Search Results (110)

Water infiltration into soil is a key process in regulating the hydrological cycle and sustaining ecosystem services in high-Andean environments. However, limited information is available regarding its dynamics in these ecosystems. This study evaluated the influence of three types of vegetation cover and soil properties on water infiltration in a high-Andean environment. A double-ring infiltrometer, the Water Drop Penetration Time (WDPT, s) method, and laboratory physicochemical characterization were employed. Soils under forest cover exhibited significantly higher quasi-steady infiltration rates (i_s, 0.248 ± 0.028 cm·min⁻¹) compared to grazing areas (0.051 ± 0.016 cm·min⁻¹) and agricultural lands (0.032 ± 0.013 cm·min⁻¹). Soil organic matter content was positively correlated with i_s. The modified Kostiakov infiltration model provided the best overall fit, while the Horton model better described infiltration rates approaching i_s. Sand and clay fractions, along with K⁺, Ca²⁺, and Mg²⁺, were particularly significant during the soil’s wet stages. In drier stages, increased Na⁺ concentrations and decreased silt content were associated with higher water repellency. Based on WDPT, agricultural soils exhibited persistent hydrophilic behavior even after drying (median [IQR] from 0.61 [0.38] s to 1.24 [0.46] s), whereas forest (from 2.84 [3.73] s to 3.53 [24.17] s) and grazing soils (from 4.37 [1.95] s to 19.83 [109.33] s) transitioned to weakly or moderately hydrophobic patterns. These findings demonstrate that native Andean forest soils exhibit a higher infiltration capacity than soils under anthropogenic management (agriculture and grazing), highlighting the need to conserve and restore native vegetation cover to strengthen water resilience and mitigate the impacts of land-use change. Full article

Land desertification represents a significant and sensitive global ecological issue. In the Inner Mongolia region of China, soil desertification and salinization are widespread, resulting from the combined effects of extreme drought conditions and human activities. Using Gaofen 5B AHSI imagery as our data source, we collected spectral data for seven distinct land cover types: lush vegetation, yellow sand, white sand, saline soil, saline shell, saline soil with saline vegetation, and sandy soil. We applied Particle Swarm Optimization (PSO) to fine-tune the Wavelet Packet (WP) decomposition levels, thresholds, and wavelet basis function, ensuring optimal spectral decomposition and reconstruction. Subsequently, PSO was deployed to optimize key hyperparameters of the Random Forest algorithm and compare its performance with the ResNet-Transformer model. Our results indicate that PSO effectively automates the search for optimal WP decomposition parameters, preserving essential spectral information while efficiently reducing high-frequency spectral noise. The Genetic Algorithm (GA) was also found to be effective in extracting feature bands relevant to land desertification, which enhances the classification accuracy of the model. Among all the models, integrating wavelet packet denoising, genetic algorithm feature selection, the first-order differential (FD), and the hybrid architecture of the ResNet-Transformer, the WP-GA-FD-ResNet-Transformer model achieved the highest accuracy in extracting soil sandification and salinization, with Kappa coefficients and validation set accuracies of 0.9746 and 97.82%, respectively. This study contributes to the field by advancing hyperspectral desertification monitoring techniques and suggests that the approach could be valuable for broader ecological conservation and land management efforts. Full article

Inner Mongolia, a typical arid and semi-arid region in northern China, has undergone significant ecological transformation over the past two decades through climate shifts and large-scale ecological restoration projects. However, the relative contributions of climate and anthropogenic drivers to these ecological changes have not been sufficiently quantified. This study presents a comprehensive quantitative evaluation of the relative contributions of climate change, land conversion, and ecological management to changes in four critical ecosystem services—carbon sequestration, hydrological regulation, soil and water conservation, and windbreak and sand fixation—between 2001 and 2020. Using the residual trend method—a technique to separate climate-driven from human-induced effects—we further decomposed human influence into land conversion and management components. The results show that climate change was the primary driver, enhancing carbon sequestration and hydrological regulation but negatively impacting erosion control, with contributions often over 90%. In contrast, human activities had more spatially variable effects; while land conversion improved several services, it also heightened the vulnerability of sand fixation functions. The analysis further revealed ecosystem-type-specific responses, where grasslands and deserts responded better to management measures and forests and croplands showed greater improvements from land conversion. These findings offer crucial insights into the differentiated mechanisms and outcomes of ecological interventions, providing a scientific basis for optimizing restoration strategies and achieving sustainable ecosystem governance in climate-sensitive regions. Full article

