Digital Soil Assessment Research Articles

Spatio Prediction of Soil Capability Modeled with Modified RVFL Using Aptenodytes Forsteri Optimization and Digital Soil Assessment Technique

To meet the needs of Egypt’s rising population, more land must be cultivated. Land evaluation is vital to achieving sustainable agricultural production. To determine the soil capability in the northeast Nile Delta region of Egypt, the present study introduces a new form of integration between the Agriculture Land Evaluation System (ALES Arid) model and the machine learning (ML) approach. The soil capability indicators required for the ALES Arid model were determined for the 47 collected soil profiles covering the study area. These indicators include soil pH, soil salinity, the sodium adsorption ratio (SAR), the exchangeable sodium percentage (ESP), the organic matter (OM) content, the calcium carbonate (CaCO3) content, the gypsum content, the clay percentage, and the slope. The ALES Arid model was run using these indicators, and soil capability indexes were obtained. Using GIS, these indexes helped to classify the study area into four capability classes, ranging from good to very poor soils. To predict the soil capability, three machine learning algorithms named traditional RVFL, sine cosine algorithm (SCA), and AFO were also applied to the same soil criteria. The developed ML method aims to enhance the prediction of soil capability. This method depends on improving the performance of Random Vector Functional Link (RVFL) using an optimization technique named Aptenodytes Forsteri Optimization (AFO). The operators of AFO were used to determine the best parameters of RVFL since traditional RVFL is sensitive to parameters. To assess the performance of the developed AFO-RVFL method, a set of real collected data was used. The experimental results illustrate the high efficacy of AFO-RVFL in the spatial prediction of soil capability. The correlations found in this study are critical for understanding the overall techniques for predicting soil capability.

Digital soil assessment in support of a soil information system for monitoring salinization and sodification in agricultural areas

AbstractSalinization and sodification are types of degradation associated with the accumulation of salts and alkaline materials in the soil. They gradually advance unnoticed till severe degradation appears if not properly controlled. Relevant soil information is not routinely kept by many countries thus contributing to their advancement particularly in agricultural areas where their impacts have huge consequences on food security. We developed a 3‐step protocol to detect salinization and sodification advancement at different spatial scales and support soil information system development. The first step establishes an indicator database focusing on measured soil Electrical Conductivity (EC), pH, Exchangeable Sodium Percent (ESP), and a suit of environmental covariates. The second step outlines data harmonization strategies and classification of salinization and sodification problems. It also incorporates digital soil mapping for spatial information on salinization or sodification. The third step has time‐series modelling of salinization and sodification using mixed‐effects approach to improve hotspot detection in agricultural areas. The protocol was tested in Afghanistan, Sudan, and Lesotho using time‐series data between 2001 and 2018. It successfully identified salt and soda accumulation at different soil depths with more than 80% accuracy on holdout samples. In Sudan and Afghanistan, it identified topsoils as more prone to salinization than the subsoils and consequently depicted more salt accumulation in topsoils than subsoils in agricultural areas. In Lesotho, it identified emerging subsoil sodification. The protocol has potential for supporting the development of soil information on salinization and sodification which is currently lacking at many national and regional levels.

Digital soil assessment of soil fertility for Thai jasmine rice in the Thung Kula Ronghai region, Thailand

Digital soil assessment (DSA) is an application for the interpretation of digital soil mapping (DSM) outputs for evaluating soil and related environmental factors. However, DSA has not been widely applied to assess soil fertility in the humid tropics due to the complexity of integrating numerous soil chemical properties into one map. In this study, principal component analysis was applied to extract the most appropriate soil indicator for crop production. A digital map of soil fertility for jasmine rice was created using a multiple linear regression (MLR) model. Finally, the digital map was confirmed by comparing it with actual rice yield in the Thung Kula Ronghai (TKR) region of Thailand. The calculated soil fertility was significantly expressed by soil pH, electrical conductivity, organic matter, and contents of macronutrients (P, K, Ca, and Mg). The obtained MLR model for this region’s soil fertility consisted of spectral indices (brightness, coloration, normalized difference water, and moisture stress) and topographic indices (slope and topographic wetness). The digital map indicated that more than half of the TKR region contained “very low” to “low” soil fertility. The soil fertility map fits well to actual rice production in the TKR region.

