Search Results (40)

Soils serve as critical carbon reservoirs, playing an essential role in climate change mitigation and agricultural sustainability. Accurate soil property determination relies on soil spectral reflectance data from Earth observation (EO), but current vegetation models often oversimplify soil conditions. This study introduces a novel approach that combines radiative transfer models (RTMs) with open-access soil spectral libraries to address this challenge. Focusing on conditions of low soil moisture content (SMC), photosynthetic vegetation (PV), and non-photosynthetic vegetation (NPV), the coupled Marmit–Leaf–Canopy (MLC) model is used to simulate early crop growth stages. The MLC model, which integrates MARMIT and PRO4SAIL2, enables the generation of mixed soil–vegetation scenarios. A simulated EO disturbed soil spectral library (DSSL) was created, significantly expanding the EU LUCAS cropland soil spectral library. A 1D convolutional neural network (1D-CNN) was trained on this database to predict Soil Organic Carbon (SOC) content. The results demonstrated relatively high SOC prediction accuracy compared to previous approaches that rely only on RTMs and/or machine learning approaches. Incorporating soil moisture content significantly improved performance over bare soil alone, yielding an R² of 0.86 and RMSE of 4.05 g/kg, compared to R² = 0.71 and RMSE = 6.01 g/kg for bare soil. Adding PV slightly reduced accuracy (R² = 0.71, RMSE = 6.31 g/kg), while the inclusion of NPV alongside moisture led to modest improvement (R² = 0.74, RMSE = 5.84 g/kg). The most comprehensive model, incorporating bare soil, SMC, PV, and NPV, achieved a balanced performance (R² = 0.76, RMSE = 5.49 g/kg), highlighting the importance of accounting for all surface components in SOC estimation. While further validation with additional scenarios and SOC prediction methods is needed, these findings demonstrate, for the first time, using radiative-transfer simulations of mixed vegetation-soil-water environments, that an EO-DSSL approach enhances machine learning-based SOC modeling from EO data, improving SOC mapping accuracy. This innovative framework could significantly improve global-scale SOC predictions, supporting the design of next-generation EO products for more accurate carbon monitoring. Full article

Accurate prediction of soil lead (Pb) content in small sample scenarios is often limited by data scarcity and variability in soil properties, with traditional spectral modeling methods yielding suboptimal precision. To address this, we propose a transfer learning-based framework integrated with SHAP analysis for predicting soil Pb content in the Gejiu mining area, Yunnan. Using pH data from the European LUCAS soil database as the source domain, spectral features were extracted via a 1D-ResNet model and transferred to the target domain (130 soil samples from Gejiu) for Pb prediction. SHAP analysis was applied to clarify the role of spectral characteristics in cross-component transfer learning, uncovering shared and adaptive features between pH and Pb predictions. The transfer learning model (ResNet-pH-Pb) significantly outperformed direct modeling methods (PLS-Pb, SVM-Pb, and ResNet-Pb), with an R² of 0.77, demonstrating superior accuracy. SHAP analysis showed that the model retained key pH-related wavelengths (550–750 nm and 1600–1700 nm) while optimizing Pb-related wavelengths (e.g., 919 nm and 959 nm). This study offers a novel approach for soil heavy metal prediction under small sample constraints and provides a theoretical basis for understanding spectral prediction mechanisms through interpretability analysis. Full article

Visible and near-infrared (Vis–NIR) spectroscopy enables the rapid prediction of soil properties but faces three limitations with conventional machine learning: information loss and overfitting from high-dimensional spectral features; inadequate modeling of nonlinear soil–spectra relationships; and failure to integrate multi-scale spatial features. To address these challenges, we propose ReSE-AP Net, a multi-scale attention residual network with spatial pyramid pooling. Built on convolutional residual blocks, the model incorporates a squeeze-and-excitation channel attention mechanism to recalibrate feature weights and an atrous spatial pyramid pooling (ASPP) module to extract multi-resolution spectral features. This architecture synergistically represents weak absorption peaks (400–1000 nm) and broad spectral bands (1000–2500 nm), overcoming single-scale modeling limitations. Validation on the LUCAS2009 dataset demonstrated that ReSE-AP Net outperformed conventional machine learning by improving the R² by 2.8–36.5% and reducing the RMSE by 14.2–69.2%. Compared with existing deep learning methods, it increased the R² by 0.4–25.5% for clay, silt, sand, organic carbon, calcium carbonate, and phosphorus predictions, and decreased the RMSE by 0.7–39.0%. Our contributions include statistical analysis of LUCAS2009 spectra, identification of conventional method limitations, development of the ReSE-AP Net model, ablation studies, and comprehensive comparisons with alternative approaches. Full article

