Spatial data mining for enhanced soil map modelling

The principle of using induction rules based on spatial environmental data to model a soil map has previously been demonstrated Whilst the general pattern of classes of large spatial extent and those with close association with geology were delineated small classes and the detailed spatial pattern of the map were less well rendered Here we examine several strategies to improve the quality of the soil map models generated by rule induction Terrain attributes that are better suited to landscape description at a resolution of 250 m are introduced as predictors of soil type A map sampling strategy is developed Classification error is reduced by using boosting rather than cross validation to improve the model Further the benefit of incorporating the local spatial context for each environmental variable into the rule induction is examined The best model was achieved by sampling in proportion to the spatial extent of the mapped classes boosting the decision trees and using spatial contextual information extracted from the environmental variables.

What's in that soil map?

Mode of access: Internet.

General soil map, Jackson Brook watershed, Morris County, New Jersey /

"January 1988."

General soil map, Burlington County, New Jersey /

"June 1970."

Soil Organic Carbon Stocks of Rio Grande do Sul, Brazil

Robust and accurate regional estimates of C storage in soils are currently an important research topic because of ongoing debate about human-induced changes in the terrestrial C cycle. Widely available geoprocessing tools were applied to estimate native soil organic C (SOC) stocks of Rio Grande do Sul state in southern Brazil to a depth of 30 cm from previously sampled soil pedons under undisturbed vegetation. The study used a statewide comprehensive soil survey comprising a small-scale soil map, a climate map, and a soil pedon database. Soil organic C stocks under native vegetation were calculated with two different approaches: the Tier 1 method of the Intergovernmental Panel on Climate Change (IPCC) and a refined method based on actual field measurements derived from soil profile data. Highest SOC stocks occurred in Neossolos Quartzarenico hidromorfico (Aquents), Organossolos Tiomorficos (Hemists), Latossolos Brunos (Udox), and Vertissolos Ebanicos (Uderts) soil classes. Before human use of soils, most C was stored in the Latossolos Vermelhos (Udox) and Neossolos Regoliticos (Orthents), which occupy a large area of Rio Grande do Sul. Generally, IPCC default reference SOC stocks compared well with SOC stocks calculated from soil pedons. The total SOC stock of Rio Grande do Sul was estimated at 1510.3 Tg C (5.8 kg C m(-2)) by the IPPC method and 1597.5 +/- 363.9 Tg C (7.4 +/- 1.9 kg C m(-2)) calculated from soil pedons. The SOC digital map and SOC database developed in this study provide crucial background information for state-level contemporary assessment of C stocks and soil C sequestration programs and initiatives.

Soil Survey of Black Hawk County, Iowa, 2005

The general soil map, which is a color map, shows the survey area divided into groups of associated soils called general soil map units. This map is useful in planning the use and management of large areas. To find information about your area of interest, locate that area on the map, identify the name of the map unit in the area on the color-coded map legend, then refer to the section General Soil Map Units for a general description of the soils in your area.

Soil Survey of Clay County, Iowa, 2005

The general soil map, which is a color map, shows the survey area divided into groups of associated soils called general soil map units. This map is useful in planning the use and management of large areas. To find information about your area of interest, locate that area on the map, identify the name of the map unit in the area on the color-coded map legend, then refer to the section General Soil Map Units for a general description of the soils in your area.

Digital soil mapping: strategy for data pre-processing

The region of greatest variability on soil maps is along the edge of their polygons, causing disagreement among pedologists about the appropriate description of soil classes at these locations. The objective of this work was to propose a strategy for data pre-processing applied to digital soil mapping (DSM). Soil polygons on a training map were shrunk by 100 and 160 m. This strategy prevented the use of covariates located near the edge of the soil classes for the Decision Tree (DT) models. Three DT models derived from eight predictive covariates, related to relief and organism factors sampled on the original polygons of a soil map and on polygons shrunk by 100 and 160 m were used to predict soil classes. The DT model derived from observations 160 m away from the edge of the polygons on the original map is less complex and has a better predictive performance.

