Table 2 - uploaded by Lin Yang
Content may be subject to copyright.
Source publication
Conventional soil maps, as the major data source for information on the spatial variation of soil, are limited in terms of both the level of spatial detail and the accuracy of soil attributes. These soil maps, however, contain valuable knowledge on soil-environment relationships. Such knowledge can be extracted for updating conventional soil maps t...
Contexts in source publication
Context 1
... was eventually selected as the optimal number of clusters because four soil types occur in this unit on the conventional soil map. Th e centroids for four environmental clusters are listed in Table 2. ...
Context 2
... determine to which soil type Environmental Cluster 4 should be related, the TWI was considered as the decisive vari- able in this study because it could be used to distinguish diff er- ent soil drainage conditions, which was essential in determining the soil mapping units in this area. We compared the TWI value (Table 2) of its centroid with two other clusters that were identi- fi ed as well-drained Carleton and imperfectly drained Carleton to determine the soil type for Cluster 4 or to decide whether it is just a transition type. Th e TWI value for the centroid of Cluster 1 (associated with imperfectly drained Carleton) was 8.91. ...
Citations
... Conventional soil maps (legacy data) are limited by the level of spatial detail and the prediction accuracy of soils and properties (Yang et al., 2011). Soil properties affect many physical (structure, available water holding capacity), chemical (nutrients, soil reaction) and biological (soil organic matter, microorganisms) properties to support research decisions regarding crops and soil management at these study sites (Brady et al., 2008). ...
... However, predicting soil properties across a flat terrain, where topographic variation is minimal, based on the relationship between soil properties and landscape is challenging (Guo et al., 2021). Thus, selecting the appropriate ECs depends on their relationship with soils and properties and is site-specific, and a combination of ECs derived from DEM and remote sensing (reflectance) can improve accuracy predictions for flat terrains (Yang et al., 2011). ...
... Machine learning first captures the relation between environmental variables and the soil property of interest using training data and next uses this relation to spatially predict the soil property from maps of the environmental variables (McBratney et al., 2003). Advances in remote sensing provide ever increasing spatial and detailed information of environmental variables (Yang et al., 2011;Asgari et al., 2020). The ...
Spatial soil information is essential for informed decision-making in a wide range of fields. Digital soil mapping (DSM) using machine learning algorithms has become a popular approach for generating soil maps. DSM capitalises on the relation between environmental variables (i.e., features) and a soil property of interest. It typically needs a training dataset that covers the feature space well. Mapping in areas where there are no training data is challenging, because extrapolation in geographic space often induces extrapolation in feature space and can seriously deteriorate prediction accuracy. The objective of this study was to analyse the extrapolation effects of random forest DSM models by predicting topsoil properties (OC, clay, and pH) in four African countries using soil data from the ISRIC Africa Soil Profiles database. The study was conducted in eight experiments whereby soil data from one or three countries were used to predict in the other countries. We calculated similarities between donor and recipient areas using four measures, including soil type similarity, homosoil, dissimilarity index by area of applicability (AOA), and quantile regression forest (QRF) prediction interval width. The aim was to determine the level of agreement between these four measures and identify the method that had the strongest agreement with common validation metrics. The results indicated a positive correlation between soil type similarity, homosoil and dissimilarity index by AOA. Surprisingly, we observed a negative correlation between dissimilarity index by AOA and QRF prediction interval width. Although the cross-validation results for the trained models were acceptable, the extrapolation results were unsatisfactory, highlighting the risk of extrapolation. Using soil data from three countries instead of one increased the similarities for all measures, but it had a limited effect on improving extrapolation. Also, none of the measures had a strong correlation with the validation metrics. This was particularly disappointing for AOA and QRF, which we had expected to be strong indicators of extrapolation prediction performance. Results showed that homosoil and soil type methods had the strongest correlation with validation metrics. The results for this case study revealed limitations of using AOA and QRF as measures of extrapolation effects, highlighting the importance of not relying on these methods blindly. Further research and more case studies are needed to address the effects of extrapolation of DSM models.
... Soil surveys in the framework of CSM are important to encourage DSM efforts. CSMs are the principal sources of soil attributes information; additionally, in CSM, soil scientists have identified soil-landscape relationships that, in quantitative approximations, are difficult to interpret (Yang et al., 2011). However, soil surveys in CSM are costly and time-consuming in proportion to scale: the more detail, the more sampling density and soil laboratory analyses (Grunwald et al., 2011;Wadoux et al., 2021). ...
