Soil Survey Maps Research Articles

Soil landscapes of the United States (SOLUS): Developing predictive soil property maps of the conterminous United States using hybrid training sets

AbstractDetailed soil property maps are increasingly important for land management decisions and environmental modeling. The US Soil Survey is investing in production of the Soil Landscapes of the United States (SOLUS), a new set of national predictive soil property maps. This paper documents initial 100‐m resolution maps of 20 soil properties that include various textural fractions, physical parameters, chemical parameters, carbon, and depth to restrictions. Many of these properties have not been previously mapped at this resolution. A hybrid training strategy helped increase training data by roughly 10‐fold over previous similar studies by combining commonly used laboratory data with underutilized field descriptions tied to soil survey map unit component property estimates (to help represent within polygon variability) as well as randomly selected soil survey map unit weighted average property estimates. Relative prediction intervals were used to help select which training data sources improved model performance. Conventional and spatial cross‐validation strategies yielded generally strong coefficients of determination between 0.5 and 0.7, but with substantial variability and outliers among the various properties, types of training data, and depths. Internal review of the maps highlighted both strengths and weaknesses of the maps, but most of the critical comments were in areas with high model uncertainty that can be used to guide future improvements. Generally, previously glaciated areas and complex large alluvial basins were harder to model. The new SOLUS 100‐m maps will be updated in the future to address identified issues and feedback as users interact with the data.

Soil Survey Mapping and Classification of Engiz Sub Basin Soils

Bu çalışma, Samsun ili Ondokuzmayıs ilçesi arazisinin Aşağı Engiz Alt Havzası’nın detaylı toprak etüd haritalarının ve toprak sınıflarının belirlenmesi amacıyla yapılmıştır. Çalışma alanı, 4590000-4598000 K, 250000-258000 E (WGS-84, Zone37, UTMm) koordinatlarında yer almaktadır. 2021 yılı Temmuz ayında gerçekleştirilen çalışmanın alanı 4758 hektardır. Yıllık ortalama sıcaklık 13.8 °C ve toplam yıllık yağış miktarı 717.5 mm'dir. Alanın topoğrafya, jeoloji ve jeomorfik haritaları ve arazi gözlemleri incelenerek araştırma alanında 6 adet toprak profili açılmıştır. Yapılan analizler ve arazi gözlemlerinden elde edilen sonuçlar değerlendirilerek 6 farklı toprak serisi tanımlanmıştır. Düzköy, Dağköy, Çepinler, Esenyer, Ballıca ve Yukarıengiz serileri sırayla Toprak Taksonomisine göre Vertic Dystrustept, Vertic Haplustepts, Lithic Orthent, Lithic Orthent, Typic Ustifluvents ve Calcic Haplusterts; FAO/WRB’ye göre ise sırayla Dystric Vertic Cambisol, Colluvic Vertic Cambisol, Lithic Leptosol, Lithic Leptosol, Clayic Fulvisol ve Calcic Vertisol olarak belirlenmiştir. Araştırma alanında % 24.54 ile Ballıca serisi en fazla alana sahip iken, % 1.45 ile Esenyer serisi en az alana sahiptir. Çalışma alanından elde edilen sayısal toprak veri tabanı, sürdürülebilir arazi kullanımı ve doğal kaynakların korumasına yönelik yapılacak projelerde altlık olarak kullanılmasına olanak sağlanılmıştır.

Quaternary Geology of the Washington-Jasper Area

"Quaternary Geology of the Washington-Jasper Area" was created to present basic quaternary geologic information that contributes to the characterization of potential aggregate resources, characterization of bedrock aquifer systems, and analysis of the overlying predominantly glacial deposits. This map is based on data compiled from project field observations and project exploratory borings, complemented with IGWS cartographic (e.g., Gray, 1989) and archive borehole data, select Indiana Department of Natural Resources water well logs, and United States Department of Agriculture soil survey maps. Expert knowledge of fluvial, glacifluvial and ice-marginal environments was used to draw contacts between units. This geologic map was funded in part through the STATEMAP program supported by the U.S. Geological Survey under Cooperative Agreement No. G21AC10646. "Quaternary Geology of the Washington-Jasper Area" is a composite geodata set that conforms to "GeMS (Geologic Map Schema)--a standard format for the digital publication of geologic maps," available at http://ngmdb.usgs.gov/Info/standards/GeMS/. Metadata records associated with each element within the geodata set contain more detailed descriptions of their purposes, constituent entities, and attributes. An OPEN shapefile version of the data set is also available. It consists of shapefiles, DBF files, and delimited text files and retains all information in the native geodatabase, but some programming will likely be necessary to assemble these components into usable formats.

