The distribution of heavy metals in agricultural soils is affected by various anthropogenic activities and environmental factors occurring at different spatial scales. This paper introduced the ...two-dimensional empirical mode decomposition (2D-EMD) to separate the spatial variability in soil heavy metals into different scales. Geostatistics and multivariate analysis were also utilized to quantify their spatial structure and identify their potential influencing factors. The study was conducted in an arable land in southeastern China where 260 surface soil samples were collected and measured for total contents of cadmium (Cd
total
), mercury (Hg
total
), and sulfur (TS); pH; and soil organic carbon content (SOC). The results showed that both Cd
total
and Hg
total
had high coefficients of variation. The overall variation in all five soil variables was separated into three intrinsic mode functions (IMFs) and spatial residues. All three IMFs had short-range spatial correlations (1–8 km), while the spatial residues had moderate–large spatial ranges (13–39 km). IMF1 of Cd
total
was strongly correlated with IMF1 of SOC and TS, which was consistent with the principal component analysis. This indicated that IMF1 of Cd
total
represented local variations which were influenced by agricultural activities. IMFs of Hg
total
showed clustered distributions in the study area, with IMF1 and IMF2 of Hg
total
correlated in one principal component, and IMF3 of Hg
total
and IMF3 of soil pH in another component. This indicated that all three IMFs of Hg
total
might be influenced by different industrial activities or different pathways of the same industrial activities. The residues of Cd
total
and Hg
total
, representing the regional trends, only accounted for 26% of the total variance, whereas IMF1 contributed about half of the total variance. It can be concluded that agricultural activities and industrial activities were the dominant contributors of the overall variations in Cd
total
and Hg
total
in the study area, respectively.
•Spiked-regional model is no better than local models.•Localized models can be derived using MBL algorithm.•Similar to transfer learning, a localized PLSR model is derived from regional ...model.•Localized models perform better than the spiked-regional model.•Spiking affects the regression coefficients, but not the loading of PLSR model.
An increasing number of soil spectral libraries are being developed at larger extents, including at national, continental, and global scales. However, the prediction accuracy of these libraries was often fairly poor when used on local scales. This study evaluates different strategies to improve the model accuracy of a regional spectral library for soil organic carbon prediction in four different local target areas. In total, five strategies using the Partial least squares regression (PLSR) were compared, including the use of local, spiked-regional, spiked-subset-regional and two localized models (memory based learning (MBL) and localized PLSR). MBL derives a new local prediction model based on a subset of the regional spectra similar to the new sample to be predicted. A localized PLSR calibrates a linear regression model using projected scores of the local samples derived from a pre-trained regional PLSR model. Validation results showed that the performances of the spiked models were not much better than those derived from the local and localized models. With >20 local samples, the localized PLSR model performed better than both the local and spiked-regional models. MBL model achieved similar performance to the localized PLSR model. Nevertheless, the accuracy of the models was heavily affected by both the spectral similarity of the data and the statistics of the predictand. Therefore, we recommend localizing the prediction models. Our results also suggest that spiking affected the regression coefficients of the PLSR models but not the loadings, which enabled the compression of spectra data into informative PLS scores. If the local spectra have low similarity to the regional spectral library, building a local spectral library would be more beneficial, assuming the sample size is large enough (>30).
Pedology and digital soil mapping (DSM) Ma, Yuxin; Minasny, Budiman; Malone, Brendan P. ...
European journal of soil science,
March 2019, 2019-03-00, 20190301, Letnik:
70, Številka:
2
Journal Article
Recenzirano
Pedology focuses on understanding soil genesis in the field and includes soil classification and mapping. Digital soil mapping (DSM) has evolved from traditional soil classification and mapping to ...the creation and population of spatial soil information systems by using field and laboratory observations coupled with environmental covariates. Pedological knowledge of soil distribution and processes can be useful for digital soil mapping. Conversely, digital soil mapping can bring new insights to pedogenesis, detailed information on vertical and lateral soil variation, and can generate research questions that were not considered in traditional pedology. This review highlights the relevance and synergy of pedology in soil spatial prediction through the expansion of pedological knowledge. We also discuss how DSM can support further advances in pedology through improved representation of spatial soil information. Some major findings of this review are as follows: (a) soil classes can be mapped accurately using DSM, (b) the occurrence and thickness of soil horizons, whole soil profiles and soil parent material can be predicted successfully with DSM techniques, (c) DSM can provide valuable information on pedogenic processes (e.g. addition, removal, transformation and translocation), (d) pedological knowledge can be incorporated into DSM, but DSM can also lead to the discovery of knowledge, and (e) there is the potential to use process‐based soil–landscape evolution modelling in DSM. Based on these findings, the combination of data‐driven and knowledge‐based methods promotes even greater interactions between pedology and DSM.