Studies on soil organic carbon stocks (SOCS) are increasingly relevant to developing efficient mitigation and adaptation strategies for climate change. Reliable information on soil organic carbon (SOC) content, bulk density (BD), and coarse fragments (CF) are required for precise SOCS calculation. The data quality of SOCS‐related variables is important to represent SOCS realistically across different levels of disturbance in the terrestrial ecosystems of Guatemala. The main objective is to develop Guatemala's first national SOC database to support studies of SOCS magnitudes and spatial trends. We identified and collected national sources of variables related to SOCS (SOC, BD, CF) across the country, mainly distributed in the central zone dominated by disturbed ecosystems and agricultural territories. We integrated 910 observations (soil samples and soil profiles) of SOC content (range 1.45–162 g·kg ⁻¹ ), 704 of BD (range 0.42–1.69 g·cm ⁻³ ), and 8 of CFs (0%–21% weight). This new database represents the edaphic, climatic, and land use variability of Guatemalan territory. The database contains soil observations collected from 1965 to 2010. The year 2010 has the majority of soil observations (41%). SOCS‐related variables are standardized at 0–30 centimetres of depth using mass conservative splines, which are used to represent SOCS and soil depth relationships. We provide new information on SOCS across various ecological and environmental conditions to enable SOC monitoring systems to report reliable and accurate estimates. The new database is appealing for scientific and commercial purposes, such as representing Guatemalan soils in Earth system models or using soil information in the ecosystem services market (e.g., carbon markets). The new database is accessible to all users through the platform of the Environmental Data Initiative https://doi.org/10.6073/pasta/8dd15238c604c3ac75daf985548bd05c .
... This model has been widely applied to infer soil types and soil properties [22]. For example, Yang, et al. [23] used the acquired knowledge of soil-environment relationships and the SoLIM to update the conventional soil-type map of Wakefield in northern Canada. Their study showed that the updated digital soil map contained more spatial details compared to traditional soil maps. ...
Soil salinization can decrease soil productivity and is a significant factor in causing land degradation. Precision mapping of salinization in agricultural fields would improve farmland management. This study focuses on the cropland in the Manas River Basin, located in the arid region of northwest China. It explores the potential of a soil mapping method, the Soil–Land Inference Model (SoLIM), which only requires a small number of soil samples to infer soil salinization of farmlands in arid areas. The model was utilized to create spatial distribution maps of soil salinity for the years 2009 and 2017, and changes in the distribution were analyzed. The research results indicate: (1) Through the analysis of sample point data, it was observed that soil salinity in the study area tends to accumulate in the surface layer (0–30 cm) in spring and in the subsoil layer (60–90 cm) during the crop growing season, with significant spatial variability. Therefore, it is necessary to conduct detailed salinity mapping. (2) Using field measurements as validation data, the simulation results of the SoLIM were compared with spatial interpolation methods and regression models. The SoLIM showed higher inference accuracy, with R2 values for the simulation results of the three soil layers all exceeding 0.5. (3) The SoLIM spatial inference showed salt accumulation in the northern part and desalination in the southern part. The findings of this study suggest that the SoLIM has the potential to effectively map soil salinization of croplands in arid areas, offering an efficient solution for monitoring soil salinity in arid oasis croplands.
... Traditionally, conventional soil maps (CSMs) and survey reports were utilized for the preparation and implementation of management strategies on agricultural soils (Tóth et al., 2018;Head et al., 2020). In Canada, these CSMs are available at a range of scales from 1:10,000 to 1:250,000 (Yang et al., 2011) and were produced by experienced soil surveyors. They contain general information on name of soil taxonomic units (soil order, great groups, series etc.), distribution and attributes (slope, drainage class, texture etc.) in polygon-based maps (Hole, 1978;Hole and Campbell, 1985). ...
... In the first two regions, the density of soil profile samples is high compared to the last (Fig. 1C). This was not expected, as studies related greater uncertainty in prediction to the smaller number of samples (Yang et al., 2011;Brungard et al., 2015;Li et al., 2016). In addition, the greater or lesser certainty in the classification may also be related to the complexity of the soil-landscape relationship and its representation through environmental covariates. ...
... These models assumed that soils within the same class had low variability and that the changes between classes were discrete, separated by polygon borders. Consequently, this type of map failed to reveal details about intrapolygonal variation within each class, leading to a lack of precision regarding soil attributes 15 . ...