Evaluating the impact of using digital soil mapping products as input for spatializing a crop model: The case of drainage and maize yield simulated by STICS in the Berambadi catchment (India)

Digital Soil Mapping (DSM) can be an alternative data source for spatializing crop models over large areas. The objective of the paper was to evaluate the impact of DSM products and their uncertainties on a crop model’s outputs in an 80 km2 catchment in south India. We used a crop model called STICS and evaluated two essential soil functions: the biomass production (through simulated yield) and water regulation (via calculated drainage). The simulation was conducted at 217 sites using soil parameters obtained from a DSM approach using either Random Forest or Random Forest Kriging. We first analysed the individual STICS simulations, i.e., at two cropping seasons for 14 individual years, and then pooled the simulations across years, per site and crop season. The results show that i) DSM products outperformed a classical soil map in providing spatial estimates of STICS soil parameters, ii) although each soil parameters were estimated separately, the correlations between soil parameters were globally preserved, ii) Errors on STICS’ yearly outputs induced by DSM estimations of soil parameters were globally low but were important for the few years with high impacts of soil variations, iii) The statistics of the STICS simulations across years were also affected by DSM errors with the same order of magnitude as the errors on soil inputs and iv) The impact of DSM errors was variable across the studied soil parameters. These results demonstrated that coupling DSM with a crop model could be a better alternative to the classical Digital Soil Assessment techniques. As such, it will deserve more work in the future.

Spatio-Temporal Analysis of Heavy Metals in Arid Soils at the Catchment Scale Using Digital Soil Assessment and a Random Forest Model

Predicting the spatio-temporal distribution of absorbable heavy metals in soil is needed to identify the potential contaminant sources and develop appropriate management plans to control these hazardous pollutants. Therefore, our aim was to develop a model to predict soil adsorbable heavy metals in arid regions of Iran from 1986 to 2016. Soil adsorbable heavy metals were measured in 201 samples from locations selected using the Latin hypercube sampling method in 2016. A random forest (RF) model was used to determine the relationship between a suite of geospatial predictors derived from remote sensing and digital elevation model data with georeferenced measurements of soil absorbable heavy metals. The trained RF model from 2016 was used to reconstruct the spatial distribution of soil absorbable heavy metals at three historical timesteps (1986, 1999, and 2010). Results indicated that the RF model was effective at predicting the distribution of heavy metals with coefficients of determination of 0.53, 0.59, 0.41, 0.45, and 0.60 for Fe, Mn, Ni, Pb, and Zn, respectively. The predicted maps showed high spatio-temporal variability; for example, there were substantial increases in Pb (the 1.5–2 mg/kg−1 class) where its distribution increased by ~25% from 1988 to 2016—similar trends were observed for the other heavy metals. This study provides insights into the spatio-temporal trends and the potential causes of soil heavy metal contamination to facilitate appropriate planning and management strategies to prevent, control, and reduce the impact of heavy metal contamination in soils.

