Soil Mapping Research Articles

Validation of Digital Soil Map in Maize Growing Areas of Chitwan, Nepal

National Soil Science Research Centre of the Nepal Agricultural Research Council (NARC) with technical support from the International Maize and Wheat Improvement Center developed Digital Soil Map (DSM), a web-based information system, in 2020 using the legacy data with a geospatial model using a random forest machine learning prediction approach. The map generated with the model predicted values besides geo-referenced points that require further validation. Since DSM was launched, no work has been done to validate the map. We sampled 452 points from all municipalities of the Chitwan district using a gridded sampling approach to validate the existing predicted values of the DSM. We found that the observed values such as soil texture, soil organic matter, and total nitrogen content were similar to the range values of DSM. Still, a discrepancy was found between the available potassium and phosphorous. In the majority of areas, the observed value of available soil potassium (20 – 450 kg K ha-1 ± 15 kg K ha-1) was found lower compared to the DSM values (118 – 330 kg K ha-1), however, available phosphorous (55 – 230 kg P ha-1 ± 10 kg P ha-1) was found higher compared to DSM range values (11 – 139 kg P ha-1). The maize growing area of Chitwan was found suitable with soil pH (6.4 – 6.8) and other nutrients except for available soil potassium. Most of the areas from Eastern and Western Chitwan reported potassium mining, which needs to be considered in balancing nutrients in field crops.

A Tribute to Jaume Porta Casanellas and His Influence on Soil Science

This article provides personal and professional assessments from disciples, colleagues and friends of Jaume Porta Casanellas (Barcelona, 1944; Lleida, 2023), a prominent soil scientist. He began his agricultural engineering studies at the Polytechnic University of Madrid (UPM) where he met Marta López-Acevedo, his wife and outstanding collaborator. At UPM, he started his early work in soil science under the guidance of Professor Carlos Roquero who became his mentor and friend. Jaume Porta was a dedicated, passionate soil scientist who engaged extensively in teaching and research in Soil Science, while also excelling as a manager. He emerged as a leader due to his initiatives in promoting Soil Science in Catalonia and Spain, and for his forward-thinking vision, evident in his decisions as Rector of the University of Lleida, which have significantly contributed to the city’s development. From the beginning, he advocated for detailed (1:25,000) soil mapping of Catalonia to enhance territorial planning and agricultural progress. His primary research focus was on salt-affected soils and soils with gypsum, alongside soil erosion and conservation. Porta devoted a lot of effort to improve soil field descriptions with his Agenda de campo. He played a key role in standardizing soil analytical methods, establishing large series laboratories in Spain, notably the LAF in Sidamon (Lleida), and aligning Spanish soil labs with the international GLOSOLAN network. As president of the SECS, he energized activities and encouraged member participation. His educational publications, mainly his comprehensive textbook Edafología, are considered fundamental in Soil Science across Spanish-speaking countries, as is the Multilingual Dictionary of Soil Science, representing the pinnacle of his efforts to rigorously disseminate soil science concepts and terms in Spanish, Catalan, Galician, and Portuguese. He contributed significantly to international Soil Science courses in Mexico and played a key role in establishing the JADE postgraduate training program. He facilitated the creation and international visibility of the Spanish Journal of Soil Science. Additionally, he advocated for the establishment of the Soil Sciences Documentation Centre (Ce.SECS) to preserve historical publications and the legacy of soil scientists. Jaume Porta’s enduring impact, both professionally and personally, will be felt for years to come.

Predictive soil mapping using random forest models: Applications in pH and soil organic matter assessment