Spatially explicit soil information is crucial for comprehending and managing many of Earth´s processes related to carbon, water, and other biogeochemical cycles. We introduced a gridded database of soil physical properties and hydraulic parameters at 100 meters spatial resolution. It covers the continental area of Chile and binational basins shared with Argentina for six standardized depths following the specifications of the GlobalSoilMap project. We generated soil maps based on digital soil mapping techniques based on more than 4000 observations, including unpublished data from remote areas. These maps were used as input for the pedotransfer function Rosetta V3 to obtain predictions of soil hydraulic properties, such as field capacity, permanent wilting point, total available water capacity, and other parameters of the water retention curve. The trained models outperformed several other DSM studies applied at the national and regional scale for soil physical properties (nRMSE ranging from 6.93% to 15.7%) and delivered acceptable predictions (nRMSE ranging from 10.4% to 15.6%) for soil hydraulic properties, making them suitable for countless environmental studies.
... Compared with traditional soil mapping, digital soil mapping (DSM) is cost effective and less time consuming, and the generated soil map is expressed by raster data, which can more accurately express the spatial variation of soil properties [29,30]. DSM is a soil survey and mapping method based on the soil-landscape hypothesis and spatial analysis and mathematical modeling [30]. ...
In the last 30 years, severe soil acidification has been found in China due to acid deposition and nitrogen fertilizer overuse. Understanding the spatial pattern and vertical variations in base saturation percentage (BSP) and exchangeable cations (Ca2+, Mg2+, K+, Na+, H+ and Al3+) can directly benefit fertilization management and ecological protection. Here, 1253 soil profiles were surveyed in tropical and subtropical regions in China to investigate the spatial variations in BSP and exchangeable cations at three soil depths of 0–20 cm, 20–50 cm and 50–100 cm. The spatial distributions were interpolated by using advanced machine learning techniques. We found that the exchangeable Ca2+ (Exch. Ca), Mg2+ (Exch. Mg) and BSP were significantly higher in paddy fields and uplands than in forests and gardens, regardless of soil depth, while the exchangeable K (Exch. K) did not significantly differ between various land-use types. The Exch. Ca and BSP in Anthrosols were significantly higher than those in Ferrosols, Argosols and Cambosols in the three soil layers. The spatial prediction results indicated that exchangeable cations and BSP were generally characterized by strong heterogeneity, and the Exch. Ca, Exch. K and exchangeable H+ (Exch. H) contents and BSP declined with increasing soil depth. This study helps us understand the spatial variation in BSP and exchangeable cations in the study area and benefits fertilization management and environmental protection.
... Some DSM approaches start from existing maps, which implicitly contain rich geopedological knowledge, and use digital methods to re ne or update them (e.g., Kempen et al. 2009;Yang et al. 2011), and even attempt to disaggregate existing maps to a ner scale, e.g., the DSMART approach (Odgers et al. 2014) used in the POLARIS gridded maps of the continental USA (Chaney et al. 2019). The SoLIM (Soil-Landscape Inference Model) approach (Zhu et al. 2001) reasons by analogy from known soil-landscape relations. ...
Much of current digital soil mapping (DSM) practice relies on terrain, climate and remote sensing-derived covariates. These are easy to obtain and can serve as proxies to soil forming factors and from these to soil properties or classes. However, mapping of soil bodies, not properties in isolation, is what gives insight into the soil landscape. A naïve attempt at correlating environmental covariates will not succeed in the presence of unmapped variations in parent material, soil bodies and landforms inherited from past environments. It also takes no account of spatial relations among soil bodies. Geopedology integrates an understanding of the geomorphic conditions under which soils evolve with field observations. Examples where simplistic DSM would fail but geopedology would succeed in mapping and, even better, explaining the soil distribution are shown: exhumed paleosols, low-relief depositional environments, inverted landscapes, and recent post-glacial landscapes.KeywordsGeomorphologyDigital soil mappingSoil-landscape relationsPleistocene glaciation
... In the first two regions, the density of soil profile samples is high compared to the last (Fig. 1C). This was not expected, as studies related greater uncertainty in prediction to the smaller number of samples (Yang et al., 2011;Brungard et al., 2015;Li et al., 2016). In addition, the greater or lesser certainty in the classification may also be related to the complexity of the soil-landscape relationship and its representation through environmental covariates. ...
