Artificial Neural Networks and Spatial Estimation of Chernobyl Fallout

Kanevsky, M. B.; Arutyunyan, R. V.; Bolshov, L. A.; Demyanov, Vasily; Maignan, M.

doi:10.6010/geoinformatics1990.7.1-2_5

Cited by 57 publications

(28 citation statements)

References 10 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Starting with an analysis of the monitoring network and the identification of possible clusters, the measurements are then analysed using statistics and geostatistics for identifying outliers and spatial correlations. These first stages are common to all environmental mapping tasks and we refer to (Kanevski and Maignan 2004) for a comprehensive description of the methodology. The next step concerns the data preparation for the training of the algorithm.…”

Section: General Methodologymentioning

confidence: 99%

Multi-scale support vector algorithms for hot spot detection and modelling

Pozdnoukhov

Kanevski

2007

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

The algorithmic approach to data modelling has developed rapidly these last years, in particular methods based on data mining and machine learning have been used in a growing number of applications. These methods follow a data-driven methodology, aiming at providing the best possible generalization and predictive abilities instead of concentrating on the properties of the data model. One of the most successful groups of such methods is known as Support Vector algorithms. Following the fruitful developments in applying Support Vector algorithms to spatial data, this paper introduces a new extension of the traditional support vector regression (SVR) algorithm. This extension allows for the simultaneous modelling of environmental data at several spatial scales. The joint influence of environmental processes presenting different patterns at different scales is here learned automatically from data, providing the optimum mixture of short and large-scale models. The method is adaptive to the spatial scale of the data. With this advantage, it can provide efficient means to model local anomalies that may typically arise in situations at an early phase of an environmental emergency. However, the proposed approach still requires some prior knowledge on the possible existence of such short-scale patterns. This is a possible limitation of the method for its implementation in early warning systems. The purpose of this paper is to present the multi-scale SVR model and to illustrate its use with an application to the mapping of Cs 137 activity given the measurements taken in the region of Briansk following the Chernobyl accident.

show abstract

Section: General Methodologymentioning

confidence: 99%

Multi-scale support vector algorithms for hot spot detection and modelling

Pozdnoukhov

Kanevski

2007

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

show abstract

“…This problem was traditionally tackled using methods such as (Weber 1992(Weber , 1994: kriging, inverse distance weighting, interpolating polynomials, splines, etc., and more recently through neural networks (Chakraborty et al 1992;Kanevski et al 1996;Demyanov et al 2001;Koike et al 2001).…”

Section: Introductionmentioning

confidence: 96%

Support vector machines and gradient boosting for graphical estimation of a slate deposit

Matías

Liste

Taboada

et al. 2004

Stochastic Environmental Research and Risk Assessment

View full text Add to dashboard Cite

Critical for an efficient and effective exploitation of a slate mine is to obtain information on its technical quality, in other words, on the exploitability potential of the deposit. We applied support vector machines (SVM) and LS-Boosting to the assessment of the technical quality of a new unexploited area of a mine, and compared the results to those obtained for kriging and neural networks. Firstly we analyzed the relationship between kriging and semi-parametric SVM in a regularization framework and explored the different alternatives for training these networks. Subsequently, in an attempt to combine both radial and projection structures, we formulated a boosting technique for radial basis function (RBF) networks defined over projections in the input space (RBFPP). The application of these techniques to our test drilling data demonstrated a similar level of performance for all the estimators examined, with the main difference occurring in the shape of the respective deposit reconstructions. Therefore, in choosing between the different techniques, an essential aspect will be their ability to reproduce the morphological characteristics of the true process. In this paper we also evaluate the benefits of using the estimated covariogram as the kernel of the SVMs and compare the sparsity of the different solutions. The results obtained show that the selection of a standard kernel that ignores the variability structure of the problem produces poorer results than when the estimated covariogram is used as the kernel.

show abstract

“…spatial interpolation, Mantoglou, 2002, or pilot point andKriging methods, RamaRao et al 1995). Neural networks were proposed by Cybenko (1989), Murata (1996), Kanevsky et al (1996) and Candés (1999) for approximating multi-dimensional spatial functions while Torfs and Bier (2000) used neural networks with a sigmoidal transfer function for parameterizing the transmissivity in the context of inverse aquifer modelling.…”

Section: Introductionmentioning

confidence: 99%

Estimation of heterogeneous aquifer parameters from piezometric data using ridge functions and neural networks

Mantoglou

2003

Stochastic Environmental Research and Risk Assessment (SERRA)

View full text Add to dashboard Cite

Inverse modeling aims to estimate transmissivity and other parameters needed by distributed aquifer models, using piezometric measurements. While these parameters are highly variable in space, the twodimensional aquifer area is essentially empty of measurements (''curse of dimensionality''). To address this problem, a representation of the twodimensional transmissivity map based on ridge functions and neural networks is introduced and applied to inverse aquifer modeling. The proposed representation has good expressive power, i.e. it is concise and convergences quickly as the number of parameters are increased, and it is expected to express complex transmissivity variations with relatively few parameters which can be estimated from the piezometric measurements. A simple regularization that can dampen erratic high frequency terms in the estimated parameters is suggested. Several examples indicate that the proposed parameterization can handle diverse types of transmissivity variations while it is particularly suited when the true transmissivity map exhibits specific sorts of heterogeneity with large anisotropies or abrupt changes along lines.

show abstract

Artificial Neural Networks and Spatial Estimation of Chernobyl Fallout

Cited by 57 publications

References 10 publications

Multi-scale support vector algorithms for hot spot detection and modelling

Multi-scale support vector algorithms for hot spot detection and modelling

Support vector machines and gradient boosting for graphical estimation of a slate deposit

Estimation of heterogeneous aquifer parameters from piezometric data using ridge functions and neural networks

Contact Info

Product

Resources

About