Highlights
Demonstrates relevance and synergy of pedology in soil spatial prediction, and links pedology and DSM.
Indicates the successful application of DSM in mapping soil classes, profiles, pedological features and processes.
Shows how DSM can help in forming new hypotheses and gaining new insights about soil and soil processes.
Combination of data‐driven and knowledge‐based methods recommended to promote greater interactions between DSM and pedology.
The application of machine learning (ML) techniques in various fields of science has increased rapidly, especially in the last 10 years. The increasing availability of soil data that can be ...efficiently acquired remotely and proximally, and freely available open-source algorithms, have led to an accelerated adoption of ML techniques to analyse soil data. Given the large number of publications, it is an impossible task to manually review all papers on the application of ML in soil science without narrowing down a narrative of ML application in a specific research question. This paper aims to provide a comprehensive review of the application of ML techniques in soil science aided by a ML algorithm (latent Dirichlet allocation) to find patterns in a large collection of text corpora. The objective is to gain insight into publications of ML applications in soil science and to discuss the research gaps in this topic. We found that (a) there is an increasing usage of ML methods in soil sciences, mostly concentrated in developed countries,
(b) the reviewed publications can be grouped into 12 topics, namely remote sensing, soil organic carbon, water, contamination, methods (ensembles), erosion and parent material, methods (NN, neural networks, SVM, support vector machines), spectroscopy, modelling (classes), crops, physical, and modelling (continuous),
and (c) advanced ML methods usually perform better than simpler approaches thanks to their capability to capture non-linear relationships.
From these findings, we found research gaps, in particular, about the precautions that should be taken (parsimony) to avoid overfitting, and that the interpretability of the ML models is an important aspect to consider when applying advanced ML methods in order to improve our knowledge and understanding of soil. We foresee that a large number of studies will focus on the latter topic.
Declines in soil multifunctionality (e.gsoil capacity to provide food and energy) are closely related to changes in the soil microbiome (e.g., diversity) Determining ecological drivers promoting such ...microbiome changes is critical knowledge for protecting soil functions. However, soil‐microbe interactions are highly variable within environmental gradients and may not be consistent across studies. Here we propose that analysis of community dissimilarity (β‐diversity) is a valuable tool for overviewing soil microbiome spatiotemporal changes. Indeed, β‐diversity studies at larger scales (modelling and mapping) simplify complex multivariate interactions and refine our understanding of ecological drivers by also giving the possibility of expanding the environmental scenarios. This study represents the first spatial investigation of β‐diversity in the soil microbiome of New South Wales (800,642 km2), Australia. We used metabarcoding soil data (16S rRNA and ITS genes) as exact sequence variants (ASVs) and UMAP (Uniform Manifold Approximation and Projection) as the distance metric. β‐Diversity maps (1000‐m resolution)—concordance correlations of 0.91–0.96 and 0.91–0.95 for bacteria and fungi, respectively—showed soil biome dissimilarities driven primarily by soil chemistry—pH and effective cation exchange capacity (ECEC)—and cycles of soil temperature—land surface temperature (LST‐phase and LST‐amplitude). Regionally, the spatial patterns of microbes parallel the distribution of soil classes (e.g., Vertosols) beyond spatial distances and rainfall, for example. Soil classes can be valuable discriminants for monitoring approaches, for example pedogenons and pedophenons. Ultimately, cultivated soils exhibited lower richness due to declines in rare microbes which might compromise soil functions over time.
