Abstract
Extreme environmental events have considerable impacts on society. Preparation to mitigate or forecast accurately these events is a growing concern for governments. In this regard, policy and decision makers require accurate tools for risk estimation in order to take informed decisions. This work proposes a Bayesian framework for a unified treatment and statistical modeling of the main components of risk: hazard, vulnerability and exposure. Risk is defined as the expected economic loss or population affected as a consequence of a hazard event. The vulnerability is interpreted as the loss experienced by an exposed population due to hazard events. The framework combines data of different spatial and temporal supports. It produces a sequence of temporal risk maps for the domain of interest including a measure of uncertainty for the hazard and vulnerability. In particular, the considered hazard (rainfall) is interpolated from point-based measured rainfall data using a hierarchical spatio-temporal Kriging model, whose parameters are estimated using the Bayesian paradigm. Vulnerability is modeled using zero-inflated distributions with parameters dependent on climatic variables at local and large scales. Exposure is defined as the total population settled in the spatial domain and is interpolated using census data. The proposed methodology was applied to the Vargas state of Venezuela to map the spatio-temporal risk for the period 1970–2006. The framework highlights both high and low risk areas given extreme rainfall events.
Similar content being viewed by others
References
Banerjee S, Carlin B, Gelfand A (2014) Hierarchical modeling and analysis for spatial data, 2nd edn. CRC Press/Chapman Hall, Boca Raton
Bartlett M (1934) On the theory of statistical regression. Proc R Soc Edinb 53:260–283
Bravo L et al (2014) Repositorio de Datos Hidroclimáticos para la Gestión de Riesgos Epidemiológicos y Ambientales. USB-UCV-FONACIT, Caracas
Cardona O, Carreño M (2011) Updating the indicators of disaster risk and risk management for the Americas. J Integr Disaster Risk Manag 1(1):27–47
Centro de Estadística y Matemáticas Aplicadas (2015) Repositorio de Datos Hidroclimáticos para la Gestión de Riesgos Epidemiológicos y Ambientales. https://github.com/CEsMA/ARGUs
Coles S, Pericchi L (2003) Anticipating catastrophes through extreme value modelling. J R Stat Soc Ser C 52(4):405–416
Colón L (2013) Sources of societal vulnerability to extreme weather. Master Thesis
CRED (2013) Center for research on the epidemiology of disasters. https://www.cred.be. Accessed 2013
Cutter S, Finch C (2008) Temporal and spatial changes in social vulnerability to natural hazards. PNAS 105(7):2301–2306
Desinventar (2014) Sistema de inventario de efectos de desastres. https://www.desinventar.org/es/ Accessed 2014–2016
Downing T et al (1999) Climate, change and risk. Routledge, London
Ediciones Ediarte y Editorial El Nacional (2006) Venezuela en datos 2007. 320 p
FUNVISIS (2013) Estudios y Desastres, Fundación Venezolana de Investigaciones Sismológicas. http://www.estudiosydesastres.gob.ve/. Accessed 2013
Gamerman D, Lopes H (2006) Markov chain monte carlo: stochastic simulation for bayesian inference, 2nd edn. Chapman & Hall/CRC, Boca Raton
Garay A, Lachos V, Bolfarine H (2015) Bayesian estimation and case influence diagnostics for the zero-inflated negative binomial regression model. J Appl Stat 42(6):1148–1165. https://doi.org/10.1080/02664763.2014.995610
Gelfand A, Ghosh S (1998) Model choice: a minimum posterior predictive loss approach. Biometrika 85(1):1–11
Gelman A, Meng X, Stern H (1996) Posterior predictive assessment of model fitness via realized discrepancies. Stat Sin 6:733–807
Ghosh S, Mukhopadhyay P, Lu J (2006) Bayesian analysis of zero-inflated regression models. J Stat Plan Inference 136(4):1360–1375
Gneiting T, Balabdaoui F, Raftery A (2007) Probabilistic forecasts, calibration and sharpness. J R Stat Soc Ser B (Stat Methodol) 69(2):243–268
IPCC (2012) Managing the risks of extreme events and disasters to advance climate change adaptation. In: Field CB, Barros V, Stocker TF, Qin D, Dokken DJ, Ebi KL, Mastrandrea MD, Mach KJ, Plattner G-K, Allen SK, Tignor M, Midgley PM (eds) Special report of the intergovernmental panel on climate change. Cambridge University Press, Cambridge, p 582. https://www.ipcc.ch/report/managing-the-risks-of-extreme-events-and-disasters-to-advance-climate-change-adaptation/