Digital Soil Mapping (DSM) presents a highly scalable and efficient alternative to traditional soil analysis, which is typically limited by its labor-intensive processes, time constraints and low spatial resolution. By utilizing advanced computational techniques such as machine learning and remote sensing, DSM overcomes these limitations and improves the accuracy, efficiency and scalability of soil property assessments. This study, conducted across Tamil Nadu, India, applied DSM and Random Forest (RF) models to predict 2 key soil properties: pH and Soil Organic Matter (SOM). We employed Conditioned Latin Hypercube Sampling (cLHS) for optimized sampling point selection and utilized the Boruta algorithm to identify the most relevant covariates for accurate modeling. The RF models were fine-tuned using a comprehensive grid search, with the optimal configuration spanning from 500 to 2000 trees (ntree) and mtry from 1 to 11. The best-performing model was found with 2000 trees and mtry set to 1 yielding superior prediction for SOM and pH with Root Mean Square Error (RMSE) values of 0.71 and 0.60 respectively, showcasing a high level of predictive accuracy. Our findings emphasize the critical role that remote sensing indices play in predicting SOM, while pH was influenced by both terrain features and remote sensing data. In comparison to previous studies, this research offers novel improvements in both sampling optimization and model configuration, leading to enhanced predictive performance. These results hold significant potential for sustainable land-use planning, agricultural productivity and environmental management.

Integrating proximal geophysical sensing and machine learning for digital soil mapping: Spatial prediction and model evaluation using a small dataset

Geophysical methods support soil security by providing non-invasive tools to assess soil properties, monitor degradation, and guide sustainable management strategies. However, studies focusing the spatial prediction of geophysical data remain limited. In this research, we aimed to model and predict the spatial distribution of soil geophysical properties using parent material and terrain attributes with machine learning algorithms. In addition, we tested the nested leave-one-out cross validation (nested-LOOCV) method to deal with datasets with limited size. We performed a geophysical survey using three types of sensors (radiometric, magnetic and electric methods). The random forest (RF) and support vector machine (SVM) algorithms presented the best results, with RF showing higher performance for K40 and magnetic susceptibility, and SVM had higher performance for eU, eTh and apparent electrical conductivity. Parent materials and digital elevation model were the most significant variables for the modelling. The nested-LOOCV method proved to be adequate for small soil dataset. Machine learning techniques are potential tools for modelling soil geophysical variables. The combination with computational techniques shows the great relevance of geophysical measurements for the estimation of soil properties related to fertility and soil genesis.

Mapping soil VOCs using three green sample extraction techniques and GC–MS

Sample preparation is a very crucial step prior to sample analysis. Three green adsorptive sample preparation micro-extraction techniques were investigated (smart solid-phase microextraction (SPME), high-capacity sorptive extraction (HiSorb), and stir bar sorptive extraction (SBSE)) for the determination of volatile organic compounds (VOCs) emitted from vineyard soil samples after method optimization. More specifically, the 95 μm Carbon Wide Range/Polydimethylsiloxane (CWR/PDMS) smart SPME fiber, CWR/PDMS HiSorb, and PDMS Twister micro-extraction tools were compared for their extraction capabilities. The headspace (HS)-SPME-gas chromatography-mass spectrometry (GC–MS) method was proved better for the extraction of VOCs from the vineyard soils due to shorter exposure time (45 min), its automation (use of a fully automated system compared to the other two), and the high sample throughput analysis. The validation of the HS-SPME-GC–MS method showed good linearity (R2 ≥ 0.9951) and limit of detection (LOD), whereas the limit of quantitation (LOQ) ranged from 0.04-3.65 μg/kg. Also, the repeatability and reproducibility of the results showed a relative standard deviation (RSD) lower than 4.73 %. A total number of 47 soil-derived VOCs were identified through the validated HS-SPME-GC–MS method, and 9 targeted VOCs were quantified with total average concentrations ranging from 0.14-28.07 µg/kg. Smart SPME fiber proved beneficial over the two other tools, highlighting the aspects of green chemistry.

Maps of agrolandscape and ecological zoning of natural and natural-agricultural ecosystems of the Russian Federation

