Advanced geostatistical and machine-learning models for spatial data analysis of radioactively contaminated regions

Radioactive soil-contamination mapping and risk assessment is a vital issue for decision makers. Traditional approaches for mapping the spatial concentration of radionuclides employ various regression-based models, which usually provide a single-value prediction realization accompanied (in some cases) by estimation error. Such approaches do not provide the capability for rigorous uncertainty quantification or probabilistic mapping. Machine learning is a recent and fast-developing approach based on learning patterns and information from data. Artificial neural networks for prediction mapping have been especially powerful in combination with spatial statistics. A data-driven approach provides the opportunity to integrate additional relevant information about spatial phenomena into a prediction model for more accurate spatial estimates and associated uncertainty. Machine-learning algorithms can also be used for a wider spectrum of problems than before: classification, probability density estimation, and so forth. Stochastic simulations are used to model spatial variability and uncertainty. Unlike regression models, they provide multiple realizations of a particular spatial pattern that allow uncertainty and risk quantification. This paper reviews the most recent methods of spatial data analysis, prediction, and risk mapping, based on machine learning and stochastic simulations in comparison with more traditional regression models. The radioactive fallout from the Chernobyl Nuclear Power Plant accident is used to illustrate the application of the models for prediction and classification problems. This fallout is a unique case study that provides the challenging task of analyzing huge amounts of data ('hard' direct measurements, as well as supplementary information and expert estimates) and solving particular decision-oriented problems.

Spatial distribution and biomass of aquatic rooted macrophytes and their relevance in the metabolism of a Mediterranean coastal lagoon

This work aims to characterise the current autotrophic compartment of the Albufera des Grau coastal lagoon (Menorca, Balearic Islands) and to assess the relationship between the submerged macrophytes and the limnological parameters of the lagoon. During the study period the submerged vegetation was dominated by the macrophyte Ruppia cirrhosa, which formed dense extensive meadows covering 79% of the surface. Another macrophyte species, Potamogeton pectinatus, was also observed but only forming small stands near the rushing streams. Macroalgae were only occasionally observed. Macrophyte biomass showed a clear seasonal trend, with maximum values in July. The biomass of R. cirrhosa achieved 1760 g DW m-2, the highest biomass ever reported for this species in the literature. The seasonal production-decomposition cycle of the macrophyte meadows appears to drive the nutrient dynamics and carbon fluxes in the lagoon. Despite the significant biomass accumulation and the absence of a washout of nutrients and organic matter to the sea, the lagoon did not experience a dystrophic collapse. These results indicate that internal metabolism is more important than exchange processes in the lagoon.