Extreme Value Theory with Applications to Natural Hazards: From Statistical Theory to Industrial Practice

ISBN-13: 9783030749415 / Angielski / Twarda / 2021 / 494 str.

Nicolas Bousquet; Pietro Bernardara

Spis treści

1 E. Garnier: Extreme Events and History: for a better consideration of natural hazards.- 2 N. Bousquet and P. Bernardara: Introduction.- Part I Standard Extreme Value Theory.- 3 P. Bernardara and N. Bousquet: Probabilistic modeling and statistical quantification of natural hazards.- 4 N. Bousquet: Fundamental concepts of probability and statistics.- 5 M. Andreewsky and N. Bousquet: Collecting and analyzing data.- 6 A. Dutfoy: Univariate extreme value theory: practice and limitations.- Part II Elements of Extensive Statistical Analysis.- 7 J. Weiss and M. Andreewsky: Regional extreme value analysis.- 8 S. Parey, T. Hoang: Extreme values of non-stationary time series.- 9 A. Dutfoy: Multivariate extreme value theory: practice and limits.- 10 S., T. Hoang and N. Bousquet: Stochastic and physics-based simulation of extreme situations.- 11 N. Bousquet: Bayesian extreme value theory.- 12 M. Andreewsky, P. Bernardara, N. Bousquet, A. Dutfoy and S. Parey: Perspectives.- Part III Detailed Case Studies on Natural Hazards.- 13 P. Bernardara: Predicting extreme ocean swells.- 14 M. Andreewsky: Predicting storm surges.- 15 S. Parey: Forecasting extreme winds.- 16 N. Roche and A. Dutfoy: Conjunction of rainfall in neighboring watersheds.- 17 A. Sibler and A. Dutfoy: Conjunction of a flood and a storm.- 18 E. Paquet: SCHADEX: an alternative to extreme value statistics in hydrology.- Appendix A.- Appendix B.- References.- Index.

O autorze

Dr. Nicolas Bousquet is a mathematician specializing in probability and statistics. Trained in computer science, he received his Ph.D in Mathematics from the Paris XI University in 2006. He has developed Bayesian modeling methodologies to merge heterogeneous sources of information into decision support problems in uncertain environments, methods for sensitivity analysis and Monte Carlo acceleration methods within complex numerical models. Awarded Best Young European Statistician by ENBIS in 2016, he worked in industrial risk and environmental resource management at EDF R&D for 9 years and in collaboration with many public and international research centers. He was also an associate researcher at the Institut de Mathématique de Toulouse. Between 2017 and 2020, he was in charge of R&D at Quantmetry, a consulting firm specializing in Artificial Intelligence (AI), while also serving as an Associate Professor at Sorbonne University. He has published about 40 research articles and book chapters and in 2018 he directed the production of the first scientific book translated using artificial intelligence tools (Deep Learning, by Goodfellow, Bengio and Courville). Still an Associate Professor, he is currently the Deputy Head of the industrial AI joint laboratory SINCLAIR (EDF-Total-Thales) and a Expert Researcher at EDF R&D. 

Dr. Pietro Bernardara is a hydrologist and holds a Ph.D from the Politechnico di Milano (2004). With a strong background in applied statistics, he has developed numerous techniques for quantifying extreme natural hazards in river and marine environments to mitigate industrial risks. After working as an expert researcher at EDF R&D, then as a Natural Hazard R&D Manager at EDF Energy (UK), he currently heads the CEREA (Centre for Teaching and Research in Atmospheric Environment) at the Ecole des Ponts ParisTech, as well as the "Atmospheric Environment" Group at EDF R&D. He is the author or co-author of about thirty publications.

 

 

Blurb

This richly illustrated book describes statistical extreme value theory for the quantification of natural hazards, such as strong winds, floods and rainfall, and discusses an interdisciplinary approach to allow the theoretical methods to be applied. The approach consists of a number of steps: data selection and correction, non-stationary theory (to account for trends due to climate change), and selecting appropriate estimation techniques based on both decision-theoretic features (e.g., Bayesian theory), empirical robustness and a valid treatment of uncertainties. It also examines and critically reviews alternative approaches based on stochastic and dynamic numerical models, as well as recently emerging data analysis issues and presents large-scale, multidisciplinary, state-of-the-art case studies. 

Intended for all those with a basic knowledge of statistical methods interested in the quantification of natural hazards, the book is also a valuable resource for engineers conducting risk analyses in collaboration with scientists from other fields (such as hydrologists, meteorologists, climatologists).