Sensitivity Analysis is a set of statistical techniques that can be used to investigate the behaviour of a numerical model. In particular, Sensitivity Analysis investigates how variations in the model inputs reflect into variations in the model outputs so to: (i) identify those inputs, if any, that have negligible influence on the model output; (ii) rank the influential inputs according to their relative importance; (iii) identify thresholds or regions in the input space that maps into particularly interesting output values (e.g. extremes). This information can be useful for a variety of purposes, including: to support the model calibration by identifying the parameters that play a minor role and therefore can be excluded by computationally-expensive calibration tasks; to support model validation by evaluating the consistency between our understanding of the system behaviour and the model behaviour, e.g. activation of different model components at different time-steps; to investigate uncertainty propagation from different sources, for instance input forcing errors, uncertain parameters or boundary conditions, and thus prioritize efforts for uncertainty reduction.
Given their generic and widely applicable underlying principles, Sensitivity Analysis techniques can be applied to any application domain where numerical models are used, independently of the nature and meaning of the model variables and equations, and even more generally to any input-output sample (e.g. datasets generated in a lab or collected from other sources).
- 1 hour introduction to Sensitivity Analysis and the SAFE Toolbox 
- 1 hour computer session (using own laptop with Matlab/Octave installed) using SAFE Toolbox
- Basic statistics
- Basic Matlab/Octave programming (or equivalent languages like C, R, Python)
Numbers are limited so booking via this Eventbrite is essential.
 Pianosi, F., Sarrazin, F., T Wagener (2015), A Matlab Toolbox for Global ensitivity Analysis, Environmental Modelling & Software, In press.
 Butler, MP , PM Reed, K Fisher-Vanden, K Keller, T Wagener (2014), Identifying parametric controls and dependencies in integrated assessment models using global sensitivity analysis, Environmental Modelling & Software, 59, 10-29.
 Chen, W., Jin, R.C., Sudjianto, A. (2005), Analytical Variance-Based Global Sensitivity Analysis In Simulation-Based Design Under Uncertainty, Journal of Mechanical Design, 127(5), 875-886.
 Kiparissides, A., Kucherenko, S.S. Mantalaris, A. and Pistikopoulos E.N. (2009), Global Sensitivity Analysis Challenges In Biological Systems Modeling, Industrial & Engineering Chemistry Research, 48 (15), 7168-7180.
 Herman, JD , JB Kollat, PM Reed, T Wagener (2013), Method of Morris effectively reduces the computational demands of global sensitivity analysis for distributed watershed models, Hydrology and Earth System Sciences 17 (7), 2893-2903.
 Han, X, CA Kelleher, GP Warn, T Wagener (2013), Identification of the controlling mechanism for predicting critical loads in elastomeric bearings, Journal of Structural Engineering, 139(12).
 Sin, G., Gernaey, K.V., Neumann, M.B. et al. (2011), Global Sensitivity Analysis in Wastewater Treatment Plant Model Applications: Prioritizing Sources of Uncertainty, Water Research, 45(2), 39-651.
 Triantaphyllou, E.; A. Sanchez (1997), A Sensitivity Analysis Approach For Some Deterministic Multi-Criteria Decision-Making Methods, Decision Sciences, 28 (1): 151–194.
 Murray, C.J.L., Lopez, A.D., Jamison, D.T, (1994), The Global Burden Of Disease In 1990 - Summary Results, Sensitivity Analysis And Future-Directions, Bulletin of the World Health Organization, 72(3), 495-509.
 Giannetti, B. F.; Bonilla, S. H.; Silva, C. C.; Et Al. (2009), The Reliability Of Experts' Opinions In Constructing A Composite Environmental Index: The Case Of ESI 2005, Journal of Environmental Management, 90(8), 2448-2459.
 Morris, D. J., Speirs, D. C.; Cameron, A. I.; et al. (2014) Global sensitivity analysis of an end-to-end marine ecosystem model of the North Sea: Factors affecting the biomass of fish and benthos, ECOLOGICAL MODELLING, 273, 251-263.