Soil texture, defined by the proportions of sand, silt, and clay particles in the soil, is one of the most essential physical properties of soil. High-resolution soil texture data can provide critical parameter support for soil hydrological modeling, agricultural production management, and ecosystem assessment. In digital soil mapping, previous studies often predicted the sand, silt, and clay contents in soil and then indirectly calculated soil texture. Currently, approaches that directly map soil texture by classification modeling are gaining increasing attention due to the decreased error from data conversion, but few studies have systematically compared these two methods yet. In this study, we comprehensively assessed the performance of direct and indirect predicting soil texture using four machine learning algorithms (e.g., extreme gradient boosting, random forest, gradient boosting decision tree, and extremely randomized tree) with 190 covariates from the Digital Elevation Model, Sentinel-1/2 satellite images, and classification maps and generated a 10 m resolution soil texture map based on 405 topsoil (0–20 cm) sample data collected in Suichuan County, China. The results showed that compared with indirect predictions, direct predictions improved overall accuracy (OA) by 20.57–44.19% and the Kappa coefficient (Kappa) by 0.220–0.402. Among the models used, the XGB model achieved the highest accuracy (OA: 0.948; Kappa: 0.931) and the lowest uncertainty (confusion index: 0.052). The direct prediction map (nine classes recorded) exhibited more detailed and diverse spatial distribution patterns than the indirect prediction map (six classes recorded), aligning better with the actual environment. Based on accuracy validation and spatial distribution, the performance of the XGB model was best during direct prediction. The Shapley additive explanation from the XGB model revealed that the normalized height and stream power indices were the most significant factors driving the soil texture in the study area. Our results provide a reference for future studies on soil texture mapping using machine learning models. Full article

Boreal forests have historically been regarded as some of the largest terrestrial carbon (C) sinks. However, increased soil organic matter (SOM) decomposition due to forest harvesting and post-harvest silviculture (e.g., site preparation, planting, and managing for competing vegetation) may exacerbate the effects of climate warming and shift boreal forests from being C sinks to C sources. We used an established stand-scale, fully replicated, experimental study to identify how two levels of forest management (harvesting = Harvest Only, and harvesting with post-harvest silviculture = Harvest Plus) influence SOC dynamics at three boreal forest sites varying in soil texture. Each site was surveyed for forest floor (litter and F/H horizons) and mineral soils pre-harvest (0) and 5, 14, and 20 years post-harvest. We predicted that sites harvested and left to revegetate naturally would have the lowest SOC stocks after 20 years, as sites that were planted and managed for competing vegetation would recover faster and contribute to a larger nutrient pool, and that the sand-dominated site would have the largest SOC losses following harvest due to the inherently lower ability of sand soils to chemically and/or physically protect SOC from decomposition following harvest. Over a 20-year period, both forest management treatments generally resulted in reduced total (litter, F/H, and mineral horizon) SOC stocks compared with the control: the Harvest Only treatment reduced overall SOC stocks by 15% at the silt-dominated site and 31% at the clay-dominated site but increased overall SOC stocks by 4% at the sand-dominated site, whereas the Harvest Plus treatment reduced overall SOC stocks by 32% at the sand- and silt-dominated sites and 5% at the clay-dominated site. This suggests that harvesting and leaving plots to revegetate naturally on sand-dominated sites and harvesting followed by post-harvest silviculture on clay-dominated sites may minimize total SOC losses at similar sites, though a full replicated field experiment is needed to test this hypothesis. Most treatment effects in this study were observed only in the second decade post-harvest (14 and 20 years post-harvest), highlighting the importance of long-term field experiments on the effects of forest harvesting and post-harvest silviculture. This research improves our understanding of the relationship between C dynamics, forest management, and soil texture, which is integral for developing sustainable management strategies that optimize C sequestration and contribute to the resilience of boreal forest ecosystems in the face of climate change. Full article