Development of Hungarian spectral library: Prediction of soil properties and applications

Updating soil information systems (SIS) requires advanced technologies to support the time and cost-effective and environment-friendly soil data. The use of mid- infrared (MIR) Spectroscopy as alternative to wet chemistry has been tested. The MIR spectral library is a useful technique for predicting soil attributes with high accuracy, efficiency, and low cost. The Hungarian MIR spectral library contained data on 2200 soil samples from 10 counties representing the first Soil Information and Mentoring System (SIMS) survey. Archived soil samples were prepared and scanned based on Diffuse Reflectance Infrared spectroscopy (DRIFT) technique and spectra data were saved in the fourier transform infrared (FTIR) spectrometer OPUS software. Preprocessed filtering methods, outlier detection methods and calibration sample selection methods were applied for spectral library. MIR calibration models were built for soil attributes using Partial Least Square Regression (PLSR) method. Coefficient determination (R2), The Root Mean Squared Error (RMSE) and Ratio of Performance to Deviation (RPD) were used to assess the goodness of calibration and validation models. MIR spectral library had the ability to significantly estimate soil properties such as SOC, CaCO3, sand, clay and silt through various scale models (national, county and soil type). The findings showed that our spectral library soil estimations are precise enough to provide information on national, county and soil type levels enabling a wide range of soil applications that demand huge amounts of data such as soil survey, precision agriculture and digital soil mapping.

Digital Mapping of Soil Organic Carbon Based on Machine Learning and Regression Kriging.

In the last two decades, machine learning (ML) methods have been widely used in digital soil mapping (DSM), but the regression kriging (RK) model which combines the advantages of the ML and kriging methods has rarely been used in DSM. In addition, due to the limitation of a single-model structure, many ML methods have poor prediction accuracy in undulating terrain areas. In this study, we collected the SOC content of 115 soil samples in a hilly farming area with continuous undulating terrain. According to the theory of soil-forming factors in pedogenesis, we selected 10 topographic indices, 7 vegetation indices, and 2 soil indices as environmental covariates, and according to the law of geographical similarity, we used ML and RK methods to mine the relationship between SOC and environmental covariates to predict the SOC content. Four ensemble models-random forest (RF), Cubist, stochastic gradient boosting (SGB), and Bayesian regularized neural networks (BRNNs)-were used to fit the trend of SOC content, and the simple kriging (SK) method was used to interpolate the residuals of the ensemble models, and then the SOC and residual were superimposed to obtain the RK prediction result. Moreover, the 115 samples were divided into calibration and validation sets at a ratio of 80%, and the tenfold cross-validation method was used to fit the optimal parameters of the model. From the results of four ensemble models: RF performed best in the calibration set (R2c = 0.834) but poorly in the validation set (R2v = 0.362); Cubist had good accuracy and stability in both the calibration and validation sets (R2c = 0.693 and R2v = 0.445); SGB performed poorly (R2c = 0.430 and R2v = 0.336); and BRNN had the lowest accuracy (R2c = 0.323 and R2v = 0.282). The results showed that the R2 of the four RK models in the validation set were 0.718, 0.674, 0.724, and 0.625, respectively. Compared with the ensemble models without superimposed residuals, the prediction accuracy was improved by 0.356, 0.229, 0.388, and 0.343, respectively. In conclusion, Cubist has high prediction accuracy and generalization ability in areas with complex topography, and the RK model can make full use of trends and spatial structural factors that are not easy to mine by ML models, which can effectively improve the prediction accuracy. This provides a reference for soil survey and digital mapping in complex terrain areas.

INFORMATION SOURCES IMPACT ON THE ADOPTION OF PRECISION TECHNOLOGY BY COTTON PRODUCERS IN THE UNITED STATES

Farmers demand more precision farming technology and specific information is consumed in the adoption process, which could not only depend on how efficiently the information flows among farmers. It is assumed that the sources of information are inputs in the production processes and could have an impact on the decision to adopt precision farming technology, after controlling for farmer and farm business characteristics. Accordingly, the objective of this research was to evaluate the effects of nine information sources used by cotton farmers of 12 U.S. producer states on the adoption of yield monitor with GPS, grid soil sampling, zone soil sampling, aerial photos, and soil survey maps. The scientific utility of this research lies on the quantitative data from the Southern Cotton Precision Farming Survey analysed using statistical methods such as univariate, bivariate and multivariate probit regressions. The statistical results indicated that information from dealers, consultants, university publications, and university events were the most common information sources used when searching for precision farming information with positive and significant effects on the adoption of precision farming technology. The presented findings from this comprehensive analysis can assist organizations in selecting information sources, and on planning communications and partnerships strategies fostering technology transfer.

