Search results for "Identifiability"
showing 10 items of 35 documents
The identifiability analysis for setting up measuring campaigns in integrated water quality modelling.
2012
Abstract Identifiability analysis enables the quantification of the number of model parameters that can be assessed by calibration with respect to a data set. Such a methodology is based on the appraisal of sensitivity coefficients of the model parameters by means of Monte Carlo runs. By employing the Fisher Information Matrix, the methodology enables one to gain insights with respect to the number of model parameters that can be reliably assessed. The paper presents a study where identifiability analysis is used as a tool for setting up measuring campaigns for integrated water quality modelling. Particularly, by means of the identifiability analysis, the information about the location and …
Observation and identification tools for non-linear systems: application to a fluid catalytic cracker
2005
In this paper we recall general methodologies we developed for observation and identification in non-linear systems theory, and we show how they can be applied to real practical problems. In a previous paper, we introduced a filter which is intermediate between the extended Kalman filter in its standard version and its high-gain version, and we applied it to certain observation problems. But we were missing some important cases. Here, we show how to treat these cases. We also apply the same technique in the context of our identifiability theory. As non-academic illustrations, we treat a problem of observation and a problem of identification, for a fluid catalytic cracker (FCC). This FCC uni…
Identifiability analysis for receiving water body quality modelling
2009
In urban drainage, new computational possibilities have supported the development of new integrated approaches aimed at joint water quantity and quality analysis of the whole urban drainage system. Although the benefit of an integrated approach has been widely demonstrated, to date, several aspects prevent its applicability such as scarce availability of field data if compared with model complexity. These aspects sometimes prevent the correct estimation of parameters thus leading to large uncertainty in modelling response. This is a typical parameter identifiability problem that is discussed in the present paper evaluating the effect of identifiability procedures in increasing operator conf…
Do-search -- a tool for causal inference and study design with multiple data sources
2020
Epidemiologic evidence is based on multiple data sources including clinical trials, cohort studies, surveys, registries, and expert opinions. Merging information from different sources opens up new possibilities for the estimation of causal effects. We show how causal effects can be identified and estimated by combining experiments and observations in real and realistic scenarios. As a new tool, we present do-search, a recently developed algorithmic approach that can determine the identifiability of a causal effect. The approach is based on do-calculus, and it can utilize data with nontrivial missing data and selection bias mechanisms. When the effect is identifiable, do-search outputs an i…
Causal Effect Identification from Multiple Incomplete Data Sources: A General Search-Based Approach
2021
Causal effect identification considers whether an interventional probability distribution can be uniquely determined without parametric assumptions from measured source distributions and structural knowledge on the generating system. While complete graphical criteria and procedures exist for many identification problems, there are still challenging but important extensions that have not been considered in the literature. To tackle these new settings, we present a search algorithm directly over the rules of do-calculus. Due to generality of do-calculus, the search is capable of taking more advanced data-generating mechanisms into account along with an arbitrary type of both observational and…
Estimation of causal effects with small data in the presence of trapdoor variables
2021
We consider the problem of estimating causal effects of interventions from observational data when well-known back-door and front-door adjustments are not applicable. We show that when an identifiable causal effect is subject to an implicit functional constraint that is not deducible from conditional independence relations, the estimator of the causal effect can exhibit bias in small samples. This bias is related to variables that we call trapdoor variables. We use simulated data to study different strategies to account for trapdoor variables and suggest how the related trapdoor bias might be minimized. The importance of trapdoor variables in causal effect estimation is illustrated with rea…
Surrogate outcomes and transportability
2019
Identification of causal effects is one of the most fundamental tasks of causal inference. We consider an identifiability problem where some experimental and observational data are available but neither data alone is sufficient for the identification of the causal effect of interest. Instead of the outcome of interest, surrogate outcomes are measured in the experiments. This problem is a generalization of identifiability using surrogate experiments and we label it as surrogate outcome identifiability. We show that the concept of transportability provides a sufficient criteria for determining surrogate outcome identifiability for a large class of queries.
Assessment of the integrated urban water quality model complexity through identifiability analysis
2010
Urban sources of water pollution have often been cited as the primary cause of poor water quality in receiving water bodies (RWB), and recently many studies have been conducted to investigate both continuous sources, such as wastewater-treatment plant (WWTP) effluents, and intermittent sources, such as combined sewer overflows (CSOs). An urban drainage system must be considered jointly, i.e., by means of an integrated approach. However, although the benefits of an integrated approach have been widely demonstrated, several aspects have prevented its wide application, such as the scarcity of field data for not only the input and output variables but also parameters that govern intermediate st…
Identifiability analysis for pressure sensors positioning
2017
The identifiability analysis is investigated as sampling design method aimed to the leakage detection in looped water distribution networks. The preliminary ranking of the candidate nodes for the pressure sensors positioning is performed by running several hydraulic simulations and calculating sensitivity functions. The reduced subset of nodes and their sensitivities are then used to perform the identifiability analysis by calculating the collinearity index which provides the maximum number of sensors and their location into the network. The index selects the nodes according to their sensitivities to several leakages scenarios, simulated in EPANET by changing the emitter coefficient of the …
Optimal measurement setup for damage detection in piezoelectric plates
2009
[EN] An optimization of the excitation-measurement configuration is proposed for the characterization of damage in PZT-4 piezoelectric plates, from a numerical point of view. To perform such an optimization, a numerical method to determine the location and extent of defects in piezoelectric plates is developed by combining the solution of an identification inverse problem, using genetic algorithms and gradient-based methods to minimize a cost functional, and using an optimized finite element code and meshing algorithm. In addition, a semianalytical estimate of the probability of detection is developed and validated, which provides a flexible criterion to optimize the experimental design. Th…