@phdthesis{Vogel2013, author = {Vogel, Kristin}, title = {Applications of Bayesian networks in natural hazard assessments}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69777}, school = {Universit{\"a}t Potsdam}, year = {2013}, abstract = {Even though quite different in occurrence and consequences, from a modeling perspective many natural hazards share similar properties and challenges. Their complex nature as well as lacking knowledge about their driving forces and potential effects make their analysis demanding: uncertainty about the modeling framework, inaccurate or incomplete event observations and the intrinsic randomness of the natural phenomenon add up to different interacting layers of uncertainty, which require a careful handling. Nevertheless deterministic approaches are still widely used in natural hazard assessments, holding the risk of underestimating the hazard with disastrous effects. The all-round probabilistic framework of Bayesian networks constitutes an attractive alternative. In contrast to deterministic proceedings, it treats response variables as well as explanatory variables as random variables making no difference between input and output variables. Using a graphical representation Bayesian networks encode the dependency relations between the variables in a directed acyclic graph: variables are represented as nodes and (in-)dependencies between variables as (missing) edges between the nodes. The joint distribution of all variables can thus be described by decomposing it, according to the depicted independences, into a product of local conditional probability distributions, which are defined by the parameters of the Bayesian network. In the framework of this thesis the Bayesian network approach is applied to different natural hazard domains (i.e. seismic hazard, flood damage and landslide assessments). Learning the network structure and parameters from data, Bayesian networks reveal relevant dependency relations between the included variables and help to gain knowledge about the underlying processes. The problem of Bayesian network learning is cast in a Bayesian framework, considering the network structure and parameters as random variables itself and searching for the most likely combination of both, which corresponds to the maximum a posteriori (MAP score) of their joint distribution given the observed data. Although well studied in theory the learning of Bayesian networks based on real-world data is usually not straight forward and requires an adoption of existing algorithms. Typically arising problems are the handling of continuous variables, incomplete observations and the interaction of both. Working with continuous distributions requires assumptions about the allowed families of distributions. To "let the data speak" and avoid wrong assumptions, continuous variables are instead discretized here, thus allowing for a completely data-driven and distribution-free learning. An extension of the MAP score, considering the discretization as random variable as well, is developed for an automatic multivariate discretization, that takes interactions between the variables into account. The discretization process is nested into the network learning and requires several iterations. Having to face incomplete observations on top, this may pose a computational burden. Iterative proceedings for missing value estimation become quickly infeasible. A more efficient albeit approximate method is used instead, estimating the missing values based only on the observations of variables directly interacting with the missing variable. Moreover natural hazard assessments often have a primary interest in a certain target variable. The discretization learned for this variable does not always have the required resolution for a good prediction performance. Finer resolutions for (conditional) continuous distributions are achieved with continuous approximations subsequent to the Bayesian network learning, using kernel density estimations or mixtures of truncated exponential functions. All our proceedings are completely data-driven. We thus avoid assumptions that require expert knowledge and instead provide domain independent solutions, that are applicable not only in other natural hazard assessments, but in a variety of domains struggling with uncertainties.}, language = {en} } @article{SchroeterKreibichVogeletal.2014, author = {Schroeter, Kai and Kreibich, Heidi and Vogel, Kristin and Riggelsen, Carsten and Scherbaum, Frank and Merz, Bruno}, title = {How useful are complex flood damage models?}, series = {Water resources research}, volume = {50}, journal = {Water resources research}, number = {4}, publisher = {American Geophysical Union}, address = {Washington}, issn = {0043-1397}, doi = {10.1002/2013WR014396}, pages = {3378 -- 3395}, year = {2014}, abstract = {We investigate the usefulness of complex flood damage models for predicting relative damage to residential buildings in a spatial and temporal transfer context. We apply eight different flood damage models to predict relative building damage for five historic flood events in two different regions of Germany. Model complexity is measured in terms of the number of explanatory variables which varies from 1 variable up to 10 variables which are singled out from 28 candidate variables. Model validation is based on empirical damage data, whereas observation uncertainty is taken into consideration. The comparison of model predictive performance shows that additional explanatory variables besides the water depth improve the predictive capability in a spatial and temporal transfer context, i.e., when the models are transferred to different regions and different flood events. Concerning the trade-off between predictive capability and reliability the model structure seem more important than the number of explanatory variables. Among the models considered, the reliability of Bayesian network-based predictions in space-time transfer is larger than for the remaining models, and the uncertainties associated with damage predictions are reflected more completely.