Land Use and Soil Organic Carbon Stocks—Change Detection over Time Using Digital Soil Assessment: A Case Study from Kamyaran Region, Iran (1988–2018)

Land use change and soil organic carbon stock (SOCS) depletion over time is one of the predominant worldwide environmental problems related to global warming and the need to secure food production for an increasing world population. In our research, satellite images from 1988 and 2018 were analyzed for a 177.48 km2 region in Kurdistan Province, Iran. Across the study area. 186 disturbed and undisturbed soil samples were collected at two depths (0–20 cm and 20–50 cm). Bulk density (BD), soil organic carbon (SOC), rock fragments (RockF) and SOCS were measured. Random forest was used to model the spatial variability of SOCS. Land use was mapped with supervised classification and maximum likelihood approaches. The Kappa index and overall accuracy of the supervised classification and maximum likelihood land use maps varied between 83% and 88% and 78% and 85%, respectively. The area of forest and high-quality rangeland covered 5286 ha in 1988 and decreased by almost 30% by 2018. Most of the decrease was due to the establishment of cropland and orchards, and due to overgrazing of high-quality rangeland. As expected, the results of the analysis of variance showed that mean values of SOCS for the high-quality rangeland and forest were significantly higher compared to other land use classes. Thus, transformation of land with natural vegetation like forest and high-quality rangeland led to a loss of 15,494 Mg C in the topsoil, 15,475 Mg C in the subsoil and 15,489 Mg C−1 in total. We concluded that the predominant causes of natural vegetation degradation in the study area were mostly due to the increasing need for food, anthropogenic activities such as cultivation and over grazing, lack of government landuse legislation and the results of this study are useful for land use monitoring, decision making, natural vegetation planning and other areas of research and development in Kurdistan province.

Spatio-temporal dynamic of soil quality in the central Iranian desert modeled with machine learning and digital soil assessment techniques

Soil degradation reduces soil quality by a loss of organic matter, reduced soil fertility, and structural breakdown, erosion, undesirable changes in salinity, acidity or alkalinity and the effects of toxic chemicals, contaminants or excessive flooding. In this study, we investigated spatial and temporal changes of soil quality between 1986 and 2030 in the Central Iranian desert. 201 topsoil samples (0–20 cm) in Yazd-Ardakan plain of Iran were chosen with conditioned Latin hypercube sampling strategy and analysed for soil organic carbon, electrical conductivity, dry bulk density, aggregate stability, and soil heavy metals. A soil quality index was calculated using weighted index method. To predict the spatial distribution of the soil quality index, we implemented a random forest model based on a set of covariates with a coefficient of determination of 0.69 between soil quality index and covariates. The results of soil quality index changes from 1986 to 2030 show that during this period, the areal extent of the Very Low SQI Class (<0.4) increased by 78,242 ha (increase of 16.2%), while the extent of the Good SQI Class (>0.6) decreased by 366,018 ha (decrease of 75.8%). This indicates that the soil quality in the study area, over time, is progressively becoming poorer. The results of the study of soil quality changes can be used in land evaluation, environmental studies and integrated planning and management in order to properly and reasonably utilize natural resources and reduce future soil degradation.

Digital soil assessment delivers impact across scales in Australia and the Philippines

Retrospective evaluation has consistently shown that soil information has value beyond the investment used to produce it. Digital soil mapping and assessment (DSMA) is the new paradigm for soil survey and a key source of soil and land information. It promises increased utility and flexibility for the users of soil information. Does DSMA methodology add value? What are some of the outcomes and emerging impacts? Seven examples from the burgeoning use of DSMA in and near Australia have been explored to determine the nature and extent of outcomes and impact achieved. The analysis began with a workshop of key soil scientists, involved a survey of the use of DSMA and attitudes to impact amongst practitioners of DSMA and looked at each of the seven examples in the context of the systems they seek to influence. There is evidence of progress along impact pathways in each case. In the simpler systems, the products of DSMA are being used as envisaged and change is occurring. In more complex systems, the role of soil information meshes with many other influences and impact is harder to discern. Importantly, we find that few practitioners using DSMA explicitly identify impact pathways and design projects at the outset to optimise the chance of more extensive impact. Thus, an approach to planning for impact in DSMA is proposed that could improve the chance of impact and allow for iteration as our understanding of the systems in which change is expected improves through our interaction with them.