Agriculture has a large area of coverage and places the greatest burden on land, soil, water and biological resources in many countries of the world. Agricultural lands occupy huge areas in the world (4.8 billion hectares, or 37% of the land) and in Russia (221.9 million hectares, or 13% of the Russian Federation area). The agriculture best adapted to local conditions is the most beneficial one for people and nature. The main direction of agricultural adaptation is agrolandscape-ecological zoning. In order to provide information support for regionally, landscapeand ecologically differentiated agriculture and rational environmental management, an agrolandscape– ecological zoning of natural and natural-agricultural ecosystems was developed for the first time for all 11 natural-economic regions of Russia, namely, Northern, North-Western, Volga–Vyatka, Central, Central Black Earth, Volga, North Caucasus, Ural, West Siberian, East Siberian, and Far Eastern. The zoning was carried out using comparative geographical and agrolandscape-ecological methods, ecological-landscape and agroecological approaches. The contour and information basis for zoning is the map of Soil–Ecological zoning of the Russian Federation from the Faculty of Soil Science of Lomonosov Moscow State University. Maps of other types of zoning, numerous maps and atlases, statistical data, available literary and stock sources, ground-based and remote data were also used. Our sets of zoning materials included: a map, a map legend, 3 databases (land, forage lands, and negative processes), 2 classifications (forage lands, reindeer pastures, if any), articles, monographs, recommendations, and proposals for production. The maps have been compiled on a 1:2,500,000 scale on a modern, highly informative topographic cartographic basis for the map of Russian Federation. The maps show 6 types of boundaries, including 4 types of agrolandscape-ecological ones (taken from the Soil–Ecological Zoning map): 1) zones, 2) mountainous territories, 3) provinces, 4) districts and 2 types of administrative ones (available on the cartographic basis) of: 1) constituent entities of the Russian Federation, and 2) natural-economic regions.

Soil erodibility mapping using remote sensing and in situ soil data with random forest model in a mountainous catchment of Indian Himalayas.

Land degradation is accelerating in the Himalayan ecosystem, resulting in the loss of soil nutrients due to severe erosion. Soil erosion presents a significant environmental challenge, resulting in both on-site and off-site consequences, such as reduced soil productivity and siltation in reservoirs. Soil erodibility (K factor), an inherent soil property, determines the susceptibility of soils to erosion. Sampling across hilly and mountainous terrain pose challenges due to its complex landscape. Despite these challenges, it is essential to study K factor variations in different land use/land cover types to comprehend the threat of erosion. Digital soil mapping offers an opportunity to overcome this limitation by providing spatial predictions of soil properties. The objective of our study is to map the spatial distribution of soil erodibility using the Random Forest (RF) model, a machine learning method based on sampled in situ soil data and environmental covariates. We collected 556 surface soil samples from the mountainous catchment (Tehri dam catchment) using the stratified random sampling approach. The model performed satisfactorily in both training (r2 = 0.91; RMSE = 0.00185) and testing (r2 = 0.45; RMSE = 0.00318) phases. Subsequently, we generated a digital map with a resolution of 12.5m to depict the distribution of the K factor. Our analysis revealed that key environmental variables influencing the prediction of the K factor included geology, mean NDVI, and climatic factors. The average K factor value was estimated at 0.0304 and ranging from 0.0251 to 0.0400 t ha h ha-1MJ-1mm-1. A higher K factor was observed in the barren land (0.0344) primarily located in the higher and trans-Himalayan region of seasonally snow-covered areas. These areas typically feature young soils with weak soil formation and unstable soil aggregates. Subsequently cropland/cultivated soils (0.0307) exhibited higher K factor values due to the breakdown of soil aggregates by ploughing activities and exposing carbon to decomposition. The average K factor value of evergreen (0.0294) and deciduous (0.0295) forests were the lowest compared to other land use/land cover types indicating the role of forests in resisting soil erosion. By assessing and predicting soil erodibility, land planners and farmers can implement erosion control measures to protect soil health, prevent sedimentation in water bodies, and sustain agricultural productivity in the Himalayas.

A Semi-Detailed Survey of Soils in the City of Jaboatão dos Guararapes – PE

The economic development of the city of Jaboatão dos Guararapes was generated spontaneously without considering the land use capacity or its position in the landscape. Due to the occupation and intensive disordered use of the city pedological coverage, there have been mass movements that have caused economic and social losses. These can be resized based on the understanding of the pedological aspects inherent to the city. The objective of the present paper was to map the soils of the city area at a semi-detailed level. For this purpose, different toposequences were used, with soil examinations at a rate of 1 for every 2.75 km², totaling 94 points. The mapping and taxonomic classification of soils were made in accordance with standards, procedures and criteria adopted by Embrapa Soils. Based on the morphological data, locations were defined for soil description and sampling, totaling 14 soil profiles. 15 soil classes were identified, and 23 mapping units were defined, which highlighted the notable role of the source material in the distribution of the city's pedological properties. The mapping units that require greater care for use are: a) in hill environments - PAdr1, PVAd1 and PVd; and b) in the fluvial-marine plains – EKu1, EKu2 and GXbd2. The expansion of urban areas must consider the type of soil and the behavior of the material, especially during the rainy season, in order to minimize risks and adverse losses.

