Modelling has permeated virtually all areas of industrial,environmental, economic, bio-medical or civil engineering: yet theuse of models for decision-making raises a number of issues towhich this book is dedicated:
How uncertain is my model ? Is it truly valuable to supportdecision-making ? What kind of decision can be truly supported andhow can I handle residual uncertainty ? How much refined should themathematical description be, given the true data limitations ?Could the uncertainty be reduced through more data, increasedmodeling investment or computational budget ? Should it be reducednow or later ? How robust is the analysis or the computationalmethods involved ? Should / could those methods be more robust ?Does it make sense to handle uncertainty, risk, lack of knowledge,variability or errors altogether ? How reasonable is the choice ofprobabilistic modeling for rare events ? How rare are the events tobe considered ? How far does it make sense to handle extremeevents and elaborate confidence figures ? Can I take advantage ofexpert / phenomenological knowledge to tighten the probabilisticfigures ? Are there connex domains that could provide models orinspiration for my problem ?
Written by a leader at the crossroads of industry, academia andengineering, and based on decades of multi-disciplinary fieldexperience, Modelling Under Risk and Uncertainty gives aself-consistent introduction to the methods involved by any type ofmodeling development acknowledging the inevitable uncertainty andassociated risks. It goes beyond the "black-box" viewthat some analysts, modelers, risk experts or statisticians developon the underlying phenomenology of the environmental or industrialprocesses, without valuing enough their physical properties andinner modelling potential nor challenging the practicalplausibility of mathematical hypotheses; conversely it is also toattract environmental or engineering modellers to better handlemodel confidence issues through finer statistical and risk analysismaterial taking advantage of advanced scientific computing, to facenew regulations departing from deterministic design or supportrobust decision-making.
Modelling Under Risk and Uncertainty:
* Addresses a concern of growing interest for large industries,environmentalists or analysts: robust modeling for decision-makingin complex systems.
* Gives new insights into the peculiar mathematical andcomputational challenges generated by recent industrial safety orenvironmental control analysis for rare events.
* Implements decision theory choices differentiating oraggregating the dimensions of risk/aleatory and epistemicuncertainty through a consistent multi-disciplinary set ofstatistical estimation, physical modelling, robust computation andrisk analysis.
* Provides an original review of the advanced inverseprobabilistic approaches for model identification, calibration ordata assimilation, key to digest fast-growing multi-physical dataacquisition.
* Illustrated with one favourite pedagogical example crossingnatural risk, engineering and economics, developed throughout thebook to facilitate the reading and understanding.
* Supports Master/PhD-level course as well as advanced tutorialsfor professional training
Analysts and researchers in numerical modeling, appliedstatistics, scientific computing, reliability, advancedengineering, natural risk or environmental science will benefitfrom this book.