This study focuses on the reclassification of a soil texture system following a hybrid approach in which the conventional particle-size distribution (PSD) models are coupled with a random forest (RF) algorithm for achieving more generally applicable and precise outputs. The existing parametric PSD models that could be used for this purpose have various limitations; different models frequently show unequal degrees of precision in different soils or under different environments. The authors present in this article a novel ensemble modeling approach in which the existing PSD models are used as ensemble members. An improvement in precision was proved by better statistical indicators for the results obtained, and the article documents that the ensemble model worked better than any of its constituents (different existing parametric PSD models). This study is verified by using a soil dataset from Slovakia, which was originally labeled by a national texture classification system, which was then transformed to the USDA soil classification system. However, the methodology proposed could be used more generally, and the information provided is also applicable when dealing with the soil texture classification systems used in other countries.KEY WORDS: soil texture, particle-size distribution, data-driven modeling, ensemble model, random forests ACADEMIC EDITOR: carlos Alberto Martinez-huitle, editor is chief PEER REVIEW: three peer reviewers contributed to the peer review report. reviewers' reports totaled 993 words, excluding any confidential comments to the academic editor.

Rye Island is a unique natural formation, which lies between the main flow of the Danube River and the Little Danube River and is the largest river island in Europe. It is located in the southwest of Slovakia and with its mild to slightly warm climate is one of the most fertile agricultural areas in Slovakia. The whole Rye Island is also our greatest reservoir of quality waters used for drinking purposes, where groundwaters of Rye Island are permanently supplied with water from the Danube River. It means that as water levels in the Danube River were unstable before the construction of the Gabčíkovo Water Project, also the groundwater level faced large fluctuations. Changes occurred after putting the Gabčíkovo Water Project into service, with a decrease in groundwater levels. Thereby, the conditions for agriculture have improved and drying of surrounding protected floodplain forests has stopped. Through the present contribution we decided to analyse the impact of Gabčíkovo on soil water regime in the area of Rye Island, and evaluate the course of groundwater level, precipitation and soil water storage over time. For the representative area we chose a forest ecosystem of Král’ovská Lúka and evaluated the period 1999 to 2009.

This paper is focused on phytocoenological characteristics and production analysis of herbaceous layer biomass of the softwood floodplain forests (Salici-Populetum (R. Tx. 1931) Meijer Drees 1936 association) and their phytocoenological characteristics. The sampling site was located in the young stands, which were formed after the Gabčíkovo Waterwork construction in 1992. Redirection of the major ratio of flow into the supply channel has caused essential decrease of water level in the old Danube riverbed. As a result of this, new bare sites have appeared having character of pioneer habitat. In the process of primary succession, new softwood floodplain forests have formed here within a few years. These stands are the subject of the study presented in this paper. We estimated herb layer biomass using indirect sampling modified for non-repeated field measurements (Kubíček, Brechtl, 1970). Total biomass of herbaceous layer was estimated to be 5577 kg ha

No abstract

The