Soil salinization, referring to the excessive accumulation of soluble salts in soils, adversely influences nutrient cycling, biodiversity, soil structure, crop production, soil health, and ecosystem functioning. Accurately assessing soil salinity via electrical conductivity (EC) is key to mitigating its impacts. Thus, developing predictive tools for soil EC at regional and continental scales is essential for sustainable soil management. Here, we apply machine learning models to predict soil EC in the European Union (EU) and United Kingdom (UK) soils using different environmental factors like soil, climate, topography, and satellite data as predictors. The model is trained by ≈40,000 soil EC data points from the 2015 and 2018 Land Use/Cover Area Frame Survey data (LUCAS) surveys, complemented by the EC observations from World Soil Information Services (WoSIS) dataset. To improve the model performance, a forward feature selection technique was used resulting in selection of 17 covariates out of initially 34 predictors. The final selected XGBoost model achieved R2 values of 0.68, 0.6, and 0.63 for the training, internal testing, and independent validation datasets, respectively. For the year 2018, we estimate ≈21.7 Mha of EU + UK land exceeds an EC of 0.6 dS/m (at a 1:5 soil to water ratio, the so-called EC1:5). This estimate should be interpreted as elevated predicted EC1:5, rather than a direct estimate of soils meeting protosalic diagnostic criteria. The output of the predictive model consists of a gridded dataset that illustrates the spatial distribution of EC1:5 throughout the study area for the year 2018, along with an associated uncertainty map with a spatial resolution of 1 km.
Mohammad Aziz Zarif, Amirhossein Hassani, Mehdi H. Afshar et al.· Science of the Total Environ...· 0 citations
Soil hydraulic properties govern the movement and storage of water in soils and are essential inputs for hydrological and land surface models, influencing water‐holding capacity, matter and energy transport, erosion susceptibility and plant water availability. However, direct measurement of these properties is labour‐intensive and thus often limited in spatial coverage. Therefore, pedotransfer functions (PTFs) are widely used to estimate soil hydraulic properties from readily available soil characteristics. We present a spatial dataset of soil hydraulic properties for Europe at 0–20 cm depth, developed using harmonised soil property maps derived from the LUCAS dataset and the improved PTFs (EUPTFv2) proposed by Szabó et al., which are developed on the European Hydropedological Data Inventory. The derived dataset includes water content at saturation, field capacity (at −10 and −33 kPa), wilting point (−1500 kPa), saturated hydraulic conductivity and their associated uncertainty maps. In addition, we derived available water capacity and air capacity (air‐filled porosity) from the predicted properties. The input datasets (LUCAS‐based soil maps) used in this study are derived from harmonised data in terms of measurement methods and spatial consistency. This is expected to improve the reliability of the resulting maps compared with existing products. The generated dataset is freely available and can therefore support a wide range of environmental and modelling applications.
Surya Gupta, C. Alewell, C. Ballabio et al.· Hydrological Processes· 0 citations