Agricultural systems exhibit a large degree of within-field yield variability. We require a better understanding of the drivers of this variability in order to optimally manage croplands. We investigated drivers of sub-field spatial variability in yield for three crops (hard red winter wheat, Triticum aestivum L. variety Langin; corn, Zea mays L.; and proso millet, Panicum milaceum L.) usings a multi-year dataset from a dryland research farm in northeastern Colorado, USA. The dataset spanned 18 2.6–4.3 ha management units, over 4 years, and included high-resolution topographic data, densely sampled soil properties, and on-site weather data. We modeled yield for each crop separately using random forest regression and evaluated model performance using spatially blocked cross-validation. The topographic position index (TPI) and increasing percent sand had a strong negative effect on yield, while the nitrogen application rate (N) and total soil carbon had strong positive effects on yield in both the wheat and millet models. Remarkably, TPI had almost as large of an effect size as N, and outperformed other more commonly used topographic predictors of yield such as the topographic wetness index (TWI), elevation, and slope. Despite the size and quality of our dataset, cross-validation results revealed that our models account for approximately one-quarter of the total yield variance, highlighting the need for continued research into drivers of spatial variability within fields. Full article

Protective forests play a crucial role in ecosystems, particularly in arid and semi-arid regions, where they provide irreplaceable ecological functions such as windbreaks, sand fixation, soil and water conservation, and climate regulation. This study selects Aral City in Xinjiang as the research area and proposes a method that integrates high-resolution remote sensing data (GF-2) with a Spatiotemporal Attention Neural Network (STANet) model to improve the accuracy of protective forest change detection. The study utilizes GF-2 remote sensing imagery and employs a spatiotemporal attention mechanism to incorporate spatial and temporal information, overcoming the limitations of traditional methods in processing long-term time-series remote sensing data. The results demonstrate that the combination of GF-2 imagery and the STANet model effectively detects protective forest changes in Aral City, achieving an F1-score of 83.64% and an accuracy of 78.52%, indicating significant detection capability. Spatial analysis based on the change detection results reveals notable changes in the protective forest area within the study region, with a decline in vegetation coverage in certain areas. This study suggests that the STANet method has strong application potential in protective forest change detection in arid regions, providing precise spatiotemporal change information for protective forest restoration and management. The findings offer a scientific basis for ecological restoration and sustainable development in Aral City, Xinjiang, and are of great significance for improving protective forest management and land use decision-making. Full article

Soil texture is an important physical property of soil. Understanding the spatial distribution of cultivated soil texture in black soil areas is crucial for precise agricultural management and cultivated land protection in these zones. This study utilizes the random forest algorithm, Landsat-8 satellite remote sensing data, and climate- and terrain-related environmental covariates to map the spatial distribution of soil texture and analyze its impact on crop growth. The results show that (1) the order of prediction accuracy differs for different soil texture types; April is determined to have the highest prediction accuracy for silt and sand, while May exhibits the greatest accuracy for clay. (2) Adding environmental variables can significantly improve the accuracy of soil texture predictions; the root mean square error (RMSE) has decreased to varying degrees (silt: 0.84; clay: 0.04; sand: 0.85). (3) Soybean growth has the strongest response to soil texture; clay grain is the key factor affecting crop growth in drought scenarios, and sand grain is the dominant factor influencing flooding. This study improves the accuracy of the remote sensing mapping of soil texture through the combination of remote sensing images and environmental variables and quantitatively evaluates the impact of soil texture on crop growth. Full article

The Amazon has undergone significant changes in the landscape with the expansion of human activities. The objective of this study was to characterize the relationship between soil temperature (ST) and moisture (SM) with meteorological data and soil attributes in pasture, forest, and transition areas in the Itacaiúnas River Watershed (IRW), Eastern Amazon. Soil samples were analyzed to determine chemical and granulometric attributes. SM and ST were measured up to 40 cm deep using sensors, and the meteorological variables were quantified by hydrometeorological stations. The chemical characteristics and granulometry indicated greater limitations in the Forest soil, with lower levels of organic carbon and higher contents of sand. In Pasture A, Pasture B, and Transition areas, with some exceptions, there was a progressive increase in ST from July to September. In general, SM was positively correlated with rainfall and negatively correlated with ST, air temperature, wind speed, and solar radiation. Linear models for ST (10–20 cm depth) in Pasture B and Forest areas indicate positive relationships with air temperature and wind speed and negative relationships with solar radiation. The findings of this study can be useful in decision-making regarding the management of ecosystems in the IRW. Full article