Antibiotic resistance (AR) is recognized by the World Health Organization as a major threat to human health, and recent studies highlight the role of microplastics (MPs) in its spread. MPs in the environment may act as vectors for antibiotic-resistant bacteria (ARB) and antibiotic resistance genes (ARGs). Bacterial communities on the plastisphere, the surface of MPs, are influenced by plastic properties, allowing ARB to colonize and form biofilms. These biofilms facilitate the transfer of ARGs within microbial communities. This study analyzed data from the LUCAS soil dataset (885 soil samples across EU countries) using the Emu tool to characterize microbial communities at the genus/species level. Functional annotation via PICRUSt2, supported by a custom tool for Emu output formatting, revealed significant correlations between the genera Solirubrobacter, Bradyrhizobium, Nocardioides, and Bacillus with pathways linked to microplastic degradation and antibiotic resistance. These genera were consistently present in various soil types (woodland, grassland, and cropland), suggesting their potential as bioindicators of soil health in relation to MP pollution. The findings underscore MPs as hotspots for ARB and ARGs, offering new insights into the identification of bioindicators for monitoring soil health and the ecological impacts related to MP contamination. Full article

Gravel coverage on slopes influences overland flow and soil erosion. However, the effect of different gravel sizes on the soil erosion process remains underexplored. In this study, a runoff scour test was performed to examine the effects of gravel coverage on the hydrodynamic characteristics of slope runoff and sediment transport capacity (T_c). The slope gradient varied from 18% to 84%, the unit flow discharge ranged from 0.27 × 10⁻³ to 1.11 × 10⁻³ m² s⁻¹, and gravel coverage was adjusted from 0% to 90%. The results reveal that water depth, shear stress, and stream power increased with gravel coverage. However, once coverage exceeded 20%, flow velocity and unit stream power decreased and stabilized. As gravel coverage increased, the hydraulic regimes transitioned from laminar to turbulent flow and shifted from supercritical to subcritical. Consequently, T_c first increased and then decreased with the increase in gravel coverage, reaching a peak at 20% coverage (1.66 kg m⁻¹ s⁻¹). Moreover, the degree of coverage indirectly influenced T_c through grain shear stress. The new equations, based on the Box–Lucas function, incorporated slope, grain shear stress, and flow velocity, thereby effectively simulating T_c for runoff on gravel-covered slopes (R² = 0.94, NSE = 0.94). These findings provide a basis for modeling soil erosion on gravel-covered slopes. Full article

Accurate prediction of soil properties is essential for sustainable land management and precision agriculture. This study presents an LSTM-CNN-Attention model that integrates temporal and spatial feature extraction with attention mechanisms to improve predictive accuracy. Utilizing the LUCAS soil dataset, the model analyzes spectral data to estimate key soil properties, including organic carbon (OC), nitrogen (N), calcium carbonate (CaCO₃), and pH (in H₂O). The Long Short-Term Memory (LSTM) component captures temporal dependencies, the Convolutional Neural Network (CNN) extracts spatial features, and the attention mechanism highlights critical information within the data. Experimental results show that the proposed model achieves excellent prediction performance, with coefficient of determination (R²) values of 0.949 (OC), 0.916 (N), 0.943 (CaCO₃), and 0.926 (pH), along with corresponding ratio of percent deviation (RPD) values of 3.940, 3.737, 5.377, and 3.352. Both R² and RPD values exceed those of traditional machine learning models, such as partial least squares regression (PLSR), support vector machine regression (SVR), and random forest (RF), as well as deep learning models like CNN-LSTM and Gated Recurrent Unit (GRU). Additionally, the proposed model outperforms S-AlexNet in effectively capturing temporal and spatial patterns. These findings emphasize the potential of the proposed model to significantly enhance the accuracy and reliability of soil property predictions by capturing both temporal and spatial patterns effectively. Full article