Lambert D (1992) Zero-inflated Poisson regression, with an application to defects in manufacturing. Technometrics 34(1):1–14
Lapajne J (1981) Social and economic aspects of seismic risk. In: Proceeding of the third international conference: the social and economic aspect of earthquakes and planning to mitigate their impacts. pp 103–112
Le N, Zidek J (1992) Interpolation with uncertain spatial covariances: a Bayesian alternative to kriging. J Multivar Anal 43(2):351–374
Le N, Zidek J (2006) Statistical analysis of environmental space-time processes. Springer, Berlin
Liu B, Siu Y, Mitchell G (2016) A quantitative model for estimating risk from multiple interacting natural hazards: an application to northeast Zhejiang, China. Stoch Environ Res Risk Assess 31:1319–1340. https://doi.org/10.1007/s00477-016-1250-6
Lunn D, Thomas A, Best N, Spiegelhalter D (2000) WinBUGS and Ndash; a Bayesian modelling framework: concepts, structure and extensibility. Stat Comput 10(4):325–337
Martínez R (2015) Una aproximación bayesiana a la medición de la vulnerabilidad poblacional a desastres naturales: estudio de caso para el Estado Plurinacional de Bolivia
Merz B, Thieken A, Gocht M (2007) Flood risk mapping at the local scale: concepts and challenges. In: Begum S, Stive MJF, Hall JW (eds) Flood risk management in europe. Advances in natural and technological hazards research, vol 25. Springer, Dordrecht, pp 231–251
Migon H, Gamerman D (2014) Statistical inference: an integrated approach, second edn. Chapman & Hall/CRC, Boca Raton
Ming X, Xu W, Li Y, Du J, Liu B, Shi P (2015) Quantitative multi-hazard risk assessment with vulnerability surface and hazard joint return period. Stoch Environ Res Risk Assess 29(1):35–44
Ntzoufras I (2011) Bayesian modeling using WinBUGS, vol 698. Wiley, Hoboken
Patt A, Tadross M, Nussbaumer P et al (2010) Estimating least-developed countries’ vulnerability to climate-related extreme events over the next 50 years. PNAS 107(4):1333–1337
Plate E (1996) Risk management for hydraulic systems under hydrologic loads. In: Third Kovacs colloquium on risk reliability. Uncertainty and robustness of resources systems. UNESCO, Paris
R Core Team (2017) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna
Rodríguez J, Guenni L (2013) Bayesian analysis of population vulnerability to rainfall events in Venezuela. IDRiM J 3(1):137–154
Sajo-Castelli AM, Villalta D, Bravo de Guenni L (2014) A ser sometido a Journal of Statistical Software. A bayesian model for the prediction of hidrometeorological risks: An application to Venezuela
Spiegelhalter D, Best N, Carlin B, Van der Linde A (2002) Bayesian measures of model complexity and fit. J R Stat Soc B 64(4):583639
UNDP (2004) Reducing disaster risk: a challenge for development. Technical report, Bureau for Crisis Prevention and Recovery, Nueva York, USA
United Nations (2013) Living with risk: a global review of disaster reduction initiatives. http://www.unisdr.org/we/inform/publications/657. Accessed 2013
Velasco M, Cerrillo S (2010) Un Modelo de Regresión Poisson Inflado con Ceros para Analizar datos de un Experimento de Fungicidas en Jitomate. Memoria del 2 Encuentro Iberoamericano de Biometría y la V Reunión de la Región Centroamericana y del Caribe de la Sociedad Internacional de Biometría p 16. ISBN: 9783659052163
Velázquez C, Cardona O, Yamín L, Mora CM, Carreño TM, Barbat BH (2013) Hybrid loss exceedance curve (HLEC) for risk assessment. In: Proceedings of the 10th international symposium computational civil engineering: IASI, Romania, May 25th, 2012, Societatea Academica, pp 155–174
Vörösmarty C, Bravo de Guenni L, Wollheim W, Pellerin B, Bjerklie D, Cardoso M, D’Almeida C, Green P, Colón L (2013) Extreme rainfall, vulnerability and risk: a continental-scale assessment for South America. Philos Trans R Soc Lond A Math Phys Eng Sci 371(2002):1–18
Yohe G (2002) Indicators for social and economic coping capacity: moving toward a working definition of adaptive capacity. Glob Environ Change 12(1):25–40
Acknowledgements
This work was partially supported by the Venezuelan Academy of Physical, Mathematical and Natural Sciences (ACFIMAN), the Inter-American Network of Academies of Sciences (IANAS) and Research and Development Deanery, USB (Grant No. GID-065).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
A Appendix
A Appendix
1.1 A. 1 Spatial-temporal hierarchical Bayesian Kriging
The components of the rainfall posterior predictive distribution given by Eq. (4) are described as follows.
