Whereas temporal variability of plant phenology in response to climate change has already been well studied, the spatial variability of phenology is not well understood. Given that phenological shifts may affect biotic interactions, there is a need to investigate how the variability in environmental factors relates to the spatial variability in herbaceous species' phenology by at the same time considering their functional traits to predict their general and species-specific responses to future climate change. In this project, we analysed phenology records of 148 herbaceous species, which were observed for a single year by the PhenObs network in 15 botanical gardens. For each species, we characterised the spatial variability in six different phenological stages across gardens. We used boosted regression trees to link these variabilities in phenology to the variability in environmental parameters (temperature, latitude and local habitat conditions) as well as species traits (seed mass, vegetative height, specific leaf area and temporal niche) hypothesised to be related to phenology variability. We found that spatial variability in the phenology of herbaceous species was mainly driven by the variability in temperature but also photoperiod was an important driving factor for some phenological stages. In addition, we found that early-flowering and less competitive species characterised by small specific leaf area and vegetative height were more variable in their phenology. Our findings contribute to the field of phenology by showing that besides temperature, photoperiod and functional traits are important to be included when spatial variability of herbaceous species is investigated.

• MeSH
• fenotyp MeSH
• fotoperioda * MeSH
• klimatické změny MeSH
• listy rostlin * fyziologie   MeSH
• roční období MeSH
• rostliny MeSH
• teplota MeSH
• Publikační typ
• časopisecké články MeSH

River ecosystems are threatened by future changes in land use and climatic conditions. However, little is known of the influence of interactions of these two dominant global drivers of change on ecosystems. Does the interaction amplify (synergistic interaction) or buffer (antagonistic interaction) the impacts and does their interaction effect differ in magnitude, direction and spatial extent compared to single independent pressures. In this study, we model the impact of single and interacting effects of land use and climate change on the spatial distribution of 33 fish species in the Elbe River. The varying effects were modeled using step-wise boosted regression trees based on 250 m raster grid cells. Species-specific models were built for both 'moderate' and 'extreme' future land use and climate change scenarios to assess synergistic, additive and antagonistic interaction effects on species losses, species gains and diversity indices and to quantify their spatial distribution within the Elbe River network. Our results revealed species richness is predicted to increase by 0.7-2.9 species by 2050 across the entire river network. Changes in species richness are likely to be spatially variable with significant changes predicted for 56-85% of the river network. Antagonistic interactions would dominate species losses and gains in up to 75% of the river network. In contrast, synergistic and additive effects would occur in only 20% and 16% of the river network, respectively. The magnitude of the interaction was negatively correlated with the magnitudes of the single independent effects of land use and climate change. Evidence is provided to show that future land use and climate change effects are highly interactive resulting in species range shifts that would be spatially variable in size and characteristic. These findings emphasize the importance of adaptive river management and the design of spatially connected conservation areas to compensate for these high species turnovers and range shifts.

• MeSH
• biodiverzita MeSH
• klimatické změny * MeSH
• řeky MeSH
• ryby * MeSH
• teoretické modely * MeSH
• zachování přírodních zdrojů MeSH
• zvířata MeSH
• Check Tag
• zvířata MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• Geografické názvy
• Evropa MeSH

The future distribution of river fishes will be jointly affected by climate and land use changes forcing species to move in space. However, little is known whether fish species will be able to keep pace with predicted climate and land use-driven habitat shifts, in particular in fragmented river networks. In this study, we coupled species distribution models (stepwise boosted regression trees) of 17 fish species with species-specific models of their dispersal (fish dispersal model FIDIMO) in the European River Elbe catchment. We quantified (i) the extent and direction (up- vs. downstream) of predicted habitat shifts under coupled "moderate" and "severe" climate and land use change scenarios for 2050, and (ii) the dispersal abilities of fishes to track predicted habitat shifts while explicitly considering movement barriers (e.g., weirs, dams). Our results revealed median net losses of suitable habitats of 24 and 94 river kilometers per species for the moderate and severe future scenarios, respectively. Predicted habitat gains and losses and the direction of habitat shifts were highly variable among species. Habitat gains were negatively related to fish body size, i.e., suitable habitats were projected to expand for smaller-bodied fishes and to contract for larger-bodied fishes. Moreover, habitats of lowland fish species were predicted to shift downstream, whereas those of headwater species showed upstream shifts. The dispersal model indicated that suitable habitats are likely to shift faster than species might disperse. In particular, smaller-bodied fish (<200 mm) seem most vulnerable and least able to track future environmental change as their habitat shifted most and they are typically weaker dispersers. Furthermore, fishes and particularly larger-bodied species might substantially be restricted by movement barriers to respond to predicted climate and land use changes, while smaller-bodied species are rather restricted by their specific dispersal ability.