Составление интерактивных электронных почвенных карт и карт экологической оценки почв Азербайджана на основе географических информационных систем

On the basis of the GIS software, an electronic map platform has been created covering the entire territory of the Republic of Azerbaijan, which supports an interactive update mode. This map covers the entire scale of the spectrum and meets the requirements of e-agriculture and other public information systems, which are based on the use of data space. For conducting soil, agrochemical and interdisciplinary research on the platform, a method of plastic relief was developed. A detailed methodology for compiling digital soil and ecological soil assessment maps using 3D visualization has also been prepared.

A preliminary soil security assessment of agricultural land in middle‐eastern China

AbstractSustainable management of agricultural land requires not only an accurate assessment of the biophysical status of the soil but also estimates of the social and economic aspects of the soil. This paper focuses on soil security mapping of an approximately 80 000 km2 agricultural area in middle‐eastern China. We examined a digital soil assessment framework in mapping soil security and its five dimensions (capability, condition, capital, connectivity and codification) using digital soil maps and environmental variables. The main objective is to improve the understanding of soil protection in agricultural practices. Soil and environmental variables were coded as indicator values based on their functions, and three averaging models were used to integrate the indicators for soil security mapping. Results show that agricultural land in the study area currently has a high potential to achieve the crop production function, while there is still lack of sufficient social connectivity. Most of agricultural land has been properly protected by the public policy. More than half of the agricultural land has high security for cropping, while there is no unsecured soil. In general, most of the agricultural lands have already been well developed for cropping. The low soil security mainly contributes to the lack of proper connection to the soil. The findings suggest that digital soil security assessment is highly recommended for guiding sustainable development of agricultural land, because it could provide the knowledge of factors affecting soil security from complex multifaceted dimensions, and potential solutions to make agriculture soil more secure.

Digital soil assessment for quantifying soil constraints to crop production: a case study for rice in Punjab, India

AbstractAssessments of land capability for particular functions such as food production need to allow for uncertainties both in the criteria used to specify the function and in information on relevant soil properties. In this paper, we evaluate the use of digital soil assessment (DSA) for dynamic assessment of soil capability allowing for both uncertainties and spatial variability in soil properties and flexibility in the values of assessment criteria. We do this for soil constraints to rice production in the state of Punjab, India, where soil salinity and alkalinity are potentially important constraints to cropping. In DSA, spatial predictions of soil properties and associated uncertainties made with digital soil mapping (DSM) are used to assess soil functions. We use a combination of DSM and Monte Carlo simulation methods to estimate the spatial variation in soil electrical conductivity (ECe) and pH to 20 cm depth in soils across Punjab. We then use the estimates and associated uncertainties to assess the likelihood that soil salinity or alkalinity or both could constrain rice production. Results show that allowing for prediction uncertainties of soil attributes results in far smaller areas affected by salinity (1.2 vs. 2.0 Mha) and alkalinity (3.0 vs. 3.2 Mha). Results also show the importance of correctly setting threshold values for constraint criteria and the flexibility of the DSA approach for setting thresholds.

Digital soil assessment of agricultural suitability, versatility and capital in Tasmania, Australia