Provincial-scale digital soil mapping using a random forest approach for British Columbia

Although British Columbia (BC), Canada, has a rich history of producing conventional soil maps (CSMs) between 1925 and 2000, the province still lacks a detailed soil map with a comprehensive coverage due to the cost and time required to develop such a product. This study builds on previous digital soil mapping (DSM) research in BC and develops provincial-scale maps. Soil taxonomic classes (e.g., great groups and order) and parent material classes were mapped at a 100 m spatial resolution for BC (944 735 km2). Training points were generated from detailed and semi-detailed soil survey maps. The training points were intersected with 26 topographic indices for mapping parent materials with an additional 9 climatic and vegetation indices for mapping soil classes. The soil–environmental relationships were inferred using the random forest (RF) classifier. The fitted models were used to predict 23 soil great groups, 9 soil orders, and 10 parent material classes. Accuracy assessments were performed using n = 14 570 validation points for parent material classes and n = 14 316 validation points for soil classes, acquired from the BC Soil Information System. The accuracy rates for soil great groups, orders, and parent material classes were 55%, 62%, and 69%, respectively, and kappa coefficients were 0.37, 0.41, and 0.59, respectively. This study demonstrated that when RF was trained using CSMs, the accuracy for the resulting DSM was higher than the original CSM. To assess prediction uncertainties, ignorance uncertainty maps were developed using class-probability layers generated by the RF models.

Soilscapes of New Zealand: Pedologic diversity as organised along environmental gradients

Soilscapes are a regionalisation of the landscape into a suite of contiguous segments with an homogeneous set of soil forming factors. The concept has been present in the soil science literature since the late 1950s, proving to be a useful framework for generalising traditional soil survey maps. This concept is inherently multi-scale, and current approaches generally build either on existing soil maps, or on cluster analysis of environmental proxies of soil forming factors. In this study, in parallel with the concept of beta-diversity in numerical ecology, we built a soilscape regionalisation for New Zealand based on detecting the turnover in soil types along different environmental gradients. It was implemented using Gradient Forest, a method that analyses the frequency of species (in our case, soil type) turnover alongside such gradients, which are then ranked relative to their ecological (in our case, pedological) relevance. Based on this analysis, the environmental covariates were transformed to amplify their most important parts in terms of soil type turnover. The transformed variables were then segmented into contiguous regions, at three different levels of scale. Finally, hierarchical clustering was used to produce discrete soilscapes, at different scales, and for the entire country. This approach was developed using pseudo-observations derived from a national scale coverage of soil types, and validated using an independent set of actual soil profile observations. Validation results reveal strong agreement between the dissimilarity quantified between soilscapes and the taxonomic distance between actual soil profile observations (R = 0.61, P < 0.001). We expect the resulting layers from this soilscape delineation exercise to be used for a diverse suite of pedometrics applications, from stratifying soil sampling schemes, to optimising the soil survey boundaries, and for digital soil mapping.

Digital soil mapping in a low-relief landscape to support wetland restoration decisions

Efforts to utilize conventional soil maps in wetland conservation and restoration planning are often hampered by the coarse scale of the soil maps relative to the scale of restoration decisions, the spatial aggregation of soil components, and the difficulty in accounting for uncertainty in soil maps. The goal of this study was to explore the potential of digital soil mapping (DSM) techniques to improve identification of wetland soils and map soil properties on a low relief depressional wetland landscape. Separate random forests models were constructed to predict natural soil drainage and texture class on forest and cropland. The models were trained using soil profile data collected from local soil surveyors and previous research. Environmental covariates included topographic metrics developed from a 3 m lidar digital elevation model, and attributes derived from soil survey maps, the agricultural ditch network, and the National Wetlands Inventory. The resulting soil class probability maps demonstrated better representation of soil-landscape relationships on depressional wetlands on forest than on cropland; an independent field validation of soil maps resulted in greater than 70% accuracy in predicting natural soil drainage and texture class on forested depressions. DSM techniques can be used to generate maps with greater spatial detail than conventional soil maps in low relief depressional wetland landscapes; these maps and the attribute importance measures derived from the models have potential to improve watershed models and inform our understanding of wetland hydrology in these landscapes.