Soil microbial communities directly affect soil functionality through their roles in the cycling of soil nutrients and carbon storage. Microbial communities vary substantially in space and time, ...between soil types and under different land management. The mechanisms that control the spatial distributions of soil microbes are largely unknown as we have not been able to adequately upscale a detailed analysis of the microbiome in a few grams of soil to that of a catchment, region or continent. Here we reveal that soil microbes along a 1000 km transect have unique spatial structures that are governed mainly by soil properties. The soil microbial community assessed using Phospholipid Fatty Acids showed a strong gradient along the latitude gradient across New South Wales, Australia. We found that soil properties contributed the most to the microbial distribution, while other environmental factors (e.g., temperature, elevation) showed lesser impact. Agricultural activities reduced the variation of the microbial communities, however, its influence was local and much less than the overall influence of soil properties. The ability to predict the soil and environmental factors that control microbial distribution will allow us to predict how future soil and environmental change will affect the spatial distribution of microbes.
Tropical peatland holds a large amount of carbon in the terrestrial ecosystem. Indonesia, responding to the global climate issues, has legislation on the protection and management of the peat ...ecosystem. However, this effort is hampered by the lack of fine-scale, accurate maps of peat distribution and its thickness. This paper presents an open digital mapping methodology, which utilises open data in an open-source computing environment, as a cost-effective method for mapping peat thickness and estimating carbon stock in Indonesian peatlands. The digital mapping methodology combines field observations with factors that are known to influence peat thickness distribution. These factors are represented by multi-source remotely-sensed data derived from open and freely available raster data: digital elevation models (DEM) from SRTM, geographical information, and radar images (Sentinel and ALOS PALSAR). Utilising machine-learning models from an open-source software, we derived spatial prediction functions and mapped peat thickness and its uncertainty at a grid resolution of 30m. Peat volume can be calculated from the thickness map, and based on measurements of bulk density and carbon content, carbon stock for the area was estimated. The uncertainty of the estimates was calculated using error propagation rules. We demonstrated this approach in the eastern part of Bengkalis Island in Riau Province, covering an area around 50,000ha. Results showed that digital mapping method can accurately predict the thickness of peat, explaining up to 98% of the variation of the data with a median relative error of 5% or an average error of 0.3m. The accuracy of this method depends on the number of field observations. We provided an estimate of the cost and time required for map production, i.e. 2 to 4months with a cost between $0.3 and $0.5/ha for an area of 50,000ha. Obviously, there is a tradeoff between cost and accuracy. The advantages and limitations of the method were further discussed. The methodology provides a blueprint for a national-scale peat mapping.
Display omitted
•A digital mapping methodology is proposed for mapping peat thickness in tropical peatlands.•Open digital mapping methodology utilises open data in an open-source computing environment.•Digital maps of peat thickness were used to derive peatland carbon stocks.•The method is scalable for national extent peat mapping.
Tropical peatlands are vital ecosystems that play an important role in global carbon storage and cycles. Current estimates of greenhouse gases from these peatlands are uncertain as emissions vary ...with environmental conditions. This study provides the first comprehensive analysis of managed and natural tropical peatland GHG fluxes: heterotrophic (i.e. soil respiration without roots), total CO2 respiration rates, CH4 and N2O fluxes. The study documents studies that measure GHG fluxes from the soil (n = 372) from various land uses, groundwater levels and environmental conditions. We found that total soil respiration was larger in managed peat ecosystems (median = 52.3 Mg CO2 ha−1 year−1) than in natural forest (median = 35.9 Mg CO2 ha−1 year−1). Groundwater level had a stronger effect on soil CO2 emission than land use. Every 100 mm drop of groundwater level caused an increase of 5.1 and 3.7 Mg CO2 ha−1 year−1 for plantation and cropping land use, respectively. Where groundwater is deep (≥0.5 m), heterotrophic respiration constituted 84% of the total emissions. N2O emissions were significantly larger at deeper groundwater levels, where every drop in 100 mm of groundwater level resulted in an exponential emission increase (exp(0.7) kg N ha−1 year−1). Deeper groundwater levels induced high N2O emissions, which constitute about 15% of total GHG emissions. CH4 emissions were large where groundwater is shallow; however, they were substantially smaller than other GHG emissions. When compared to temperate and boreal peatland soils, tropical peatlands had, on average, double the CO2 emissions. Surprisingly, the CO2 emission rates in tropical peatlands were in the same magnitude as tropical mineral soils. This comprehensive analysis provides a great understanding of the GHG dynamics within tropical peat soils that can be used as a guide for policymakers to create suitable programmes to manage the sustainability of peatlands effectively.