Empirical Modeling of Soil Loss and Yield Utilizing RUSLE and SYI: A Geospatial Study in South Sikkim, Teesta Basin

Soil erosion and subsequent sedimentation pose significant challenges in the Sikkim Himalayas. In this study, we conducted an assessment of the impact of rainfall-induced soil erosion and sediment loss in South Sikkim, which falls within the Teesta Basin, employing Revised Universal Soil Loss Equation (RUSLE) and Sediment Yield Index (SYI) models. Leveraging mean annual precipitation data, a detailed soil map, geomorphological landforms, Digital Elevation Models (DEMs), and LANDSAT 8 OLI data were used to prepare the factorial maps of South Sikkim. The results of the RUSLE and SYI models revealed annual soil loss >200 t ha−1 yr−1, whereas mean values were estimated to be 93.42 t ha−1 yr−1 and 70.3 t ha−1 yr−1, respectively. Interestingly, both models displayed similar degrees of soil loss in corresponding regions under the various severity classes. Notably, low-severity erosion <50 t ha−1 yr−1 was predominantly observed in the valley sides in low-elevation zones, while areas with severe erosion rates >200 t ha−1 yr−1were concentrated in the upper reaches, characterized by steep slopes. These findings underscore the strong correlation between erosion rates and topography, which makes the region highly vulnerable to erosion. The prioritization of such regions and potential conservation methods need to be adopted to protect such precious natural resources in mountainous regions.

Examining the effect of soil organic carbon on major Canadian Prairie crop yields with predictive soil mapping

AbstractMaintaining soil organic carbon (SOC) is critical for global food security as it is essential for soil functions that sustain crop yields. There has been an increase in predictive soil mapping, which when combined with extensive crop yield datasets, enables a better understanding of crop yield and SOC relationships. This study focused on updating maps of SOC content in Saskatchewan using recently digitized historical SOC datasets and predictive soil mapping, and using the maps to examine the relationship between SOC and crop yield. A database of 5014 SOC values was used to map SOC contents using a Random Forest model and a range of environmental covariates. The final SOC model had a R2 of 0.48, root mean square error of 0.98%, concordance correlation coefficient of 0.67, and a bias of 0.12%. The relationship between mapped SOC values and crop yield data, with 100,000–200,000 records depending on crop type, was then assessed using a linear mixed effects model after normalizing the data by rural municipality to remove broad‐scale climate effects. Overall, an increase in SOC by 1% led to an increase on average of 263 kg ha−1 for wheat (Triticum aestivum L.), 293 kg ha−1 for barley (Hordeum vulgare L.), 133 kg ha−1 for canola (Brassica napus L.), and 135 kg ha−1 for field peas (Pisum sativum L.). These results show that increasing SOC was associated with greater yields for four major crops in Saskatchewan, with the largest gains occurring when the initial SOC contents are lower.

Soil sampling design matters - Enhancing the efficiency of digital soil mapping at the field scale