Evaluation of conditioned Latin hypercube sampling for soil mapping based on a machine learning method

Sampling design plays an important role in soil survey and soil mapping. Conditioned Latin hypercube sampling (cLHS) has been proven as an efficient sampling strategy and used widely in digital soil mapping. cLHS samples are randomly selected in each stratum of environmental variables, thus the produced sample sets can vary significantly at different runs with the same sample size. Although variation of mapping accuracies caused by the randomness of cLHS has been realized and qualitatively mentioned in past studies. However, how the randomness of cLHS could quantitatively influence mapping accuracy has rarely been examined. In this study, we conducted experiments to examine how the sample randomness quantitatively influence soil mapping accuracy with different sample sizes, and analyzed the possible reasons from a pedogenesis perspective. The results showed that the largest range of mapping accuracies of 500 repeats was 39.5% at a sample density of 2.59 point/km2, while the smallest range was 7.3% at the maximum sample size with a sample density of 32.47 point/km2. The sample density for satisfactory prediction accuracies in our study area was at least 10.06 Point/km2. The results showed that both the allocation of sample points to each soil series and the typicality of sample points played important roles in mapping accuracies. But the deep reasons causing the unstable performance of cLHS at small sample sizes were the imbalanced class distribution of soil series and the overlap between soil series in the distribution of environmental covariates. Researchers need to be cautious about the output when applying cLHS with small sampling densities. Some effective approaches to address this issue include increasing the sample size, checking the sample allocations of a cLHS design with the assistance of legacy soil maps, or adding the legacy soil map as a variable during sampling design. When the sampling resources and legacy soil maps are limited for an area, fuzzy k-means clustering sampling could be a potential alternative. This study provides useful references for better understanding the uncertainty of cLHS when the sample density is small and selecting alternative sampling methods accordingly.

Differences in Inventories of Waterlogged Territories in Soil Surveys of Different Years and in Land Management Documents

On soil maps and in land management documents, the excessively moistened areas of the earth surface are shown differently, and their areas on three different source maps (large-scale soil survey map, land cadaster map, and land management planning map) may differ by five times. According to current land legislation, soil maps should be used for cadastral valuation and cadastral division of arable land. It is supposed that the three sources of information on the land cover do not contradict one another. We analyzed the allocation of waterlogged lands on these source maps in order to find the reason for the existing discrepancies in the areas of waterlogged lands. Soil and land management materials from four rounds of the soil survey in 1937–1996 and remote sensing materials from 1968 to 2018 were analyzed. It was found that, until the third round of soil surveys, the concept of waterlogged area was the same for soil scientists, cadastral specialists, and land surveyors and meant the areas of limited use for arable farming because of the excessive atmospheric or ground moistening. Since the mid-1980s, soil scientists have ceased to consider waterlogging as a factor limiting land use, whereas land management specialists have not changed their approaches. In the cadastral division of land, the use of soil maps has become fragmentary; often, land plots are characterized as agreed with the owner. In 1958, the area of waterlogged soils on the soil map of Tambov oblast was 14%; all these lands had certain limitations of their use for arable farming. On the soil map of 1986, the area of waterlogged soils reached 65%, though only 6% of them were of limited use for arable farming. Independent retrospective monitoring methods applied by us to this territory indicated that limitations in the arable use of land related to the soil water regime are observed on about 16% of the territory of Tambov oblast. It is suggested that the allocation of waterlogged soils and lands should be unified on the basis on the technology of retrospective monitoring of soil and land covers.

