Type Raster Dataset
Soil Landscapes of the United States (SOLUS) is a national map product developed by the National Cooperative Soil Survey and focused on providing a consistent set of spatially continuous soil property maps to support large scope soil investigations and land use decisions. SOLUS maps use continuous property mapping, which predicts soil physical or chemical properties in horizontal and vertical dimensions. The soil properties are represented across a continuous range of values. Raster datasets of select soil properties can be predicted at specified depths or depth intervals.
SOLUS maps use a digital soil mapping framework that combines multiple sources of soil survey data with environmental covariate data and machine learning. The SOLUS100 maps are a set of 100 m spatial resolution maps that predict 20 soil properties (listed below with units) at 7 depths with uncertainty estimates for the contiguous United States. Very Fine Sand (%)Fine Sand (%)Medium Sand (%)Coarse Sand (%)Very Coarse Sand (%)Total Sand (%)Silt (%)Clay (%)pHSoil Organic Carbon (%)Calcium Carbonate Equivalent (%)Gypsum Content (% by weight)Electrical Conductivity (mmhos/cm)Sodium Adsorption RatioCation Exchange Capacity (meq/100 g)Effective Cation Exchange Capacity (meq/100 g)Oven Dry Bulk Density (g/cm^3)Depth to Bedrock (cm)Depth to Restriction (cm)Rock Fragment Volume (%)Each property listed above is predicted at 0, 5, 15, 30, 60, 100, and 150 cm depths. Each property-depth prediction has an estimate of uncertainty expressed as the relative prediction interval (RPI) that ranges from 0 to 1. RPI is a relative measure of uncertainty with high values being more uncertain. It is computed as the ratio of the 95 percent prediction interval width to the training set 95 percent quantile width (97.5 percent quantile value minus 2.5 percent quantile value). Values closer to 0 indicate lower uncertainty and values closer to 1 indicate higher uncertainty. Values greater than 1 indicate that the prediction at that location is outside the range of the training data used for that property at that depth. Prediction interval high and low are also provided. Property prediction and uncertainty layers follow the naming convention: propertyname_depth_cm_p (predicted property values)propertyname_depth_cm_rpi (relative prediction interval)propertyname_depth_cm_l (prediction interval low)propertyname_depth_cm_h (prediction interval high)Select property, prediction interval, and RPI layers have been rescaled to provide the data in integer format. Information about scaling factors is provided in the Fields section of this document. A summary table with layer filename, property, depth, filetype, scalar, description, and units is also included with the maps: Final_Layer_Table_20231215.csvSOLUS webpage: https://www.nrcs.usda.gov/resources/data-and-reports/soil-landscapes-of-the-united-states-solus
There are no credits for this item.
The U.S. Department of Agriculture, Natural Resources Conservation Service, should be acknowledged as the data source in products derived from these data.
This dataset is not designed for use as a primary regulatory tool in permitting or citing decisions, but it may be used as a reference source. This dataset is public information and may be interpreted by organizations, agencies, units of government, or others based on needs; however, they are responsible for the appropriate application. Federal, state, or local regulatory bodies are not to reassign to the Natural Resources Conservation Service any authority for the decisions that they make. The Natural Resources Conservation Service will not perform any evaluations of these maps for purposes related solely to state or local regulatory programs.
Photographic or digital enlargement of these maps to scales greater than at which they were originally mapped can cause misinterpretation of the data. If enlarged, maps do not show the small areas of contrasting soils that could have been shown at a larger scale. The depicted soil boundaries, interpretations, and analysis derived from the maps do not eliminate the need for onsite sampling, testing, and detailed study of specific sites for intensive uses. Thus, these data and their interpretations are intended for planning purposes only. Digital data files are periodically updated. Files are dated, and users are responsible for obtaining the latest version of the data.
Although data in this product have been processed successfully on a computer system at the U.S. Department of Agriculture, no warranty expressed or implied is made by the Agency regarding the utility of the data on any other system nor shall the act of distribution constitute any such warranty. The U.S. Department of Agriculture will warrant the delivery of this product in computer-readable format and will offer appropriate adjustment of credit when the product is determined unreadable by correctly adjusted computer input peripherals. Request for adjustment of credit must be made within 90 days from the date of ordering. The U.S. Department of Agriculture nor any of its agencies are liable for misuse of the data. It is also not liable for damage, transmission of viruses, or computer contamination through the distribution of these datasets. USDA is an equal opportunity provider, employer, and lender. Full nondiscrimination statement: https://www.nrcs.usda.gov/non-discrimination
There is no extent for this item.
| Maximum (zoomed in) | 1:5,000 |
| Minimum (zoomed out) | 1:150,000,000 |
Nauman, T. W., Kienast-Brown, S., Roecker, S. M., Brungard, C., White, D., Philippe, J., & Thompson, J. A. (2024). Soil landscapes of the United States (SOLUS): developing predictive soil property maps of the conterminous United States using hybrid training sets. Soil Science Society of America Journal, 1–20. https://doi.org/10.1002/saj2.20769 SOLUS100 Ag Data Commons Repository: https://agdatacommons.nal.usda.gov/articles/dataset/Data_from_Soil_Landscapes_of_the_United_States_100-meter_SOLUS100_soil_property_maps_project_repository/25033856
The period over which training data used in the models was collected.