The scientific evaluation of land potential for different uses is essential for sustainable land development. Our study attempts to quantify this potential for agricultural purposes at a national scale, using GIS techniques, high-resolution spatial data, and recent climate data. The land evaluation methodology we applied in our study was developed in the 1980s by soil scientists from the National Institute of Research and Development for Pedology, Agrochemistry and Environmental Protection (ICPA) and it is still the official approach for the assessment of land suitability for crops in Romania. In our study, the application of the methodology is based on high-resolution spatial data including the 25 × 25 m resolution EU-DEM, the CHESLA climate database from which mean annual temperatures and precipitations were extracted for the 1990–2019 period, the digital soil map of Romania, the European LUCAS soil database. Firstly, we compared the evolution of mean annual temperatures and precipitations for 1961–1990 and 1990–2019 periods and found that there is a significant warming trend (an overall increase of 1.27 °C for the entire country, ranging from 0.9 °C to 1.6 °C) among the major landform units and a slight precipitation increase throughout the country (68.8 mm yr⁻¹ for the whole country, ranging from 9.3 to 118.8 mm yr⁻¹). Then, we applied the land evaluation methodology for the recent period (1990–2019), starting with the digital mapping of 15 land suitability factors, which were further aggregated to achieve the land suitability index and classes for the main agricultural crops of Romania (winter wheat, maize, sunflower, potato, and vine for wine). The results show that the most suitable landform units for wheat, maize, and sunflower are the plain areas (Romanian Plain, Western Plain) with LSI average values over 60. For potato, the suitable areas (LSI over 50–60) are less extended, being found especially in the intra-mountainous depressions and cooler plateau areas, while vines find very suitable conditions (LSI over 70) at the contact of the Romanian Plain and the Subcarpathians. To assess the model performance, we determined the shares of land suitability classes within the areas occupied by the specific crops. A second validation was carried out by correlating the total crop production at the county level with the cumulated LSI values. We found that, apart from potatoes, the model performs well for the analyzed crops. However, a methodological revision is necessary to accommodate temperature and precipitation values, which did not manifest in the reference climate period (1961–1990), but which are now part of the current climate of Romania. Full article

The aim of this study was to narrow the research gap of ambiguity in which machine learning algorithms should be selected for evaluation in digital soil organic carbon (SOC) mapping. This was performed by providing a comprehensive assessment of prediction accuracy for 15 frequently used machine learning algorithms in digital SOC mapping based on studies indexed in the Web of Science Core Collection (WoSCC), providing a basis for algorithm selection in future studies. Two study areas, including mainland France and the Czech Republic, were used in the study based on 2514 and 400 soil samples from the LUCAS 2018 dataset. Random Forest was first ranked for France (mainland) and then ranked for the Czech Republic regarding prediction accuracy; the coefficients of determination were 0.411 and 0.249, respectively, which was in accordance with its dominant appearance in previous studies indexed in the WoSCC. Additionally, the K-Nearest Neighbors and Gradient Boosting Machine regression algorithms indicated, relative to their frequency in studies indexed in the WoSCC, that they are underrated and should be more frequently considered in future digital SOC studies. Future studies should consider study areas not strictly related to human-made administrative borders, as well as more interpretable machine learning and ensemble machine learning approaches. Full article

Soil, a non-renewable resource, requires continuous monitoring to prevent degradation and support sustainable agriculture. Visible-near-infrared (Vis-NIR) spectroscopy is a rapid and cost-effective method for predicting soil properties. While traditional machine learning methods are commonly used for modeling Vis-NIR spectral data, large datasets may benefit more from advanced deep learning techniques. In this study, based on the large soil spectral library LUCAS, we aimed to enhance regression model performance in soil property estimation by combining Transformer and convolutional neural network (CNN) techniques to predict 11 soil properties (clay, silt, pH in CaCl₂, pH in H₂O, CEC, OC, CaCO₃, N, P, and K). The Transformer-CNN model accurately predicted most soil properties, outperforming other methods (partial least squares regression (PLSR), random forest regression (RFR), support vector machine regression (SVR), Long Short-Term Memory (LSTM), ResNet18) with a 10–24 percentage point improvement in the coefficient of determination (R²). The Transformer-CNN model excelled in predicting pH in CaCl₂, pH in H₂O, OC, CaCO₃, and N (R² = 0.94–0.96, RPD > 3) and performed well for clay, sand, CEC, P, and K (R² = 0.77–0.85, 2 < RPD < 3). This study demonstrates the potential of Transformer-CNN in enhancing soil property prediction, although future work should aim to optimize computational efficiency and explore a wider range of applications to ensure its utility in different agricultural settings. Full article