Optimisation of sampling design (methods chosen to select the samples) and sample size (number of samples) remains a key challenge in digital soil mapping, especially in the area of precision farming with the expected economic benefits from the introduction of new technologies. As the existing information is available in the form of relevant environmental covariates, its combination with non-parametric machine learning techniques requires careful planning from the initial field sampling to the final production of digital soil maps. The aim of this study is to compare widely used covariate-wise sampling designs combined with variable sample sizes for supervised prediction of common soil drivers of agricultural productivity (pH, soil organic carbon, soil macronutrients) in a real case study of a field (35 ha) with heterogeneous soil properties. From a total of 200 samples, we evaluated different sample sets where 10, 30 and 60 field samples were selected by conditioned Latin Hypercube Sampling (cLHS) and Feature Space Coverage Sampling (FSCS) to calibrate random forest (RF) models. The evaluation was performed on independently in-situ sampled test points. In addition to these datasets, we also compared the investigated methods with Simple Random Sampling (SRS) in a numerical benchmark experiment with increasing sample size, comparing the global accuracies of the predicted maps on the test points, but using interpolated maps as the artificial true population for each soil characteristic. The results of the study in both the field experiment and the numerical experiment showed slightly better results for the FSCS method, especially when the number of samples was small. At smaller training sample sizes, the risk of insufficiently accurate prediction models was slightly lower for FSCS and the difference decreased as the sample size increased. Nevertheless, sample size proved to be the most important factor in the accuracy of RF models, regardless of the sampling technique. The results suggest that a sample size between 18 and 30 training samples (0.6 to 1 sample ha−1) seems plausible for covariate-wise predictions using RF at field scale in our case study. The relative importance of each auxiliary variable for each RF calibration was also assessed for the field experiment. The results showed that the additional introduction of spatial proxies overshadowed the importance of other covariates, but only significantly improved the model calibration at larger sample sizes. The calibrated models without spatial proxies showed the strongest effect of remotely sensed surface characteristics.

Suitability mapping for alternative crops: A consistent, high-resolution approach for the United States

Alternative crops are a key aspect of many nature-based solutions in agriculture, and there is a need for more consistent geographic information on biophysical suitability to aid in both farm-level planning and larger-scale analyses. Here we describe an approach for generating consistent, replicable, high-resolution suitability maps for any alternative crop species across the USA. The method employs a criteria-based approach to map potential species performance using a simple suitability index. Criteria for suitable and ideal ranges of values for influential biophysical variables are created using data collected from published sources and are reviewed by experts. Publicly available soil and climate map data are used with the criteria to map suitability for each variable which are integrated into an overall suitability index map. Maps of unsuitable locations are combined to produce a limiting variable map showing which category of environmental variables is most limiting. We demonstrate the application of this approach for two alternative perennial crops, apple (Malus spp.) and Chinese chestnut (Castanea mollissima) and validate its accuracy using known farm locations. Maps of apple and chestnut in four distant study regions show varying patterns of suitability and potential performance depending on the climate and geophysical characteristics of the region. The maps can be used to identify areas of high suitability and compare across regions or between species and be combined with socio-economic and environmental datasets for further analysis. Compared to other approaches, ours can be applied to multiple species with a range of pre-existing knowledge in a consistent way, allowing for reliable mapping and subsequent research and planning for alternative crops and nature-based solutions in agriculture.

Towards data-driven tropical forest restoration: Uncovering spatial variation, interactions and historical management effects on nutrients along soil depth gradients

Data scarcity hinders global conservation initiatives, and there is a pressing demand for spatially detailed soil and species data to restore human-altered tropical forests. We, therefore, aimed to generate foundational soil environment and habitat suitability data and high-resolution soil maps to aid restoration efforts in a critical ecosystem of the threatened Indo-Burma Biodiversity Hotspot region, i.e., Tarap Hill Reserve (THR) in Bangladesh. Using multiple soil depths and vegetation data, we answered three major questions. (QI) How do spatial distribution and the relationships between soil physicochemical properties (i.e., pH, sand, silt, and clay percentages, organic carbon, and nutrients – N, P, K, Ca, Mg, Fe, and Zn) vary from surface to deeper soils (top 1 m)? (QII) How do different forest management interventions, i.e., old-growth forests (OGF), mixed plantations (MXP), and mono-specific plantations (MOP), influence soil properties, nutrients, and carbon in different soil depths? (QIII) Which spatial interpolation methods are best suited for making more accurate soil property predictions at different depths? Our analyses reveal decreasing availability of critical nutrients like N, P, Mg, and Fe from surface to subsurface soils, while pH, soil organic carbon, and clay content increased with depth. Several soil properties showed significant interactions, although the strength of the interactions changed from surface to deeper soils. Besides, forest management interventions significantly influenced soil functionality by having higher nutrient availability and soil organic carbon in OGF than MXP and MOP. Predictive performances of the deterministic and geostatistical interpolation methods varied for different soil properties in different soil depths, and soil maps revealed substantial heterogeneity in the distribution of soil properties across space and along depths. This study represents a pioneering step in data-driven tropical forest restoration, and our novel findings and high-resolution soil maps could guide future studies focusing on species habitat preferences, restoration ecology, and spatial conservation planning in the Indo-Burma Biodiversity Hotspot region and elsewhere in the tropics.