Kelps are important habitat-forming species in shallow marine environments, providing critical habitat, structure, and productivity for temperate reef ecosystems worldwide. Many kelp species are currently endangered by myriad pressures, including changing water temperatures, invasive species, and anthropogenic threats. This situation necessitates advanced methods to detect kelp density, which would allow tracking density changes, understanding ecosystem dynamics, and informing evidence-based management strategies. This study introduces an innovative approach to detect kelp density with multibeam echosounder water column data. First, these data are filtered into a point cloud. Then, a range of variables are derived from these point cloud data, including average acoustic energy, volume, and point density. Finally, these variables are used as input to a Random Forest model in combination with bathymetric variables to classify sand, bare rock, sparse kelp, and dense kelp habitats. At 5 m resolution, we achieved an overall accuracy of 72.5% with an overall Area Under the Curve of 0.874. Notably, our method achieved high accuracy across the entire multibeam swath, with only a 1 percent point decrease in model accuracy for data falling within the part of the multibeam water column data impacted by sidelobe artefact noise, which significantly expands the potential of this data type for wide-scale monitoring of threatened kelp ecosystems. Full article

Efficient and reliable corn (Zea mays L.) yield prediction is important for varietal selection by plant breeders and management decision-making by growers. Unlike prior studies that focus mainly on county-level or controlled laboratory-scale areas, this study targets a production-scale area, better representing real-world agricultural conditions and offering more practical relevance for farmers. Therefore, the objective of our study was to determine the best combination of vegetation indices and abiotic factors for predicting corn yield in a rain-fed, production-scale area, identify the most suitable corn growth stage for yield estimation using machine learning, and identify the most effective machine learning model for corn yield estimation. Our study used high-resolution (6 cm) aerial multispectral imagery. Sixty-two different predictors, including soil properties (sand, silt, and clay percentages), slope, spectral bands (red, green, blue, red-edge, NIR), vegetation indices (GNDRE, NDRE, TGI), color-space indices, and wavelengths were derived from the multispectral data collected at the seven (V4, V5, V6, V7, V9, V12, and V14/VT) growth stages of corn. Four regression and machine learning algorithms were evaluated for yield prediction: linear regression, random forest, extreme gradient boosting, and gradient boosting regressor. A total of 6865 yield values were used for model training and 1716 for validation. Results show that, using random forest method, the V14/VT stage had the best yield predictions (RMSE of 0.52 Mg/ha for a mean yield of 10.19 Mg/ha), and yield estimation at V6 stage was still feasible. We concluded that integrating abiotic factors, such as slope and soil properties, significantly improved model accuracy. Among vegetation indices, TGI, HUE, and GNDRE performed better. Results from this study can help farmers or crop consultants plan ahead for future logistics through enhanced early-season yield predictions and support farm profitability and sustainability. Full article

Ion adsorption rare earths are an important strategic resource, but their leach mining causes post-mining wastelands and tailings to suffer from soil sanding, acidification, and heavy metal contamination. This makes natural vegetation recovery difficult, relying mainly on artificial reclamation; however, the reclaimed vegetation grows poorly due to environmental stress. Hyperspectral remote sensing technology, with its high efficiency, non-destructive nature, and wide-range monitoring capability, can accurately estimate the physiological parameters of reclaimed vegetation. This provides support for environmental regulation in mining areas. In this study, three typical types of reclaimed vegetation in the Lingbei Rare Earth Mining Area, Dingnan County, Ganzhou City, were analyzed. Hyperspectral data and the corresponding chlorophyll content were collected to compare the spectral differences between reclaimed and normal vegetation. The spectral data were processed using mathematical transformation, fractional order differentiation, discrete wavelet transform, and continuous wavelet transform. Sensitive bands were extracted, and multispectral transformed feature bands were integrated. Linear and machine learning regression models were used to estimate chlorophyll content. The effects of different spectral processing methods on chlorophyll estimation were then analyzed. The results showed that reclaimed vegetation had higher spectral reflectance than normal vegetation, with the red valley shifting towards the long-wave direction and a steeper red edge slope. Different spectral transformation methods impact the accuracy of chlorophyll content estimation. Using appropriate methods can improve estimation accuracy. Fusing multi-spectral transformation features can achieve relatively good results. Among the models, the random forest regression model provides the best performance in estimating the chlorophyll content of reclaimed vegetation. This study provides a scientific basis for rapid and accurate monitoring of reclaimed vegetation growth in rare earth mining areas, supporting environmental management and decision-making and contributing to ecological restoration. Full article