where l defines the degrees of freedom from the marginal distribution for the observable values and q is the number of degrees of freedom for the conditional distribution of the non-observable values conditioned on the observable values. These should satisfy the conditions: \(l=\delta +n-u-g+1\) and \(q=\delta -u+1\). The values l and q must be positive to avoid degenerate probability distributions. Since l and q decrease when u increases, for a fixed number of observations, the number of new estimation u should be bounded. The components of Eq. (13) are defined as
\(\widehat{B}^{[g]}\) and S are the usual least-squares estimators. Using the Bartlett’s decomposition (Bartlett 1934), the variance-covariance matrix \(\varSigma \) can be re-parameterized as follows
where
- \(\varSigma _{gg}\):
is the \((g\times g)\) variance-covariance matrix of \({{\,\mathrm{\mathrm {Y}}\,}}_t^{[g]}\),
- \(\varSigma _{u\,|\,g}\):
is defined as \(\varSigma _{u\,|\,g}=\varSigma _{uu}-\varSigma _{ug}\; \varSigma _{gg}^{-1}\; \varSigma _{gu}\) with dimensions \(u\times u\), and
- \(\tau \):
is a \((u\times g)\) matrix defined by \(\varSigma _{ug}\;\varSigma _{gg}^{-1}\).
After this re-parameterization, the \(\varSigma \) prior distribution defined in the Eq. (3), can be represented as
The constants describing Eq. (4) are given by the formulas:
The remaining terms are given by
and the final model for \({{\,\mathrm{\mathrm {Y}}\,}}\) is
where \(N(\,,\,)\) denotes a Gaussian Multivariate distribution; \(\beta _0\) is the hyper-parameter mean vector of the \(\beta \) coefficients, with dimensions \(l\times (g+u)\); \(F^{-1}\) is a \(l\times l\) matrix describing the variance among the l rows of \(\beta \); Z is the covariates matrix and GIW denotes the generalized inverse Wishart distribution with parameters \((\varTheta ,\,\delta )\). The hyper-parameter vector \(\mathcal {H}\) is the set \({\varTheta ,\,\delta ,\,F,\,\beta _0}\). The coefficient matrix \(\beta : l\times (u+g)\) and the covariance matrix \(\varSigma : (u+g)\times (u+g)\) can be partitioned according to the block data structure.
1.2 A. 2 Conditional probability distributions for the hierarchical zero-inflated negative binomial model
The conditional posterior probability distribution for the parameter vector \(\varvec{\beta }\) is given by
The posterior conditional distribution for \(\varvec{\gamma }\) is
The conditional posterior distributions for \(\sigma ^2_{\beta }\) and \(\sigma ^2_{\gamma }\) are
Finally, the posterior conditional distribution for \(\varvec{\theta }\) is given by
Rights and permissions
About this article
Cite this article
Villalta, D.E., Bravo de Guenni, L. & Sajo-Castelli, A.M. Spatio-temporal modelling of hydro-meteorological derived risk using a Bayesian approach: a case study in Venezuela. Stoch Environ Res Risk Assess 34, 513–529 (2020). https://doi.org/10.1007/s00477-020-01783-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-020-01783-3