Soil visible and near–infrared reflectance spectroscopy is an effective tool for the rapid estimation of soil organic carbon (SOC). The development of spectroscopic technology has increased the application of spectral libraries for SOC research. However, the direct application of spectral libraries for SOC prediction remains challenging due to the high variability in soil types and soil–forming factors. This study aims to address this challenge by improving SOC prediction accuracy through spectral classification. We utilized the European Land Use and Cover Area frame Survey (LUCAS) large–scale spectral library and employed a geographically weighted principal component analysis (GWPCA) combined with a fuzzy c–means (FCM) clustering algorithm to classify the spectra. Subsequently, we used partial least squares regression (PLSR) and the Cubist model for SOC prediction. Additionally, we classified the soil data by land cover types and compared the classification prediction results with those obtained from spectral classification. The results showed that (1) the GWPCA–FCM–Cubist model yielded the best predictions, with an average accuracy of R² = 0.83 and RPIQ = 2.95, representing improvements of 10.33% and 18.00% in R² and RPIQ, respectively, compared to unclassified full sample modeling. (2) The accuracy of spectral classification modeling based on GWPCA–FCM was significantly superior to that of land cover type classification modeling. Specifically, there was a 7.64% and 14.22% improvement in R² and RPIQ, respectively, under PLSR, and a 13.36% and 29.10% improvement in R² and RPIQ, respectively, under Cubist. (3) Overall, the prediction accuracy of Cubist models was better than that of PLSR models. These findings indicate that the application of GWPCA and FCM clustering in conjunction with the Cubist modeling technique can significantly enhance the prediction accuracy of SOC from large–scale spectral libraries. Full article

Agroforestry has a long history of evolution in Europe and has been especially selected under the unfavorable socioeconomic and environmental conditions of the Mediterranean region. The recent changes in social-ecological conditions have increased the interest in the contribution of agroforestry to the mitigation of forthcoming challenges. Thus, the present study aimed to analyze the socioeconomic and ecological suitability of agricultural lands for preserving, restoring, and establishing agroforestry practices in Europe. We classified different agroforestry systems based on the LUCAS database, finding that most agroforestry in Europe is in areas associated with older human populations of varying densities and employment levels at lower altitudes, gentler slopes, moderate annual mean temperature and precipitation, and in medium textured soils with limited organic carbon content. Focusing on the prevalent agroforestry system of silvopasture, the majority of which is found in three Mediterranean ecoregions of mainly sclerophyllous forests, the most important factors for the occurrence of this system were subsoil available water content (Aegean), land cover (Adriatic), and topsoil available water content (Iberian). The suitable area for silvopasture according to MaxEnt was 32%, 30%, and 22% of the Aegean, Adriatic, and Iberian ecoregion’s area, respectively. Such mapping of agroforestry suitability can help policymakers to undertake adaptive management for the implementation of agroforestry-based solutions to address ecosystem restoration, food insecurity, and rapid environmental changes and threats. Full article

Visible near-infrared spectroscopy (VNIR) is extensively researched for obtaining soil property information due to its rapid, cost-effective, and environmentally friendly advantages. Despite its widespread application and significant achievements in soil property analysis, current soil prediction models continue to suffer from low accuracy. To address this issue, we propose a convolutional neural network model that can achieve high-precision soil property prediction by creating 2D multi-channel inputs and applying a multi-scale spatial attention mechanism. Initially, we explored two-dimensional multi-channel inputs for seven soil properties in the public LUCAS spectral dataset using the Gramian Angular Field (GAF) method and various preprocessing techniques. Subsequently, we developed a convolutional neural network model with a multi-scale spatial attention mechanism to improve the network’s extraction of relevant spatial contextual information. Our proposed model showed superior performance in a statistical comparison with current state-of-the-art techniques. The RMSE (R²) values for various soil properties were as follows: organic carbon content (OC) of 19.083 (0.955), calcium carbonate content (CaCO₃) of 24.901 (0.961), nitrogen content (N) of 0.969 (0.933), cation exchange capacity (CEC) of 6.52 (0.803), pH in H₂O of 0.366 (0.927), clay content of 4.845 (0.86), and sand content of 12.069 (0.789). Our proposed model can effectively extract features from visible near-infrared spectroscopy data, contributing to the precise detection of soil properties. Full article

