ethics must be considered carefully to avoid misuse. This paper presents some of the current developments on the application of machine learning in this field and highlights some key needs and challenges.
Residential assets, comprising buildings and household contents, are a major source of direct flood losses. Existing damage models are mostly deterministic and limited to particular countries or ...flood types. Here, we compile building-level losses from Germany, Italy and the Netherlands covering a wide range of fluvial and pluvial flood events. Utilizing a Bayesian network (BN) for continuous variables, we find that relative losses (i.e. loss relative to exposure) to building structure and its contents could be estimated with five variables: water depth, flow velocity, event return period, building usable floor space area and regional disposable income per capita. The model’s ability to predict flood losses is validated for the 11 flood events contained in the sample. Predictions for the German and Italian fluvial floods were better than for pluvial floods or the 1993 Meuse river flood. Further, a case study of a 2010 coastal flood in France is used to test the BN model’s performance for a type of flood not included in the survey dataset. Overall, the BN model achieved better results than any of 10 alternative damage models for reproducing average losses for the 2010 flood. An additional case study of a 2013 fluvial flood has also shown good performance of the model. The study shows that data from many flood events can be combined to derive most important factors driving flood losses across regions and time, and that resulting damage models could be applied in an open data framework.
Flood loss estimation models are developed using synthetic or empirical approaches. The synthetic approach consists of what-if scenarios developed by experts. The empirical models are based on ...statistical analysis of empirical loss data. In this study, we propose a novel Bayesian Data-Driven approach to enhance established synthetic models using available empirical data from recorded events. For five case studies in Western Europe, the resulting Bayesian Data-Driven Synthetic (BDDS) model enhances synthetic model predictions by reducing the prediction errors and quantifying the uncertainty and reliability of loss predictions for post-event scenarios and future events. The performance of the BDDS model for a potential future event is improved by integration of empirical data once a new flood event affects the region. The BDDS model, therefore, has high potential for combining established synthetic models with local empirical loss data to provide accurate and reliable flood loss predictions for quantifying future risk.
•Bayesian Data-Driven approach integrates knowledge from the vast compendium of synthetic models with empirical loss data.•This approach improves accuracy and quantifies reliability of synthetic flood loss models using local empirical data.•Using empirical flood damage data from past events, this approach improves loss predictions for a potential future event.
AI and Disaster Risk: A Practitioner Perspective Moitra, Aparna; Wagenaar, Dennis; Kalirai, Manveer ...
Proceedings of the ACM on human-computer interaction,
11/2022, Letnik:
6, Številka:
CSCW2
Journal Article
Recenzirano
Emerging techniques developed by AI researchers promise to offer the capacity to support disaster risk management (DRM), through making data collection or analysis practices faster, less costly, or ...more accurate. However, in every socially consequential domain in which AI tools have been applied, these technologies have been demonstrated to have some degree of negative consequences. This paper explores an attempt to convene technical experts in the area of DRM to discuss potential negative impacts, their approaches toward mitigating these impacts as well as identifying some of the overarching challenges. In doing so, we contribute new findings about a domain that has received relatively little attention from critical and ethical AI researchers, and the opportunities and limitations that are presented by working with domain experts to evaluate the social consequences of emerging technologies.
Damage models for natural hazards are used for decision making on reducing and transferring risk. The damage estimates from these models depend on many variables and their complex sometimes nonlinear ...relationships with the damage. In recent years, data‐driven modeling techniques have been used to capture those relationships. The available data to build such models are often limited. Therefore, in practice it is usually necessary to transfer models to a different context. In this article, we show that this implies the samples used to build the model are often not fully representative for the situation where they need to be applied on, which leads to a “sample selection bias.” In this article, we enhance data‐driven damage models by applying methods, not previously applied to damage modeling, to correct for this bias before the machine learning (ML) models are trained. We demonstrate this with case studies on flooding in Europe, and typhoon wind damage in the Philippines. Two sample selection bias correction methods from the ML literature are applied and one of these methods is also adjusted to our problem. These three methods are combined with stochastic generation of synthetic damage data. We demonstrate that for both case studies, the sample selection bias correction techniques reduce model errors, especially for the mean bias error this reduction can be larger than 30%. The novel combination with stochastic data generation seems to enhance these techniques. This shows that sample selection bias correction methods are beneficial for damage model transfer.