We compiled the first comprehensive analysis of managed and natural tropical peatland GHG fluxes. Groundwater level had a stronger effect on soil CO2, N2O and CH4 emissions. Draining peatlands induced high CO2 and N2O emissions.
Microorganisms play pivotal roles in soil processes. Metabolically related microorganisms constitute functional groups, and diverse microbial functional groups control nutrient cycling in soils. This ...study explored environmental (i.e., rainfall, temperature) and soil factors driving the distribution of bacterial functional groups involved in soil carbon (C) cycling in paired natural and agricultural ecosystems. Soil samples were collected at a regional scale covering gradients of temperature and rainfall across two orthogonal transects (~1000 km) in New South Wales, Australia. Putative functions of bacteria were linked to two soil C fractions: particulate organic carbon (POC) and mineral‐associated organic carbon (MAOC). We found: (i) temperature and rainfall were important drivers of bacterial functional groups, while soil properties, such as pH, soil C and nitrogen (N), also presented significant contributions; (ii) community structure of bacteria involved in C cycling was mainly related to POC content but not to MAOC; (iii) paired sampling showed that agricultural practices had significant impacts on the composition and responses of soil bacterial functional groups. This study demonstrated the environmental regulation (e.g., temperature and rainfall) of soil microbial functional groups at large scales, which was altered by agricultural practices.
Highlights
Soil bacteria involved in C cycling were investigated across two ~1000 km transects.
Temperature and rainfall were important drivers of bacterial functional groups at large scale.
Paired sampling showed that agriculture led to a significant shift in bacterial functional groups.
Community structure of bacterial functional groups were correlated with soil POC but not MAOC.
Soil, through its various functions, plays a vital role in the Earth's ecosystems and provides multiple ecosystem services to humanity. Pedotransfer functions (PTFs) are simple to complex knowledge ...rules that relate available soil information to soil properties and variables that are needed to parameterize soil processes. In this paper, we review the existing PTFs and document the new generation of PTFs developed in the different disciplines of Earth system science. To meet the methodological challenges for a successful application in Earth system modeling, we emphasize that PTF development has to go hand in hand with suitable extrapolation and upscaling techniques such that the PTFs correctly represent the spatial heterogeneity of soils. PTFs should encompass the variability of the estimated soil property or process, in such a way that the estimation of parameters allows for validation and can also confidently provide for extrapolation and upscaling purposes capturing the spatial variation in soils. Most actively pursued recent developments are related to parameterizations of solute transport, heat exchange, soil respiration, and organic carbon content, root density, and vegetation water uptake. Further challenges are to be addressed in parameterization of soil erosivity and land use change impacts at multiple scales. We argue that a comprehensive set of PTFs can be applied throughout a wide range of disciplines of Earth system science, with emphasis on land surface models. Novel sensing techniques provide a true breakthrough for this, yet further improvements are necessary for methods to deal with uncertainty and to validate applications at global scale.
Plain Language Summary
For the application of pedotransfer functions in current Earth system models, and specifically for the different fluxes of water, solutes, and gas between soil and atmosphere, subject of the land surface models, recent developments of knowledge are entered in a new generation of pedotransfer functions. Methods for development and evaluation of pedotransfer functions are described in this comprehensive review, and perspectives for future developments in different Earth system science disciplines are presented. Challenges are still present for the application in some extreme environments of the Earth. We argue that a comprehensive set of pedotransfer functions can be applied throughout a wide range of disciplines of Earth system science, with emphasis on land surface models. Even though methodological challenges are still present for extrapolation and scaling, as outlined, integration and validation in global‐scale models is an achievable goal.
Key Points
Methods for development and evaluation of pedotransfer functions are described, and perspectives in different Earth system science disciplines presented
Novel applications are present for the different fluxes of water, solutes, and gas between soil and atmosphere, subject of the land surface models
Methodological challenges are still present for extrapolation and scaling, but integration and validation in global‐scale models is an achievable goal