A geographically weighted neural network model for digital soil mapping of heavy metal copper in coastal cities

Assessing the spatial distribution of heavy metals in soil is essential for mitigating risks to human health and ensuring the sustainable use of soil resources. This study proposed a geographically weighted neural network (GWNN) model, leveraging deep learning and geographically weighted regression (GWR). The model was designed based on the GWR concept to address the spatial autocorrelation of copper (Cu) in soil and incorporated convolutional neural network (CNN) to capture the nonlinear relationships between Cu and environmental covariates. The GWNN model was compared with GWR, extreme gradient boosting (XGBoost), and artificial neural network (ANN) models. XGBoost was employed to select important environmental covariates and spatial autocorrelation of Cu concentrations was assessed using Moran’s I. The model’s performance was evaluated using 10-fold cross-validation, and prediction uncertainty was quantified with 100 bootstrap models. The results indicated that temperature covariates were the most significant predictors of soil Cu concentrations. The R2 values for Cu prediction accuracy were 0.60 for GWNN, 0.53 for ANN, 0.49 for XGBoost, and 0.32 for GWR. The spatial distribution of Cu showed a trend of higher concentrations in the north and lower concentrations in the south, consistent with spatial clusters identified by local Moran’s I. The mean uncertainty of the 90% confidence interval for GWNN was 16.49%, closely aligning with XGBoost (15.44%) and ANN (16.29%) and significantly outperforming the GWR (18.25%). Overall, the GWNN model demonstrated strong predictive accuracy and low uncertainty, offering an improved approach for digital soil mapping applications.

Interpreting and evaluating digital soil mapping prediction uncertainty: A case study using texture from SoilGrids

Soil information is critical for a wide range of land resource and environmental decisions. These decisions will be compromised when the soil information quality is unsatisfactory. Thus, users of soil information need to understand and consider the uncertainty of the available soil information and be able to judge whether it is fit for purpose. The uncertainty information provided with the SoilGrids2.0 product was examined in a case study. We hypothesised that the soil property predictions for the Netherlands (NL) might be less uncertain than those of New Zealand (NZ) because there were more relevant training data for NL than for NZ. The study objectives were to: 1)understand whether the provided uncertainty information is correct for both countries; 2)explore spatial patterns and relationships in the prediction error and uncertainty information using quantitative tools and new graphical analyses; 3)analyse whether these patterns and relations can be explained; and 4)explore how the uncertainty information and insights derived from graphical analyses might assist an end user to determine whether a map is suitable for their purpose. The study focused on soil texture.Independent datasets showed that the SoilGrids 2.0 uncertainty information was too optimistic for sand and too pessimistic for clay for both countries. The graphical analyses confirmed the initial assumption that NL predictions were more accurate than those for NZ, but they also indicated that some locations in NL have high uncertainty. The graphical analyses allowed only a limited identification of the four sources of uncertainty in digital soil maps, but were quite insightful in helping us to better understand the reliability of the information. A set of recommendations was developed for both producers and consumers of digital soil mapping (DSM) products. This includes the provision of a summary map of accuracy classes. We suggest that more research and educational effort is needed to ensure that digital soil maps are used appropriately.

Estimation of Soil Salinity by Combining Spectral and Texture Information from UAV Multispectral Images in the Tarim River Basin, China