Suitability of Green Gram Production in Kenya under Present and Future Climate Scenarios Using Bias-Corrected Cordex RCA4 Models

Green gram is considered as one of the legumes suitable for cultivation in the Arid and Semi-Arid Lands (ASALs) of Kenya. However, climate change may alter the areas suitable for green gram production. This study sought to model green gram suitability in Kenya under present and future conditions using bias-corrected RCA4 models data. The datasets used were: maps of soil parameters extracted from Kenya Soil Survey map; present and future rainfall and temperature data from an ensemble of nine models from the Fourth Edition of the Rossby Centre (RCA4) Regional Climate Model (RCM); and altitude from the Digital elevation model (DEM) of the USGS. The maps were first reclassified into four classes of suitability as Highly Suitable (S1), Moderately Suitable (S2), Marginally Suitable (S3), and Not Suitable (N). The classes represent the different levels of influence of a factor on the growth and yield of green grams. The reclassified maps were then assigned a weight generated using the Analytical Hierarchy Process (AHP). A weighted overlay of climate characteristics (past and future rainfall and temperature), soil properties (depth, pH, texture, CEC, and drainage) and altitude found most of Kenya as moderately suitable for green gram production during the March to May (MAM) and October to December (OND) seasons under the baseline, RCP 4.5 and RCP 8.5 scenarios with highly suitable areas being found in Counties like Kitui, Makueni, and West Pokot among others. During the MAM season, the area currently highly suitable for green gram production (67,842.62 km2) will increase slightly to 68,600.4 km2 (1.1%) during the RCP 4.5 and reduce to 61,307.8 km2 (−9.6%) under the RCP 8.5 scenario. During the OND season, the area currently highly suitable (49,633.4 km2) will increase under both RCP 4.5 (22.2%) and RCP 8.5 (58.5%) scenarios. This increase is as a result of favourable rainfall and temperature conditions in the future.

At the interface between domain knowledge and statistical sampling theory: Conditional distribution based sampling for environmental survey (CODIBAS)

In environmental research, there is an extensive knowledge of the underlying processes that cause a distinct spatial landscape pattern of system properties. Statistical sampling theory deals with how a dataset must be constructed that allows for the transferability of the insights from the collected data to the system. Stratified and balanced sampling schemes applied for environmental survey, seek to reduce the necessary amount of data to capture the spatial heterogeneity of a landscape. The particular design’s specification depends on the field of application. Against this background, the author strives to draw the attention to the conceptual shortcomings of conditioned Latin hypercube sampling (cLHS) in the context of soil survey and digital soil mapping. Furthermore, a new sampling design is presented which (1) combines the advantages of both, stratified and balanced designs, (2) shows consistency in the application of pedogenetic theory, and (3) which can be obtained by some simple modifications to the computer code of cLHS. Overall, this manuscript shall promote a vivid discussion in the Pedometrics community concerning the consideration of scientific domain knowledge in statistical sampling theory.

From geological to soil parent material maps - A random forest-supported analysis of geological map units and topography to support soil survey in South Tyrol

Parent material is an important factor of soil formation and consequently plays a dominant role in both traditional field soil survey and digital soil mapping. The emergence of a new generation of detailed geological maps at high spatial resolution in South Tyrol raises the question of how to effectively incorporate these into soil mapping efforts. By comparing the units of these geological maps with the parent material description of soil pits, we evaluate to what extent these can be used as soil parent material maps. Random forest classification and feature selection are applied to highlight those terrain parameters that i) best distinguish between the different surficial geology units, ii) separate soil profile sites with different soil parent material, and iii) can be used together with the geologic map to train a classifier to model the distribution of soil parent material in the study area. The main issue detected by analyzing the differences between the geologic map units and the soil parent material information is the dominant role of till, which acts as soil parent material for a large number of soils located on different geological map units. While slope debris is another class on which geological map and soil pit descriptions often disagree, the issues concerning its misclassification are connected more to categorical transitions between soil parent material classes. Terrain parameters characterizing surface roughness, specifically a combination of vector ruggedness measure (VRM) and topographic roughness index (TRI), were identified as being best suited to join the geological map units in modeling soil parent material and indicate areas where till as soil parent material should be expected. By evaluating these results together with the distribution of soil types, a geologic-topographic characterization is performed for each geological map unit, with the aim of highlighting specific combinations of geological units and topographical situations which should be in the center of future detailed soil surveys, consequently facilitating the soil mapping procedure.