Machine Learning Techniques (MLTs) and accurate geographic mapping are crucial for managing natural hazards, especially when monitoring the movement of sand dunes. This study presents the integration of MLTs with geographic information systems (GIS) and “R” software to monitor sand dune movement in Najran City, Saudi Arabia (KSA). Utilizing Linear Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Networks (ANN) with nine dune-related variables, this study introduces a new Drifting Sand Index (DSI) for effectively identifying and mapping dune accumulations. The DSI incorporates multispectral sensors data and demonstrates a robust capability for monitoring sand dune dynamics. Field surveys and spatial data analysis were used to identify about 100 dune locations, which were then divided into training (70%) and validation (30%) sets at random. These models produced a thorough dune encroachment risk map that divided areas into five hazard zones: very low, low, medium, high, and very high risk. The results show an average sand dune movement of 0.8 m/year towards the southeast. Performance evaluation utilizing the Area Under Curve-Receiver Operating Characteristic (AUC-ROC) approach revealed AUC values of 96.2% for SVM, 94.2% for RF, and 93% for ANN, indicating RF (AUC = 96.2%) as the most effective MLTs. This crucial information provides valuable insights for sustainable development and environmental protection, enabling decision-makers to prioritize regions for mitigation techniques against sand dune encroachment. Full article

Soil quality offers a holistic approach for understanding the relationships between soil’s biological, chemical, and physical properties, which is crucial for sustainable land use and the management of non-renewable soil resources. This study evaluates the impact of land use on a set of 23 soil quality indicators (SQIs) across 5 land uses of the Mediterranean agro-ecosystems: forest, olive groves, wheat fields, a corn/wheat crop rotation system, and pasture. Seasonal soil sampling was carried out over two consecutive years in three conventionally managed fields representing each land use type. For each sampling, physicals SQIs (soil moisture, porosity-Vp-, bulck density-BD-, water holding capacity-WHC-, clay, silt, sand), chemical SQIs (organic carbon-Corg-, total Nitrogen-TN-, C/N, PH, electrical conductivity-EC-, ammonium-NH₄-N-, nitrate-NO₃-N- and available nitrogen-Nmin-), and biological SQIs (soil microbial biomass C-Cmic- and N-Nmic-, Cmic/Nmic, Cmic/Corg, Nmic/TN, active carbon—Cact-, Cact/Corg) were evaluated. Through multivariate analysis, five key soil quality factors—organic matter, microbial biomass, nutrients, C/N ratio, and compaction—were identified as indicators of soil quality changes due to land use, explaining 82.9% of the total variability in the data. Discriminant analysis identified organic matter and the C/N factors as particularly sensitive indicators of soil quality changes, reflecting the quantity and quality of soil organic matter, incorporating 87.8% of the SQIs information resulting from the 23 indicators. ΤΝ, accounting for 84% of the information on the organic matter factor, emerges as a key indicator for predicting significant changes in soil quality due to land use or management practices. The TN and C/N proposed indicators offer a simplified yet effective means of assessing soil resource sustainability in the Mediterranean agroecosystems, providing practical tools for monitoring and managing soil quality. Full article

There is an unexplored knowledge gap regarding the relationship between soil quality and mean annual increment (MAI) in forest plantations in Tanzania. Therefore, this study aimed to identify soil quality indicators and their impact on the mean annual increment (MAI) of Pinus patula at Sao Hill (SHFP) and Shume forest plantations (SFP) in Tanzania. The forests were stratified into four site classes based on management records. Tree growth data were collected from 3 quadrat plots at each site, resulting in 12 plots in each plantation, while soil samples were taken from 0 to 40 cm soil depth. Analysis of variance examined the variation in soil quality indicators between site classes at two P. patula plantation sites. Covariance analysis assessed the differences in MAI and stand variables across various site classes, taking into account the differing ages of some stands, with stand age serving as a covariate. Linear regression models explored the relationship between soil quality indicators and MAI, while partial least squares regression predicted MAI using soil quality indicators. The results showed that, at SHFP, sand, organic carbon (OC), cation exchange capacity, calcium (Ca), magnesium (Mg), and available P varied significantly between site classes, while silt, clay, and available P varied significantly at SFP. At SHFP, sand and clay content were positively correlated with MAI, while at SFP, silt content, available P (Avail P), potassium (K), Ca, and Mg showed significant positive correlations. Soil quality indicators, including physical and chemical properties (porosity, clay percentages, sand content, and OC) and only chemical (K, Mg, Avail P, and soil pH) properties were better predictors of the forest mean annual increment at SHFP and SFP, respectively. This study underscores the importance of monitoring the quality of soils in enhancing MAI and developing soil management strategies for long-term sustainability in forests production. Full article