Comparison between detailed digital and conventional soil maps of an area with complex geology

Since different pedologists will draw different soil maps of a same area, it is important to compare the differences between mapping by specialists and mapping techniques, as for example currently intensively discussed Digital Soil Mapping. Four detailed soil maps (scale 1:10.000) of a 182-ha sugarcane farm in the county of Rafard, São Paulo State, Brazil, were compared. The area has a large variation of soil formation factors. The maps were drawn independently by four soil scientists and compared with a fifth map obtained by a digital soil mapping technique. All pedologists were given the same set of information. As many field expeditions and soil pits as required by each surveyor were provided to define the mapping units (MUs). For the Digital Soil Map (DSM), spectral data were extracted from Landsat 5 Thematic Mapper (TM) imagery as well as six terrain attributes from the topographic map of the area. These data were summarized by principal component analysis to generate the map designs of groups through Fuzzy K-means clustering. Field observations were made to identify the soils in the MUs and classify them according to the Brazilian Soil Classification System (BSCS). To compare the conventional and digital (DSM) soil maps, they were crossed pairwise to generate confusion matrices that were mapped. The categorical analysis at each classification level of the BSCS showed that the agreement between the maps decreased towards the lower levels of classification and the great influence of the surveyor on both the mapping and definition of MUs in the soil map. The average correspondence between the conventional and DSM maps was similar. Therefore, the method used to obtain the DSM yielded similar results to those obtained by the conventional technique, while providing additional information about the landscape of each soil, useful for applications in future surveys of similar areas.

Soil Survey of Iowa. Report no. 34, Boone County soils, 1924

This report contains a general colored soil map of Boone County and information on the county's soil physiology, drainage and fertility. It also includes information on field experiments, rotation of crops, prevention of erosion, soil types and other vital soil information in Boone County.

Prediction of soil orders with high spatial resolution: response of different classifiers to sampling density

The objective of this work was to evaluate sampling density on the prediction accuracy of soil orders, with high spatial resolution, in a viticultural zone of Serra Gaúcha, Southern Brazil. A digital elevation model (DEM), a cartographic base, a conventional soil map, and the Idrisi software were used. Seven predictor variables were calculated and read along with soil classes in randomly distributed points, with sampling densities of 0.5, 1, 1.5, 2, and 4 points per hectare. Data were used to train a decision tree (Gini) and three artificial neural networks: adaptive resonance theory, fuzzy ARTMap; self‑organizing map, SOM; and multi‑layer perceptron, MLP. Estimated maps were compared with the conventional soil map to calculate omission and commission errors, overall accuracy, and quantity and allocation disagreement. The decision tree was less sensitive to sampling density and had the highest accuracy and consistence. The SOM was the less sensitive and most consistent network. The MLP had a critical minimum and showed high inconsistency, whereas fuzzy ARTMap was more sensitive and less accurate. Results indicate that sampling densities used in conventional soil surveys can serve as a reference to predict soil orders in Serra Gaúcha.

Digital soil mapping: evaluation of sampling systems for soil surveys and refinement of soil maps at lower cost using legacy data

In soil surveys, several sampling systems can be used to define the most representative sites for sample collection and description of soil profiles. In recent years, the conditioned Latin hypercube sampling system has gained prominence for soil surveys. In Brazil, most of the soil maps are at small scales and in paper format, which hinders their refinement. The objectives of this work include: (i) to compare two sampling systems by conditioned Latin hypercube to map soil classes and soil properties; (II) to retrieve information from a detailed scale soil map of a pilot watershed for its refinement, comparing two data mining tools, and validation of the new soil map; and (III) to create and validate a soil map of a much larger and similar area from the extrapolation of information extracted from the existing soil map. Two sampling systems were created by conditioned Latin hypercube and by the cost-constrained conditioned Latin hypercube. At each prospection place, soil classification and measurement of the A horizon thickness were performed. Maps were generated and validated for each sampling system, comparing the efficiency of these methods. The conditioned Latin hypercube captured greater variability of soils and properties than the cost-constrained conditioned Latin hypercube, despite the former provided greater difficulty in field work. The conditioned Latin hypercube can capture greater soil variability and the cost-constrained conditioned Latin hypercube presents great potential for use in soil surveys, especially in areas of difficult access. From an existing detailed scale soil map of a pilot watershed, topographical information for each soil class was extracted from a Digital Elevation Model and its derivatives, by two data mining tools. Maps were generated using each tool. The more accurate of these tools was used for extrapolation of soil information for a much larger and similar area and the generated map was validated. It was possible to retrieve the existing soil map information and apply it on a larger area containing similar soil forming factors, at much low financial cost. The KnowledgeMiner tool for data mining, and ArcSIE, used to create the soil map, presented better results and enabled the use of existing soil map to extract soil information and its application in similar larger areas at reduced costs, which is especially important in development countries with limited financial resources for such activities, such as Brazil.