Mapping parent material as part of a nested approach to soil mapping in the Arkansas River Valley

Soil mappers have traditionally relied on tacit knowledge and qualitative assessment of soil-landscape relationships to obtain the physiographic context necessary to predict soil distribution and spatial patterns. This assessment implicitly utilizes a nested hierarchical approach based on differences in the phenomenon scale of soil forming factors where climate, landscape, parent material, and topography are examined in sequence to create a model of soil-landscape relationships. Our objective was to predict parent material distribution using expert knowledge paired with quantitative digital terrain attributes as part of a nested approach to digital soil mapping. The study took place at an 890-hectare research farm in Logan County, Arkansas, which is part of the Arkansas River Valley. Two major groups of parent material are identifiable in the Arkansas River Valley: residual sandstone and shale on erosional uplands, and silty/clayey pedisediment in depositional areas. A 5-m digital elevation model was used to derive thirteen terrain attributes for the study site. Three of the terrain attributes, namely topographic position index, multi-resolution valley bottom flatness, and vertical distance to channel network, were utilized as part of a rule-based approach to model parent material distribution based on preliminary reconnaissance and expert knowledge of the area. The model was validated by sampling 20 locations using a conditioned Latin hypercube sampling (cLHS) design to evaluate the prediction accuracy. Seventy-five percent of cLHS samples were accurately predicted to be residuum or pedisediment. The resulting map also had 90% agreement with the National Cooperative Soil Survey map; however, the digital map was able to provide more spatially explicit information especially on inclusions. Incorporating parent material distribution as part of a nested hierarchical approach to digital soil mapping aids in constraining and predicting soil properties, enables a more straightforward examination of physiographic context and can ultimately lead to more accurate digital soil maps for land management.

THE SPATIAL VARIABILITY OF SOME SOIL PROPERTIES For Al- HAFFAR EAST PROJECT - AL-DEWANA PROVINCE BY TIME SERIES ANALYSIS

This study was done on semi-detailed soil survey map of east AL-Haffar project, which located in AL-Dewana province between longitudes 44° 51- 00= - 44° 38- 00= and latitudes 33° 38- 00= - 33° 57- 30=. The project total area was 50000 ha, which survived in 2015 by ministry of water resources /the ecological studies department, included 92 Soil pedons, the traditional method was done with a constant distance of 750m were involved all studies pedons. The spatial variability of some physical, chemical and Morphological properties of these soils were studies, using time series analysis . The results were as follow, the statistical models that are appropriate to describe the soil properties variation. The most frequent was ARMA and autocorrelation coefficient for soil properties was lower than in case of dependence or random lows, which required more samples relying on the autocorrelation of the soil properties was weak (less than 0.5 ) and required more samples in the random status.

Identification of soil profile classes using depth-weighted visible–near-infrared spectral reflectance

Soil visible–near-infrared (Vis-NIR) diffuse reflectance, which can be collected rapidly and cheaply, contains rich information of the properties that are useful for soil taxonomic diagnosis. Vis-NIR spectroscopy has the potential to identify soil taxonomic classes in an efficient and cost-effective way. This study explores the potential of Vis-NIR spectroscopy to identify soil profile classes at the order, suborder, group, and subgroup levels of the Chinese Soil Taxonomy (CST).The authors measured the Vis-NIR (350–2500 nm) diffuse reflectance of 2260 legacy soil samples, which were sampled by genetic horizon and collected from 527 soil profiles (75% for training and 25% for validation). To represent the overall spectral pattern for each soil profile, the depth-weighted average was used to combine the spectral reflectance of genetic horizons. The synthetic minority over-sampling technique (SMOTE) was used to obtain balanced training data. Principal component analysis (PCA) was performed to extract spectral predictors used for random forest (RF) modeling in soil classification.Vis–NIR spectral reflectance exhibited acceptable overall performance for identification of soil orders and suborders, with overall validation accuracies of 0.63 and 0.62, respectively, but low overall performance at group and subgroup levels, with overall validation accuracies of 0.40 and 0.28, respectively. The overall performance at different taxonomic levels was affected by the number of soil classes and the class distribution of the soil profiles. Soil classes with pedogenic processes associated closely with spectrally active soil properties or with characteristic profile patterns were most accurately identified, even if they were minority classes. The results show that the Vis–NIR spectral pattern of soil profile can be used to identify soil profile classes at higher taxonomic levels in the CST system. Combined with machine-learning techniques, the soil Vis–NIR spectral library will serve as an efficient tool for digital soil survey mapping and updating with the use of legacy soil samples and the reduction of conventional laboratory analyses.