The U.S. Department of Agriculture, Natural Resources Conservation Service, should be acknowledged as the data source in products derived from these data.
This dataset is not designed for use as a primary regulatory tool in permitting or citing decisions, but it may be used as a reference source. This dataset is public information and may be interpreted by organizations, agencies, units of government, or others based on needs; however, they are responsible for the appropriate application. Federal, state, or local regulatory bodies are not to reassign to the Natural Resources Conservation Service any authority for the decisions that they make. The Natural Resources Conservation Service will not perform any evaluations of these maps for purposes related solely to state or local regulatory programs.
Photographic or digital enlargement of these maps to scales greater than at which they were originally mapped can cause misinterpretation of the data. If enlarged, maps do not show the small areas of contrasting soils that could have been shown at a larger scale. The depicted soil boundaries, interpretations, and analysis derived from the maps do not eliminate the need for onsite sampling, testing, and detailed study of specific sites for intensive uses. Thus, these data and their interpretations are intended for planning purposes only. Digital data files are periodically updated. Files are dated, and users are responsible for obtaining the latest version of the data.
Although data in this product have been processed successfully on a computer system at the U.S. Department of Agriculture, no warranty expressed or implied is made by the Agency regarding the utility of the data on any other system nor shall the act of distribution constitute any such warranty. The U.S. Department of Agriculture will warrant the delivery of this product in computer-readable format and will offer appropriate adjustment of credit when the product is determined unreadable by correctly adjusted computer input peripherals. Request for adjustment of credit must be made within 90 days from the date of ordering. The U.S. Department of Agriculture nor any of its agencies are liable for misuse of the data. It is also not liable for damage, transmission of viruses, or computer contamination through the distribution of these datasets. USDA is an equal opportunity provider, employer, and lender. Full nondiscrimination statement: https://www.nrcs.usda.gov/non-discrimination
SOLUS100 maps were reviewed internally by National Cooperative Soil Survey scientists prior to release.
Final predictions omit areas of open water and depths below bedrock.
Extreme value correction
All predictions are within the minimum and maximum bounds of the training set, and all soil texture fractions sum to 100.
Model accuracy
SOLUS100 property maps follow a digital soil mapping workflow that includes: 1. preparing and testing various point-location datasets 2. filling gaps in field training data with previous soil survey property estimates 3. building empirical models for each property at seven standard depths 4. testing model performance with conventional and spatial cross validation 5. rendering predictions and uncertainty metrics
The model development for SOLUS100 property maps included five general steps: (a) selecting the optimal set of existing property measurements, (b) combining field samples with an appropriate sample of gridded National Soil Geographic Database (gNATSGO) random training points, (c) fitting a final model and estimating global uncertainty metrics from a large random sample of the mapping domain, (d) comparing global uncertainty to various scales of CV uncertainty metrics to determine an appropriate spatial CV scale to represent a low bound of performance, and (e) use of the final model to render predictions. Quantile Random Forests from the R software Ranger package was used for predictive models.
Training data selection and amount varied by property and depth, but most often included National Cooperative Soil Survey Soil Characterization Database (SCD) data, National Soil Information System (NASIS) field sites directly linked to component or linked to a Soil Survey Geographic (SSURGO) database spatial home map unit component by a name match. Most models only used observations sampled since the year 2000 (a combination selected in 41 out of 121 models).
Accuracy of the predictive models was evaluated using a random 10-fold CV to estimate a high bound of performance and a spatial 10-fold CV to estimate a low bound of performance for each property at each depth. The 10-fold CV R2 values ranged from 0.45 to 0.87 with a mean of 0.65 while spatial CV R2 values ranged from 0.38 to 0.85 with a mean of 0.58.
Final predictions were masked for areas of open water using the 2019 U.S. National Land Cover Dataset to remove all water bodies from final predictions.
Final predictions were masked using the SOLUS100 modeled depth to bedrock layer. Property predictions below the predicted depth to bedrock are not included in the maps.
Final predictions were corrected for extreme values outside of the range of training set possibilities for each soil property by adjusting all predictions above the maximum of the training set to that maximum value. Similarly, all predictions below the minimum training set value were adjusted to that minimum value.
Soil texture fraction predictions were normalized to 100 percent in the final maps by adjusting values using a sum normalization (e.g. adjusted sand equals sand divided by the sum of sand, silt, and clay) to ensure logical consistency.
Covariate data was a set of 145 environmental data layers at 100 m spatial resolution representing topography, climate, vegetation, and parent material borrowed from the work of Ramcharan et al., 2018. Sources include U.S. National Elevation Dataset, Parameter-elevation Regression on Independent Slopes Model (PRISM), Moderate Resolution Imaging Spectroradiometer (MODIS), Landsat, long-term surface water and bare ground occurrence, aero radiometric data, land cover classes, potential natural vegetation, and surficial geology.
Training data sources included National Cooperative Soil Survey SCD with laboratory measurements, NASIS pedon observations with taxonomic names but no laboratory measurements, and gNATSGO weighted average property estimates for model training.
SOLUS100 property maps follow a digital soil mapping workflow that includes: 1. preparing and testing various point-location datasets 2. filling gaps in field training data with previous soil survey property estimates 3. building empirical models for each property at seven standard depths 4. testing model performance with conventional and spatial cross validation 5. rendering predictions and uncertainty metrics