Digital soil assessment (DSA) is the application of interpretations to digital soil mapping (DSM). Since 2010, an operational DSA program has been underway in Tasmania, Australia, primarily for the assessment of agricultural land suitability for 20 different crops in newly commissioned irrigation schemes. This involves development of functional soil attribute and climate grids, initially undertaken in two pilot areas totalling 70,000ha, with comprehensive soil sampling and temperature sensor networks. Through the Tasmanian State Government ‘Water for Profit Program’, this pilot land resource assessment has become operational and applied to the entire State (68,401km2), covering a total of 19 irrigation schemes. Using a combination of newly collected and legacy soil data and a suite of spatial explanatory covariates, a total of 218 80m resolution 3D soil attribute grids were produced using the digital mapping approach, together with quantified prediction uncertainties. These grids have contributed to the ‘Soil and Landscape Grid of Australia’ and the ‘GlobalSoilMap’ projects. Using a similar approach, functional climate grids were generated for chill-hours, growing degree-days and frost risk. The digital soil and climate grids were applied to pre-defined enterprise suitability rulesets to produce 20 different maps of enterprise suitability, including opium poppies, and a range of perennial horticultural, cereal and vegetable crops, uploaded to a publically accessible spatial internet portal (Land Information Services Tasmania; LISTmap), which includes functionality to identify soil and climate limitations, as an indication of potential land management inputs. The suitability surfaces provide a regional indication of potential areas to expand or diversify into a range of cropping enterprises. However, some informative supplementary products were also developed to provide an overall spatial guide to the more versatile agricultural areas. This included an enterprise versatility index (by combining all suitability surfaces to identify areas more suited to more enterprises); and application of individual commodity ‘financial gross-margins’ to identify the highest-valued agricultural land in terms of earning potential. These products demonstrate the utility of functional soil property grids and the collective capacity of DSA to answer questions of agricultural potential; this can ensure the appropriate land is targeted for appropriate uses to stimulate agricultural markets and maintain food security.

Review of Soil Water Retention Characteristic (SWRC) Models between Saturation and Oven Dryness

Soil water retention characteristic is the key soil property used in many applications in the fields of irrigation, hydrology, geotechnical engineering and soil science in general. Since the advent of digital soil mapping and digital soil assessment paradigms, there has been an upsurge of development of soil inference models and the need to increase accurate application of soil mapping products. All soils can be partially saturated with water and also near oven dryness. Therefore, constitutive models for soils should ideally represent the soil behaviour over entire range. This paper reviewed commonly used SWRC models. In order to stem potential for biasness, the models were grouped into three categories depending on the number of fitting parameters, namely, five-parameter, four-parameter and three-parameter categories. The evaluation used correlation and residual standard error statistics to choose the best overall performing model and in each category. Its results serve as a guide for selecting the models to be preferred for fitting SWRC in case there are limitations to the number of suction potential levels in the measured data.

Digital mapping of a soil drainage index for irrigated enterprise suitability in Tasmania, Australia

An operational Digital Soil Assessment was developed to inform land suitability modelling in newly commissioned irrigation schemes in Tasmania, Australia. The Land Suitability model uses various soil parameters, along with other climate and terrain surfaces, to identify suitable areas for various agricultural enterprises for a combined 70 000-ha pilot project area in the Meander and Midlands Regions of Tasmania. An integral consideration for irrigable suitability is soil drainage. Quantitative measurement and mapping can be resource-intensive in time and associated costs, whereas more ‘traditional’ mapping approaches can be generalised, lacking the detail required for statistically validated products. The project was not sufficiently resourced to undertake replicated field-drainage measurements and relied on expert field drainage estimates at ~930 sites (260 of these for independent validation) to spatially predict soil drainage for both areas using various terrain-based and remotely sensed covariates, using three approaches: (a) decision tree spatial modelling of discrete drainage classes; (b) regression-tree spatial modelling of a continuous drainage index; (c) regression kriging (random-forests with residual-kriging) spatial modelling of a continuous drainage index. Method b was chosen as the best approach in terms of interpretation, and model training and validation, with a concordance coefficient of 0.86 and 0.57, respectively. A classified soil drainage map produced from the ‘index’ showed good agreement, with a linearly weighted kappa coefficient of 0.72 for training, and 0.37 for validation. The index mapping was incorporated into the overall land suitability model and proved an important consideration for the suitability of most enterprises.