• MeSH
• biologické modely MeSH
• druhová specificita MeSH
• ekosystém * MeSH
• klimatické změny * MeSH
• řeky MeSH
• rozšíření zvířat * MeSH
• ryby fyziologie   MeSH
• zvířata MeSH
• Check Tag
• zvířata MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• Geografické názvy
• Evropa MeSH

INTRODUCTION: Recent advances in machine learning provide new possibilities to process and analyse observational patient data to predict patient outcomes. In this paper, we introduce a data processing pipeline for cardiogenic shock (CS) prediction from the MIMIC III database of intensive cardiac care unit patients with acute coronary syndrome. The ability to identify high-risk patients could possibly allow taking pre-emptive measures and thus prevent the development of CS. METHODS: We mainly focus on techniques for the imputation of missing data by generating a pipeline for imputation and comparing the performance of various multivariate imputation algorithms, including k-nearest neighbours, two singular value decomposition (SVD)-based methods, and Multiple Imputation by Chained Equations. After imputation, we select the final subjects and variables from the imputed dataset and showcase the performance of the gradient-boosted framework that uses a tree-based classifier for cardiogenic shock prediction. RESULTS: We achieved good classification performance thanks to data cleaning and imputation (cross-validated mean area under the curve 0.805) without hyperparameter optimization. CONCLUSION: We believe our pre-processing pipeline would prove helpful also for other classification and regression experiments.

• Publikační typ
• časopisecké články MeSH

The development of a soil cover is a dynamic process. Soil cover can be altered within a few decades, which requires updating of the legacy soil maps. Soil erosion is one of the most important processes quickly altering soil cover on agriculture land. Colluvial soils develop in concave parts of the landscape as a consequence of sedimentation of eroded material. Colluvial soils are recognised as important soil units because they are a vast sink of soil organic carbon. Terrain derivatives became an important tool in digital soil mapping and are among the most popular auxiliary data used for quantitative spatial prediction. Prediction success rates are often directly dependent on raster resolution. In our study, we tested how raster resolution (1, 2, 3, 5, 10, 20 and 30 meters) influences spatial prediction of colluvial soils. Terrain derivatives (altitude, slope, plane curvature, topographic position index, LS factor and convergence index) were calculated for the given raster resolutions. Four models were applied (boosted tree, neural network, random forest and Classification/Regression Tree) to spatially predict the soil cover over a 77 ha large study plot. Models training and validation was based on 111 soil profiles surveyed on a regular sampling grid. Moreover, the predicted real extent and shape of the colluvial soil area was examined. In general, no clear trend in the accuracy prediction was found without the given raster resolution range. Higher maximum prediction accuracy for colluvial soil, compared to prediction accuracy of total soil cover of the study plot, can be explained by the choice of terrain derivatives that were best for Colluvial soils differentiation from other soil units. Regarding the character of the predicted Colluvial soils area, maps of 2 to 10 m resolution provided reasonable delineation of the colluvial soil as part of the cover over the study area.

• MeSH
• průzkumy a dotazníky MeSH
• půda chemie   MeSH
• teoretické modely * MeSH
• zeměpis MeSH
• Publikační typ
• časopisecké články MeSH
• Geografické názvy
• Česká republika MeSH