Phytomass and soil carbon storage of different land cover classes in the Usa river basin

This study describes detailed partitioning of phytomass carbon (C) and soil organic carbon (SOC) for four study areas in discontinuous permafrost terrain, Northeast European Russia. The mean aboveground phytomass C storage is 0.7 kg C/m**2. Estimated landscape SOC storage in the four areas varies between 34.5 and 47.0 kg C/m**2 with LCC (land cover classification) upscaling and 32.5-49.0 kg C/m**2 with soil map upscaling. A nested upscaling approach using a Landsat thematic mapper land cover classification for the surrounding region provides estimates within 5 ± 5% of the local high-resolution estimates. Permafrost peat plateaus hold the majority of total and frozen SOC, especially in the more southern study areas. Burying of SOC through cryoturbation of O- or A-horizons contributes between 1% and 16% (mean 5%) of total landscape SOC. The effect of active layer deepening and thermokarst expansion on SOC remobilization is modeled for one of the four areas. The active layer thickness dynamics from 1980 to 2099 is modeled using a transient spatially distributed permafrost model and lateral expansion of peat plateau thermokarst lakes is simulated using geographic information system analyses. Active layer deepening is expected to increase the proportion of SOC affected by seasonal thawing from 29% to 58%. A lateral expansion of 30 m would increase the amount of SOC stored in thermokarst lakes/fens from 2% to 22% of all SOC. By the end of this century, active layer deepening will likely affect more SOC than thermokarst expansion, but the SOC stores vulnerable to thermokarst are less decomposed.

ISRIC-WISE - Global Soil Profile Data (ver. 3.1)

Version 3.1 of the ISRIC-WISE database holds selected site and horizon data for some 10 250 soil profiles from 149 countries. Profile data were extracted from a wide range of sources and harmonized with respect to the original (1974) and revised (1988) Legend of the FAO-Unesco Soil Map of the World. Profiles have been described, sampled, and analysed according to methods and standards in use in the originating countries; analytical results for the same property cannot always be compared directly; as a result the amount of measured data available for modelling is sometimes much less than expected. WISE was specifically developed for land-related applications at continental and global scales.

Global assessment of soil phosphorus retention potential

Limited availability of P in soils to crops may be due to deficiency and/or severe P retention. Earlier studies that drew on large soil profile databases have indicated that it is not (yet) feasible to present meaningful values for "plant-available" soil P, obtained according to comparable analytical methods, that may be linked to soil geographical databases derived from 1:5 million scale FAO Digital Soil Map of the World, such as the 5 x 5 arc-minute version of the ISRIC-WISE database. Therefore, an alternative solution for studying possible crop responses to fertilizer-P applied to soils, at a broad scale, was sought. The approach described in this report considers the inherent capacity of soils to retain phosphorus (P retention), in various forms. Main controlling factors of P retention processes, at the broad scale under consideration, are considered to be pH, soil mineralogy, and clay content. First, derived values for these properties were used to rate the inferred capacity for P retention of the component soil units of each map unit (or grid cell) using four classes (i.e., Low, Moderate, High, and Very High). Subsequently, the overall soil phosphorus retention potential was assessed for each mapping unit, taking into account the P-ratings and relative proportion of each component soil unit. Each P retention class has been assigned to a likely fertilizer P recovery fraction, derived from the literature, thereby permitting spatially more detailed, integrated model-based studies of environmental sustainability and agricultural production at the global and continental level (< 1:5 million). Nonetheless, uncertainties remain high; the present analysis provides an approximation of world soil phosphorus retention potential.