}, language = {en} } @book{RoggeSoltiMansvanderAalstetal.2013, author = {Rogge-Solti, Andreas and Mans, Ronny S. and van der Aalst, Wil M. P. and Weske, Mathias}, title = {Repairing event logs using stochastic process models}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-258-2}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66797}, publisher = {Universit{\"a}t Potsdam}, pages = {19}, year = {2013}, abstract = {Companies strive to improve their business processes in order to remain competitive. Process mining aims to infer meaningful insights from process-related data and attracted the attention of practitioners, tool-vendors, and researchers in recent years. Traditionally, event logs are assumed to describe the as-is situation. But this is not necessarily the case in environments where logging may be compromised due to manual logging. For example, hospital staff may need to manually enter information regarding the patient's treatment. As a result, events or timestamps may be missing or incorrect. In this paper, we make use of process knowledge captured in process models, and provide a method to repair missing events in the logs. This way, we facilitate analysis of incomplete logs. We realize the repair by combining stochastic Petri nets, alignments, and Bayesian networks. We evaluate the results using both synthetic data and real event data from a Dutch hospital.}, language = {en} } @phdthesis{RoggeSolti2014, author = {Rogge-Solti, Andreas}, title = {Probabilistic Estimation of Unobserved Process Events}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70426}, school = {Universit{\"a}t Potsdam}, year = {2014}, abstract = {Organizations try to gain competitive advantages, and to increase customer satisfaction. To ensure the quality and efficiency of their business processes, they perform business process management. An important part of process management that happens on the daily operational level is process controlling. A prerequisite of controlling is process monitoring, i.e., keeping track of the performed activities in running process instances. Only by process monitoring can business analysts detect delays and react to deviations from the expected or guaranteed performance of a process instance. To enable monitoring, process events need to be collected from the process environment. When a business process is orchestrated by a process execution engine, monitoring is available for all orchestrated process activities. Many business processes, however, do not lend themselves to automatic orchestration, e.g., because of required freedom of action. This situation is often encountered in hospitals, where most business processes are manually enacted. Hence, in practice it is often inefficient or infeasible to document and monitor every process activity. Additionally, manual process execution and documentation is prone to errors, e.g., documentation of activities can be forgotten. Thus, organizations face the challenge of process events that occur, but are not observed by the monitoring environment. These unobserved process events can serve as basis for operational process decisions, even without exact knowledge of when they happened or when they will happen. An exemplary decision is whether to invest more resources to manage timely completion of a case, anticipating that the process end event will occur too late. This thesis offers means to reason about unobserved process events in a probabilistic way. We address decisive questions of process managers (e.g., "when will the case be finished?", or "when did we perform the activity that we forgot to document?") in this thesis. As main contribution, we introduce an advanced probabilistic model to business process management that is based on a stochastic variant of Petri nets. We present a holistic approach to use the model effectively along the business process lifecycle. Therefore, we provide techniques to discover such models from historical observations, to predict the termination time of processes, and to ensure quality by missing data management. We propose mechanisms to optimize configuration for monitoring and prediction, i.e., to offer guidance in selecting important activities to monitor. An implementation is provided as a proof of concept. For evaluation, we compare the accuracy of the approach with that of state-of-the-art approaches using real process data of a hospital. Additionally, we show its more general applicability in other domains by applying the approach on process data from logistics and finance.}, language = {en} } @article{PaprotnyKreibichMoralesNapolesetal.2020, author = {Paprotny, Dominik and Kreibich, Heidi and Morales-Napoles, Oswaldo and Wagenaar, Dennis and Castellarin, Attilio and Carisi, Francesca and Bertin, Xavier and Merz, Bruno and Schr{\"o}ter, Kai}, title = {A probabilistic approach to estimating residential losses from different flood types}, series = {Natural hazards : journal of the International Society for the Prevention and Mitigation of Natural Hazards}, volume = {105}, journal = {Natural hazards : journal of the International Society for the Prevention and Mitigation of Natural Hazards}, number = {3}, publisher = {Springer}, address = {New York}, issn = {0921-030X}, doi = {10.1007/s11069-020-04413-x}, pages = {2569 -- 2601}, year = {2020}, abstract = {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.}, language = {en} }