Using multi-objective classification to model communities of soil microarthropods

In agricultural soil, a suite of anthropogenic events shape the ecosystem processes and populations. However, the impact from anthropogenic sources on the soil environment is almost exclusively assessed for chemicals, although other factors like crop and tillage practices have an important impact as well. Thus, the farming system as a whole should be evaluated and ranked according to its environmental benefits and impacts. Our starting point is a data set describing agricultural events and soil biological parameters. Using machine learning methods for inducing regression and model trees, we produce empirical models able to predict the soil quality from agricultural measures in terms of quantities describing the soil microarthropod community. We are also interested in discovering additional higher level knowledge. In particular, we have identified the most important factors influencing the population densities of springtails and mites and their biodiversity. We also identify to which agricultural actions different microarthropods react distinctly. To obtain this higher level knowledge, we employ multi-objective regression trees.     

Determination of selected neonicotinoid insecticides by liquid chromatography with thermal lens spectrometric detection

We studied the analysis of trace amounts of neonicotinoid insecticides by liquid chromatography coupled with a thermal lens spectrometric detector (TLS). This multi-residue analysis method is based on the reversed phase separation on C₁₈ column, isocratic elution and collinear dual beam TLS detection. The insecticides thiamethoxam, imidacloprid, acetamiprid and thiacloprid were detected with retention times of 4.4, 5.7, 6.5 and 8.5 min and limits of quantifications of 50, 89, 10, and 25 μg/L, respectively. The retention times agreed well with those obtained by the same chromatographic method but using a diode-array detector (DAD). The limits of quantifications for imidacloprid were identical in both techniques. However, the limits of quantifications for thiamethoxam, acetamiprid and thiacloprid were up to 8.5 times lower using the TLS detector compared to the diode-array detector. The applicability of the developed procedure was tested on spiked river water and potato samples.     

Automatic construction of concept hierarchies: The case of foliage-dwelling spiders

In this paper, we present the hierarchical variable dependencies that were obtained from raw data with the use of two machine learning techniques on an ecological data set. The data set contains features of field margins and the corresponding number of spider species inhabiting them. This data set was used before by domain experts to construct a fuzzy qualitative model with hierarchical variable dependencies, which we use for comparison with our results. One of the machine learning methods constructs a hierarchical structure similar to the one in the experts’ model, while revealing some additional interesting relations of environmental features with respect to the number of spider species. The other method constructs a different hierarchy from the one proposed by the experts, which, according to our classification performance experiments, might be even more appropriate.     

Application of machine learning methods to palaeoecological data

A palaeoecological study was conducted to investigate past environmental conditions and vegetation dynamics around the southwestern Ljubljana Moor. In order to find potential regularities and/or dependencies among co-existent plant species through time, different machine learning methods were applied to pollen records from the cores taken at Bistra and Ho?evarica. The data comprised relative pollen frequencies of the most common plant genera/families at particular core depths that correspond to particular ages in the Early and Mid Holocene periods. The applied methods include equation discovery and hierarchical clustering. Both methods have found plausible and explainable relationships among identified plant genera/families.     

Multicriteria ranking of workplaces regarding working conditions in a mining company

Ranking of workplaces with respect to working conditions is very significant for each company. It indicates the positions where employees are most exposed to adverse effects resulting from the working environment, which endangers their health. This article presents the results obtained for 12 different production workplaces in the copper mining and smelting complex RTB Bor – ‘Veliki Krivelj’ open pit, based on six parameters measured regularly which defined the following working environment conditions: air temperature, light, noise, dustiness, chemical hazards and vibrations. The ranking of workplaces has been performed by PROMETHEE/GAIA. Additional optimization of workplaces is done by PROMETHEE V with the given limits related to maximum permitted values for working environment parameters. The obtained results indicate that the most difficult workplace is on the excavation location (excavator operator). This method can be successfully used for solving similar kinds of problems, in order to improve working conditions.     