Soil legacy data rescue via GlobalSoilMap and other international and national initiatives

Legacy soil data have been produced over 70 years in nearly all countries of the world. Unfortunately, data, information and knowledge are still currently fragmented and at risk of getting lost if they remain in a paper format. To process this legacy data into consistent, spatially explicit and continuous global soil information, data are being rescued and compiled into databases. Thousands of soil survey reports and maps have been scanned and made available online. The soil profile data reported by these data sources have been captured and compiled into databases. The total number of soil profiles rescued in the selected countries is about 800,000. Currently, data for 117, 000 profiles are compiled and harmonized according to GlobalSoilMap specifications in a world level database (WoSIS). The results presented at the country level are likely to be an underestimate. The majority of soil data is still not rescued and this effort should be pursued. The data have been used to produce soil property maps. We discuss the pro and cons of top-down and bottom-up approaches to produce such maps and we stress their complementarity. We give examples of success stories. The first global soil property maps using rescued data were produced by a top-down approach and were released at a limited resolution of 1km in 2014, followed by an update at a resolution of 250m in 2017. By the end of 2020, we aim to deliver the first worldwide product that fully meets the GlobalSoilMap specifications.

Comparing the use of training data derived from legacy soil pits and soil survey polygons for mapping soil classes

Machine-learners used for digital soil mapping are generally trained using either data derived from field-observed soil pits or from soil survey polygons - although no direct comparison of the accuracy resulting from the two methods has yet to be undertaken. This study examined such a comparison over the Okanagan Valley and Kamloops region of British Columbia where good quality soil pit and soil survey data were available. A standard set of environmental variables including vegetative, climatic, and topographic indices were used to predict soil Great Groups in accordance with the Canadian System of Soil Classification. The pit-derived training dataset was developed using n=478 points from the British Columbia Soil Information System while the polygon-derived training dataset was developed through random sampling of single-component soil survey map units based on an area-weighted approach. In both cases, the training points were intersected with a suite of 18 environmental covariates, reduced from 27 covariates using principal component analysis, and submitted to a machine-learner for predictions at a 100m spatial resolution. Four single-model learners (CART, k-nearest neighbor, multinomial logistic regression, and logistic model tree) and five ensemble-model learners (CART with bagging, k-nearest neighbor with bagging, multinomial logistic regression with bagging, logistic model trees with bagging, and Random Forest) were compared. Surfaces of prediction uncertainty were produced using ignorance uncertainty and results were validated using a 5-fold cross-validation procedure. Predictions made using polygon-derived training data were consistently higher in accuracy across all models where the Random Forest model was the most effective learner with C=61% accuracy when using pit-derived training data and C=68% accuracy when using polygon-derived training data. Comparing single-model and ensemble-learner models, the bagging algorithm resulted in a 2–11% increase in accuracy when using pit-derived training data. Ensemble-models allowed for the visualization of prediction uncertainty. This study provides further insight into the use of legacy soil data and the development of training data for digital soil mapping.

Classification of some soils from province of Kirkuk and the statement extent of their sensitivity to desertification

This study was conducted at several soil location in Kirkuk Governorate between length lines 44° 16 and 44° 29 north and two width circle 35° 7 and 35° 46 east to determine land deterioration conditions especially soil and vegetation deterioration within this location, In addition it is characterized with variety of geomorpholical patterns and physiographic units, in addition to their use in agriculture. After choosing locations of study, detection of soil pedons their number was 6 was done. Every pedon was divided in to horizons according to some morphological characters, as a first step in determination horizons of the soil. Among these characters, are variation in soil contents of stones, Soil texture, formulation and color and the separated lines between horizons as mentioned? Then it was described morphologically according to standards of American soil survey Index and its changes. Classification was completed to a level of soil series according to classification of soil according to the formula G.T.B.P.C.D. Geomorphologic map and displine photos were used determine the study district and locations of pedons with help of GPS instrument. Semi –detailed survey was done to cover an area advocating the free method. Key soils within the margins of the selected area were detected and they found to be 6 series with determining of their locations on soil survey map. The results of the study revealed that vegetation quality index indices of soil series of studied location were within the class very weak and they included the soil series 451CCW, 431CCW.The class weak included the soil series 432CCW, 453CCW, whereas the series 433CCW and 441CCW were within the class moderate. Results of study indicated that soil quality index of soil series of the studied location was within the class very low for series 441CCW whereas the series 432CCW, 431CCW was within the class low, whereas the series 433CCW, 451CCW were within the class moderate. Sensitivity of the district environment to desertification was described. Results showed that the most sensitive series was 443CCW, which was very sensitive and series 453CCW, 431CCW was sensitive, whereas the series 441CCW, 432CCW were within the class moderate and low sensitive respectively. The lower series sensitivity is the series 451CCW.