This paper quantifies the annual dynamics of the shortwave radiation reflected from bare arable land as a result of smoothing previously plowed land located in three different agricultural subregions of the European Union and associated countries. This estimate takes into account the annual variation of the bare arable land area, obtained from Sentinel 2 satellite imagery; the spatial variability of soil units within croplands, obtained from digital soil and land-cover maps; and the laboratory spectral reflectance characteristics of these units, obtained from soil samples stored in the LUCAS soil database. The properties of the soil units, which cover an area of at least 4% of each subregion, were characterized. The highest amounts of shortwave radiation reflected under clear-sky conditions from air-dried, bare arable land surfaces—approximately 850 PJ day⁻¹ and 1.10 EJ day⁻¹ for land shaped by a plow (Pd) and smoothing harrow (Hs), respectively—were found in the summer around 8 August in the western subregion. However, the lowest radiation occurred in the spring on 10 April at 340 PJ day⁻¹ for Pd and 430 PJ day⁻¹ for Hs in the central subregion. The largest and the smallest amounts of this radiation throughout the year—only as a result of smoothing, by Hs, land that was previously treated by Pd—was estimated at 42 EJ for the western and southern subregions and 19 EJ for the central subregion, respectively. Full article

High levels of chromium (Cr) in soil pose a significant threat to both humans and the environment. Laboratory-based chemical analysis methods for Cr are time consuming and expensive; thus, there is an urgent need for a more efficient method for detecting Cr in soil. In this study, a deep neural network (DNN) approach was applied to the Land Use and Cover Area frame Survey (LUCAS) dataset to develop a hyperspectral soil Cr content prediction model with good generalizability and accuracy. The optimal DNN model was constructed by optimizing the spectral preprocessing methods and DNN hyperparameters, which achieved good predictive performance for Cr detection, with a correlation coefficient value of 0.79 on the testing set. Four important hyperspectral bands with strong Cr sensitivity (400–439, 1364–1422, 1862–1934, and 2158–2499 nm) were identified by permutation importance and local interpretable model-agnostic explanations. Soil iron oxide and clay mineral content were found to be important factors influencing soil Cr content. The findings of this study provide a feasible method for rapidly determining soil Cr content from hyperspectral data, which can be further refined and applied to large-scale Cr detection in the future. Full article

Ecosystems are frequently disturbed by fires that have an important impact on the soil environment and the composition of soil organisms. In order to provide a baseline for the current research and identify trends on the effects of wildland fire on soil environment and biological changes, the available literature was identified from the Web of Science database, covering the period from 1998/1998/1999 (the year of the earliest publication in this field) to 2023. A bibliometric analysis was performed and the data were visually displayed for the number of publications, countries, authors, research institutions, and keywords representing research hotspots. Specifically, the effects of wildland fire on the soil environment, on soil microorganisms and on soil fauna were analyzed. The results show that the annual number of publications describing effects of wildland fire on the soil environment and on soil microorganisms are increasing over time, while those describing effects on soil fauna are fewer and their number remains constant. The largest number of papers originate from the United States, with the United States Department of Agriculture as the research institution with the largest output. The three authors with the largest number of publications are Stefan H. Doerr, Manuel Esteban Lucas-Borja and Jan Jacob Keizer. The research hotspots, as identified by keywords, are highly concentrated on wildfire, fire, organic matter, and biodiversity, amongst others. This study comprehensively analyzes the current situation of the research on the effects of wildland fire on changes in the soil environment and organisms, and provides reference for relevant scientific researchers in this trend and future research hotspots. Full article