Genotoxic potential of selected cytostatic drugs in human and zebrafish cells

Due to their increasing use, the residues of anti-neoplastic drugs have become emerging pollutants in aquatic environments. Most of them directly or indirectly interfere with the cell’s genome, which classifies them into a group of particularly dangerous compounds. The aim of the present study was to conduct a comparative in vitro toxicological characterisation of three commonly used cytostatics with different mechanisms of action (5-fluorouracil [5-FU], cisplatin [CDDP] and etoposide [ET]) towards zebrafish liver (ZFL) cell line, human hepatoma (HepG2) cells and human peripheral blood lymphocytes (HPBLs). Cytotoxicity was determined by 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay and acridine orange/ethidium bromide staining. All three drugs induced time- and dose-dependent decreases in cell viability. The sensitivity of ZFL and HepG2 cells towards the cytotoxicity of 5-FU was comparable (half maximal inhibitory concentration (IC₅₀) 5.3 to 10.4 μg/mL). ZFL cells were more sensitive towards ET- (IC₅₀ 0.4 μg/mL) and HepG2 towards CDDP- (IC₅₀ 1.4 μg/mL) induced cytotoxicity. Genotoxicity was determined by comet assay and cytokinesis block micronucleus (CBMN) assay. ZFL cells were the most sensitive, and HPBLs were the least sensitive. In ZFL cells, induction of DNA strand breaks was a more sensitive genotoxicity endpoint than micronuclei (MNi) induction; the lowest effective concentration (LOEC) for DNA strand break induction was 0.001 μg/mL for ET, 0.01 μg/mL for 5-FU and 0.1 μg/mL for CDDP. In HepG2 cells, MNi induction was a more sensitive genotoxicity endpoint. The LOEC values were 0.01 μg/mL for ET, 0.1 μg/mL for 5-FU and 1 μg/mL for CDDP. The higher sensitivity of ZFL cells to cytostatic drugs raises the question of the impact of such compounds in aquatic ecosystem. Since little is known on the effect of such drugs on aquatic organisms, our results demonstrate that ZFL cells provide a relevant and sensitive tool to screen genotoxic potential of environmental pollutant in the frame of hazard assessment.     

Responses of evergreen and deciduous Quercus species to enhanced ozone levels

Plants of one evergreen oak (Quercus ilex) and three deciduous oaks (Q. faginea, with small leaves; Q. pyrenaica and Q. robur, with large leaves) were exposed both to filtered air and to enhanced ozone levels in Open-Top Chambers. Q. faginea and Q. pyrenaica were studied for the first time. Based on visible injury, gas exchange, chlorophyll content and biomass responses, Q. pyrenaica was the most sensitive species, and Q. ilex was the most tolerant, followed by Q. faginea. Functional leaf traits of the species were related to differences in sensitivity, while accumulated ozone flux via stomata (POD_1.6) partly contributed to the observed differences. For risk assessment of Mediterranean vegetation, the diversity of responses detected in this study should be taken into account, applying appropriate critical levels.     

Additional disturbances as a beneficial tool for restoration of post-mining sites: a multi-taxa approach

Open interior sands represent a highly threatened habitat in Europe. In recent times, their associated organisms have often found secondary refuges outside their natural habitats, mainly in sand pits. We investigated the effects of different restoration approaches, i.e. spontaneous succession without additional disturbances, spontaneous succession with additional disturbances caused by recreational activities, and forestry reclamation, on the diversity and conservation values of spiders, beetles, flies, bees and wasps, orthopterans and vascular plants in a large sand pit in the Czech Republic, Central Europe. Out of 406 species recorded in total, 112 were classified as open sand specialists and 71 as threatened. The sites restored through spontaneous succession with additional disturbances hosted the largest proportion of open sand specialists and threatened species. The forestry reclamations, in contrast, hosted few such species. The sites with spontaneous succession without disturbances represent a transition between these two approaches. While restoration through spontaneous succession favours biodiversity in contrast to forestry reclamation, additional disturbances are necessary to maintain early successional habitats essential for threatened species and open sand specialists. Therefore, recreational activities seem to be an economically efficient restoration tool that will also benefit biodiversity in sand pits.