Bayesian network learning for natural hazard analyses

Abstract. Modern natural hazards research requires dealing with several uncertainties that arise from limited process knowledge, measurement errors, censored and incomplete observations, and the intrinsic randomness of the governing processes. Nevertheless, deterministic analyses are still widely used in quantitative hazard assessments despite the pitfall of misestimating the hazard and any ensuing risks. In this paper we show that Bayesian networks offer a flexible framework for capturing and expressing a broad range of uncertainties encountered in natural hazard assessments. Although Bayesian networks are well studied in theory, their application to real-world data is far from straightforward, and requires specific tailoring and adaptation of existing algorithms. We offer suggestions as how to tackle frequently arising problems in this context and mainly concentrate on the handling of continuous variables, incomplete data sets, and the interaction of both. By way of three case studies from earthquake, flood, and landslide research, we demonstrate the method of data-driven Bayesian network learning, and showcase the flexibility, applicability, and benefits of this approach. Our results offer fresh and partly counterintuitive insights into well-studied multivariate problems of earthquake-induced ground motion prediction, accurate flood damage quantification, and spatially explicit landslide prediction at the regional scale. In particular, we highlight how Bayesian networks help to express information flow and independence assumptions between candidate predictors. Such knowledge is pivotal in providing scientists and decision makers with well-informed strategies for selecting adequate predictor variables for quantitative natural hazard assessments.

[1]  Bruno Merz,et al.  Challenges for Bayesian network learning in a flood damage assessment application , 2014 .

[2]  W. Wong,et al.  The calculation of posterior distributions by data augmentation , 1987 .

[3]  Frank Scherbaum,et al.  Modeling the Joint Probability of Earthquake, Site, and Ground-Motion Parameters Using Bayesian Networks , 2011 .

[4]  Adnan Masood,et al.  The Theory That Would Not Die : How Bayes ' Rule Cracked the Enigma Code , Hunted Down Russian , 2013 .

[5]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[6]  Serafín Moral,et al.  Mixtures of Truncated Exponentials in Hybrid Bayesian Networks , 2001, ECSQARU.

[7]  Gregory F. Cooper,et al.  A Multivariate Discretization Method for Learning Bayesian Networks from Mixed Data , 1998, UAI.

[8]  F. Scherbaum,et al.  Flood Damage and Influencing Factors: A Bayesian Network Perspective , 2012 .

[9]  F. Scherbaum,et al.  Deriving Empirical Ground-Motion Models: Balancing Data Constraints and Physical Assumptions to Optimize Prediction Capability , 2009 .

[10]  Susanne Tina Plapp.  Wahrnehmung von Risiken aus Naturkatastrophen. Eine empirische Untersuchung in sechs gefährdeten Gebieten Süd- und Westdeutschlands [online] , 2003 .

[11]  Bruno Merz,et al.  Review article "Assessment of economic flood damage" , 2010 .

[12]  Rafael Rumí,et al.  Parameter estimation and model selection for mixtures of truncated exponentials , 2010, Int. J. Approx. Reason..

[13]  Carsten Riggelsen,et al.  Learning Bayesian Networks from Incomplete Data: An Efficient Method for Generating Approximate Predictive Distributions , 2006, SDM.

[14]  Bruno Merz,et al.  Multi-variate flood damage assessment: a tree-based data-mining approach , 2013 .

[15]  Daniel Straub,et al.  Natural hazards risk assessment using Bayesian networks , 2005 .

[16]  Rafael Rumí,et al.  Bayesian networks in environmental modelling , 2011, Environ. Model. Softw..

[17]  Adrienne Grêt-Regamey,et al.  Spatially explicit avalanche risk assessment linking Bayesian networks to a GIS , 2006 .

[18]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[19]  Huan Liu,et al.  Discretization: An Enabling Technique , 2002, Data Mining and Knowledge Discovery.

[20]  B. Merz,et al.  Flood damage and influencing factors: New insights from the August 2002 flood in Germany , 2005 .

[21]  Nir Friedman,et al.  The Bayesian Structural EM Algorithm , 1998, UAI.

[22]  David Maxwell Chickering,et al.  Optimal Structure Identification With Greedy Search , 2003, J. Mach. Learn. Res..

[23]  Carsten Riggelsen.  MCMC Learning of Bayesian Network Models by Markov Blanket Decomposition , 2005, ECML.

[24]  Nir Friedman,et al.  Being Bayesian about Network Structure , 2000, UAI.

[25]  Robert Castelo,et al.  On Inclusion-Driven Learning of Bayesian Networks , 2003, J. Mach. Learn. Res..

[26]  Fikret Berkes,et al.  Understanding uncertainty and reducing vulnerability: lessons from resilience thinking , 2007 .

[27]  Bruno Merz,et al.  How useful are complex flood damage models? , 2014 .

[28]  Yuichi S. Hayakawa,et al.  Without power? Landslide inventories in the face of climate change , 2012 .

[29]  Pamela J. Hoyt,et al.  Discretization and Learning of Bayesian Networks using Stochastic Search, with Application to Base Realignment and Closure (BRAC) , 2008 .

[30]  Y. Hayakawa,et al.  Japan's sediment flux to the Pacific Ocean revisited , 2014 .

[31]  Roderick J. A. Little,et al.  Statistical Analysis with Missing Data , 1988 .

[32]  Frank Scherbaum,et al.  Bayesian networks for tsunami early warning , 2011 .

[33]  R. Bouckaert.  Bayesian belief networks : from construction to inference , 1995 .

[34]  Michael Havbro Faber,et al.  Bayesian probabilistic network approach for managing earthquake risks of cities , 2011 .

[35]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[36]  Rafael Rumí,et al.  Aalborg Universitet Inference in hybrid Bayesian networks , 2016 .

[37]  D. Rubin,et al.  Statistical Analysis with Missing Data , 1988 .

[38]  H. Kreibich,et al.  Influence of flood frequency on residential building losses , 2010 .

[39]  Julian J. Bommer,et al.  Capturing and Limiting Groundmotion Uncertainty in Seismic Hazard Assessment , 2005 .

[40]  P. Hill,et al.  Methoden der empirischen Sozialforschung , 1992 .

[41]  Yi Li,et al.  Susceptibility assessment of earthquake-induced landslides using Bayesian network: A case study in Beichuan, China , 2012, Comput. Geosci..

[42]  Thomas D. Nielsen,et al.  Parameter Estimation in Mixtures of Truncated Exponentials , 2008 .

[43]  David M. Boore,et al.  Simulation of Ground Motion Using the Stochastic Method , 2003 .

[44]  Nir Friedman,et al.  Learning Belief Networks in the Presence of Missing Values and Hidden Variables , 1997, ICML.

[45]  Norman Fenton,et al.  Risk Assessment and Decision Analysis with Bayesian Networks , 2012 .

[46]  O. Korup,et al.  Landslide prediction from machine learning , 2014 .

[47]  Nir Friedman,et al.  Data Analysis with Bayesian Networks: A Bootstrap Approach , 1999, UAI.

[48]  Frank Scherbaum,et al.  Bayesian Belief Network for Tsunami Warning Decision Support , 2009, ECSQARU.

[49]  Carsten Riggelsen,et al.  Learning Bayesian Networks: A MAP Criterion for Joint Selection of Model Structure and Parameter , 2008, 2008 Eighth IEEE International Conference on Data Mining.