Application of fuzzy logic to Boolean models for digital soil assessment

Boolean models based on expert knowledge are often used to classify soils into a limited number of classes of a difficult-to-measure soil attribute. Although the primary data used for these classifications contain information on whether the soil is a typical class member or a boundary case between two classes, this is not retained in the final result. Such information is relevant in land use planning and soil management as it enables more flexible decision taking, but in the pre-digital era it was unfeasible to prevent the loss of it. We can now retain this information by fuzzifying the Boolean model using fuzzy logic. Choices must then be made on the type of membership function, logical operators, and formulation of the assessment rules. From a review of the main types of membership functions we conclude that piecewise linear functions are most appropriate in practical applications. Combinations of different fuzzy union ( or) and intersection ( and) connectives were tested on a 2-dimensional example. Nearly all combinations gave results that partly contradict the associated a priori knowledge, the exception being the Bounded sum connective for or, and the Product connective for and. We also found that in formulating the rules, overlap of predictor classes and negation should be avoided. Unrestricted choice of fuzzy connectives and rule formulation will generally lead to inconsistencies. The selected methods were tested in two case studies: one on suitability for seed-potatoes in an Italian region and one on suitability for grass farming in a Dutch region. The maps produced with the fuzzy and Boolean models are broadly similar. However, maps from the fuzzy models indicate that some areas represent a transition between two original Boolean classes, thereby providing relevant additional information. In the case study on seed-potatoes the quantitative prediction errors of the original Boolean suitability map were greatly reduced by the fuzzification.

On digital soil assessment with models and the Pedometrics agenda

The unique selling point of pedometricians still is close to their cradle: ability to map. Irrespective of the many scientific achievements one can ask if offering mapping ability, allbeit in various contexts, is all a pedometrician can do to bring forward soil science's broader agenda. This paper identifies, within some of the hotter issues on the soil science agenda, activities that need the input of pedometricians. Digital soil mapping (DSM) has reached maturity although some issues like the optimal use of legacy data still need attention. The necessary shift from DSM to digital soil function mapping implies an increased need for process knowledge in mapping, but also an increased focus of pedometricians on the strengthening of process models. Most quality issues related to DSM have a counterpart in process modelling, and some of these issues need elaboration to construct well-calibrated and complete models, e.g. by making motivated choices between the inclusion of processes or model reduction. Reaching out to stakeholders is also an issue of increasing interest, as these are confronted with uncertain concurrent models to evaluate future scenarios. Questions are raised such as: Does the need for a state-of-the-art (SOTA) approach imply a choice for one model and how should this be made, or is SOTA implementable as some weighted average of screened concurrent models. Can observations and model results be combined in decision making and what techniques are needed. The above issues are illustrated with existing examples and new material from soil science and beyond. As DSM and process modelling share common ground, mutual benefits can be expected at the interface of both research fields such as (i) increased usage of process knowledge in DSM and (ii) probabilistic approaches to less well understood soil processes. Stakeholders will profit from the development of decision frameworks to choose applicable DSM-techniques and the increased application of ensembles of DSM-methods and models to narrow prediction error bandwidths. Additionally, they will profit from the development of decision support systems filled with outcomes of scenario studies of multiple, uncertain, and concurrent models as these provide an interesting alternative to the application of one selected model.

Digital soil assessments: Beyond DSM

Over the last 10 years Digital Soil Mapping (DSM) has emerged as a credible alternative to traditional soil mapping. However, DSM should not be seen as an end in itself, but rather as a technique for providing data and information for a new framework for soil assessment which we call Digital Soil Assessment (DSA). Although still somewhat fluid, a procedural framework for DSM and DSA with its links and feedbacks is set out diagrammatically and discussed. A significant advantage inter alia of DSM over conventional methods in this context is the intended provision of estimates of predictor uncertainties. DSA comprises three main processes: (1) soil attribute space inference, (2) evaluation of soil functions and the threats to soils, and (3) risk assessment and the development of strategies for soil protection. Digital Soil Risk Assessment (DSRA) consists of integrating political, social, economical parameters and general environmental threats to DSA outputs for building, modelling and testing some scenarios about environmental perspectives. The procedure as a whole is illustrated using an example.