Texture features have been consistently overlooked in digital soil mapping, especially in soil salinization mapping. This study aims to clarify how to leverage texture information for monitoring soil salinization through remote sensing techniques. We propose a novel method for estimating soil salinity content (SSC) that combines spectral and texture information from unmanned aerial vehicle (UAV) images. Reflectance, spectral index, and one-dimensional (OD) texture features were extracted from UAV images. Building on the one-dimensional texture features, we constructed two-dimensional (TD) and three-dimensional (THD) texture indices. The technique of Recursive Feature Elimination (RFE) was used for feature selection. Models for soil salinity estimation were built using three distinct methodologies: Random Forest (RF), Partial Least Squares Regression (PLSR), and Convolutional Neural Network (CNN). Spatial distribution maps of soil salinity were then generated for each model. The effectiveness of the proposed method is confirmed through the utilization of 240 surface soil samples gathered from an arid region in northwest China, specifically in Xinjiang, characterized by sparse vegetation. Among all texture indices, TDTeI1 has the highest correlation with SSC (|r| = 0.86). After adding multidimensional texture information, the R2 of the RF model increased from 0.76 to 0.90, with an improvement of 18%. Among the three models, the RF model outperforms PLSR and CNN. The RF model, which combines spectral and texture information (SOTT), achieves an R2 of 0.90, RMSE of 5.13 g kg−1, and RPD of 3.12. Texture information contributes 44.8% to the soil salinity prediction, with the contributions of TD and THD texture indices of 19.3% and 20.2%, respectively. This study confirms the great potential of introducing texture information for monitoring soil salinity in arid and semi-arid regions.

Self-supervised learning of Vision Transformers for digital soil mapping using visual data

In arid environments, prospecting cultivable land is challenging due to harsh climatic conditions and vast, hard-to-access areas. However, the soil is often bare, with little vegetation cover, making it easy to observe from above. Hence, remote sensing can drastically reduce costs to explore these areas. For the past few years, deep learning has extended remote sensing analysis, first with Convolutional Neural Networks (CNNs), then with Vision Transformers (ViTs). The main drawback of deep learning methods is their reliance on large calibration datasets, as data collection is a cumbersome and costly task, particularly in drylands. However, recent studies demonstrate that ViTs can be trained in a self-supervised manner to take advantage of large amounts of unlabelled data to pre-train models. These backbone models can then be finetuned to learn a supervised regression model with few labelled data.In our study, we trained ViTs in a self-supervised way with a 9500 km2 satellite image of dry-lands in Saudi Arabia with a spatial resolution of 1.5 m per pixel. The resulting models were used to extract features describing the bare soil and predict soil attributes (pH H2O, pH KCl, Si composition). Using only RGB data, we can accurately predict these soil properties and achieve, for instance, an RMSE of 0.40 ± 0.03 when predicting alkaline soil pH. We also assess the effectiveness of adding additional covariates, such as elevation. The pretrained models can as well be used as visual features extractors. These features can be used to automatically generate a clustered map of an area or as input of random forests models, providing a versatile way to generate maps with limited labelled data and input variables.

Estimating sediment delivery ratio using the RUSLE-IC-SDR approach at a complex landscape: A case study at the Lower Snowy River area, Australia

Understanding the dynamics of sediment transport and deposition in natural landscapes is critical to developing cost-effective mitigation measures to control soil erosion and protect ecosystems. However, none of a single existing model can quantify sediment delivery ratio (SDR) and the impact factors such as vegetation and geomorphology, especially in a complex landscape. In this case study, we applied an integrated approach including the revised universal soil loss equation (RUSLE) and the index of connectivity (IC) to assess hillslope erosion and SDR, namely RUSLE-IC-SDR, across a complex landscape in the Lower Snowy River area, Australia. The RUSLE factors were derived from a high-resolution (2 m) digital elevation model (DEM), digital soil maps, high-resolution rainfall data and remotely sensed fractional vegetation cover. A seven-class landform classification was delineated from the high-resolution DEM using a fuzzy logic landform model (FLAG). We further examined the impacts of rainfall, vegetation cover and geomorphology on sediment dynamics and distribution across the study area. Field and laboratory data from 10 plot sites across the study area were collected and used for model validation. This case study showed that the RUSLE-IC-SDR approach can assess the overall sediment budget and the impacts of rainfall, vegetation cover and geomorphology across a complex landscape. Findings from this study can identify and track the areas likely to generate high sediment yield for developing ecological restoration, feral animal management and other catchment management measures.

디지털 토양도 작성 기법을 적용한 산림 토양 탄소 저장량 평가

디지털 토양도 작성 기법을 적용한 산림 토양 탄소 저장량 평가

Quantification of Soil Erosion Using Digital Soil Mapping and RUSLE Method for Coimbatore District, Tamil Nadu, India

Quantification of Soil Erosion Using Digital Soil Mapping and RUSLE Method for Coimbatore District, Tamil Nadu, India