ENVIRONMENTAL DATA MINING AND MODELLING BASED ON MACHINE LEARNING ALGORITHMS AND GEOSTATISTICS (PREPRINT IBRAE-2002-13)

Preprint IBRAE-2002-13

Parkin R., Kanevski M., Pozdnukhov A., Timonin V., Maignan M., Yatsalo B., Canu S.

The paper presents some contemporary approaches to the spatial environmental data analysis, processing and presentation. The main topics are concentrated on the decision–oriented problems of environmental and pollution spatial data mining and modelling. The set of tools used consists of machine learning algorithms (MLA) – Multilayer Perceptron and Support Vector Regression, and recently developed geostatistical predictive and simulation models. The innovative part of the report deals with integrated/hybrid models, including ML Residuals Kriging predictions and ML Residuals Sequential Gaussian simulations. ML algorithms efficiently solve problems of spatial non-stationarity, which are difficult for geostatistical approach, but geostatistical tools are widely and successfully applied to characterise the performance of the ML algorithms, analysing the quality and quantity of the spatially structured information extracted from data by ML. Moreover, mixture of ML data driven and geostatistical model based approaches are attractive for decision-making process..

Bibliographical reference 

Parkin R., Kanevski M., Pozdnukhov A., Timonin V., Maignan M., Yatsalo B., Canu S. ENVIRONMENTAL DATA MINING AND MODELLING BASED ON MACHINE LEARNING ALGORITHMS AND GEOSTATISTICS. Preprint IBRAE-2002-13. Moscow: Nuclear Safety Institute RAS, 2002. 13p. — Refs.: 9 items.