Soil salinization is one of the main threats to soils worldwide, which has serious impacts on soil functions. Our objective was to map and assess salt-affectedness on arable land (0.85 km²) in Hungary, with high spatial resolution, using a combination of ensemble machine learning and multivariate geostatistics on three salt-affected soil indicators (i.e., alkalinity, electrical conductivity, and sodium adsorption ratio (n = 85 soil samples)). Ensemble modelling with five base learners (i.e., random forest, extreme gradient boosting, support vector machine, neural network, and generalized linear model) was carried out and the results showed that ensemble modelling outperformed the base learners for alkalinity and sodium adsorption ratio with R² values of 0.43 and 0.96, respectively, while only the random forest prediction was acceptable for electrical conductivity. Multivariate geostatistics was conducted on the stochastic residuals derived from machine learning modelling, as we could reasonably assume that there is spatial interdependence between the selected salt-affected soil indicators. We used 10-fold cross-validation to check the performance of the spatial predictions and uncertainty quantifications, which provided acceptable results for each selected salt-affected soil indicator (for pH value, electrical conductivity, and sodium adsorption ratio, the root mean square error values were 0.11, 0.86, and 0.22, respectively). Our results showed that the methodology applied in this study is efficient in mapping and assessing salt-affectedness on arable lands with high spatial resolution. A probability map for sodium adsorption ratio represents sodic soils exceeding a threshold value of 13, where they are more likely to have soil structure deterioration and water infiltration problems. This map can help the land user to select the appropriate agrotechnical operation for improving soil quality and yield.

The diminishing number, extent and degradation of soda lakes were reported from the lowland area of the Carpathian Basin in the past two decades due to anthropogenic impact and climate change. This study provides a detailed spatio-temporal assessment of a degrading alkaline sodic lake ecosystem (13.5 ha) in Southeast Hungary. It discusses the results of spatially detailed topsoil and vegetation surveys from 2009 and 2018 to understand the changes among the current natural and anthropogenic conditions to support a future possible ecological water management. Habitat mapping and laboratory measurement of EC2.5, soda and calcium carbonate content from 199 topsoil samples provided the basis for the assessment. In 2009 the degradation of the naturalness was observed according to the vegetation survey, and the topsoil parameters reflected steppification, leaching and desalinization. Between 2009 and 2018 the loss in extent of Puccinellia swards and the spread of salt meadow species along the channel continued due to the changing salt content. According to the 2018 snapshot of the topsoil, higher salt (from 0.7 to 1.3 mS/cm) and soda content (from 0.08 to 0.12%), furthermore decreasing CaCO₃ content (from 25.89 to 20.08%) were characteristic, meaning that there was a changing water and salt regime in the lakebed. The past decade was partly favourable in the point that humid years could rehabilitate the natural conditions in certain parts of the lakebed, but they did not prove to be enough to sustain this alkaline sodic lake.

The process of groundwater evapotranspiration and its subsequent recharge are fundamental aspects of the Earth’s natural water cycle and have significant implications for the preservation and functionality of various forested ecosystems. This study presents a case analysis examining the recent fluctuations in groundwater levels and their replenishment in two wells situated at a designated forested experimental area and a control site. The magnitude and temporal fluctuations of groundwater recharge were examined through the utilisation of a novel adaptation of the traditional White method, which was specifically tailored to the local context. We also tested the sensitivity of the White method as an indicator of the system’s behaviour because the signal has changed in relation to the access of the forests to groundwater under the conditions of regionally declining groundwater resources and a warming climate. The novelty of this approach is found in the examination of the temporal fluctuations in groundwater recharge, which are influenced by both a decrease in groundwater levels caused by forest evaporation in response to climate change and a regional reduction in groundwater supplies. As a result, the ongoing decrease in groundwater levels may have significant adverse effects on local forests.

Salt meadows, protected within National Parks, cannot be directly surveyed, yet understanding their soil condition is crucial. Our study indirectly estimates soil parameters (Total Salt Content (TSC), Na, and pH) related to salinization/sodification/alkalinization using spectral indices and UAV survey-derived elevation model, focusing on continental lowland salt meadows. A vegetation map was created using 16 spectral indices and a Digital Elevation Model calculated from RGB orthophotos using photogrammetry. Field observations helped define habitat types based on the General National Habitat Classification System (Hungary), and quadrats with complete coverage of specific plant species were identified. Machine learning was employed on 84 training quadrats to develop a prediction algorithm for vegetation patterns. Five saline habitat types, representing variations in soil properties and topography, were identified. Spectral and topomorphometric indices derived from UAV were key to the spatial prediction of soil properties, employing random forest and co-kriging methods. TSC, Na, and pH data served as indicators of salt-affected soils (SAS), and thematic maps were generated for each indicator (57 samples). Overlapping with the vegetation map, the probability range of estimated SAS indicator values was determined. Consequently, a model-based estimation of soil pH, TSC, and Na conditions is provided for habitat types without disturbing protected areas.

This preliminary study reveals the relations between the forest growth (annual dendromass increment; ADMinc - as dependent variable) and some important soil factors, which have effect on plant growth, such as: groundwater level (GWL), groundwater composition (GWC), plant available water capacity (PAWC), depth of humus layer, texture (hyi) and pH of the soil, moreover the maximum concentration (MAX) of salt and CaCCb and the depth of its MAX in the soil profile. 17 plantations (Poplar, Common oak and Black locust) are included in the analysis investigated all over the Great Hungarian Plain. Correlation profile of the above parameters was created explaining that two abiotic parameters limit plant growth: if GWL is deeper than 5 m and if HCO3 concentration in groundwater is high (above 15 meq/L). Within the tested range (0.17 - 2.23 mS/cm for electrical conductivity (EC) and 0.5 /sand/ - 4.21 /clay loam/ for hyi), the higher magnitude of EC results in higher ADMinc and the higher hyi (higher proportion of fine soil particles) leads to higher ADMinc The positive relationship of ADMinc with EC suggests good nutrient supply of the soil, while the higher proportion of fine particles refers to better water management properties. Thickness of humus layer is an important soil factor: compared to shallow humus layer, deep one increases ADMinc exponentially. In case of Black locust, PAWC is the substantial factor for growing, unlike Poplar, whose growth depends on groundwater uptake (GWU). This phenomenon originates from the differences between the individual needs of the tree species and differences in root morphology. Merely 4 sampling plots were equipped with meteorological stations, thus the number of climatic parameter data were not enough for statistical analysis. So data for all 17 plots were collected from literature and a general, regionally calculated data were applied (mean rainfall in the vegetation period and aridity index). There was no significant correlation between climatic parameters and ADMinc Further studies and more field investigations are needed in order to clarify the results.