The National Soil Database has produced a national database of soil geochemistry including point and spatial distribution maps of major nutrients, major elements, essential trace elements, trace elements of special interest and minor elements. In addition, this study has generated a National Soil Archive, comprising bulk soil samples and a nucleic acids archive each of which represent a valuable resource for future soils research in Ireland. The geographical coherence of the geochemical results was considered to be predominantly underpinned by underlying parent material and glacial geology. Other factors such as soil type, land use, anthropogenic effects and climatic effects were also evident. The coherence between elements, as displayed by multivariate analyses, was evident in this study. Examples included strong relationships between Co, Fe, As, Mn and Cu. This study applied large-scale microbiological analysis of soils for the first time in Ireland and in doing so also investigated microbial community structure in a range of soil types in order to determine the relationship between soil microbiology and chemistry. The results of the microbiological analyses were consistent with geochemical analyses and demonstrated that bacterial community populations appeared to be predominantly determined by soil parent material and soil type.

We developed a comprehensive, gridded Global Soil Dataset for use in Earth System Models (GSDE) and other applications as well. GSDE provides soil information including soil particle-size distribution, organic carbon, and nutrients, etc. and quality control information in terms of confidence level. GSDE is based on the Soil Map of the World and various regional and national soil databases, including soil attribute data and soil maps. We used a standardized data structure and data processing procedures to harmonize the data collected from various sources. We then used a soil type linkage method (i.e. taxotransfer rules) and the polygon linkage method to derive the spatial distribution of soil properties. To aggregate the attributes of different compositions of a mapping unit, we used three mapping approaches: area-weighting method, the dominant soil type method and the dominant binned soil attribute method. In the released gridded dataset, we used the area-weighting method as it will meet the demands of most applications. The dataset can be also aggregate to a lower resolution. The resolution is 30 arc-seconds (about 1 km at the equator). The vertical variation of soil property was captured by eight layers to the depth of 2.3 m (i.e. 0- 0.045, 0.045- 0.091, 0.091- 0.166, 0.166- 0.289, 0.289- 0.493, 0.493- 0.829, 0.829- 1.383 and 1.383- 2.296 m).

This data set is a digital soil survey and generally is the most detailed level of soil geographic data developed by the National Cooperative Soil Survey. The information was prepared by digitizing maps, by compiling information onto a planimetric correct base and digitizing, or by revising digitized maps using remotely sensed and other information. This data set consists of georeferenced digital map data and computerized attribute data. The map data are in a soil survey area extent format and include a detailed, field verified inventory of soils and miscellaneous areas that normally occur in a repeatable pattern on the landscape and that can be cartographically shown at the scale mapped. A special soil features layer (point and line features) is optional. This layer displays the location of features too small to delineate at the mapping scale, but they are large enough and contrasting enough to significantly influence use and management. The soil map units are linked to attributes in the National Soil Information System relational database, which gives the proportionate extent of the component soils and their properties.

This hosted feature layer has been published in RI State Plane Feet NAD 83.This data set is a digital soil survey and generally is the most detailed level of soil geographic data developed by the Rhode Island Soil Survey Program in partnership with the National Cooperative Soil Survey. The information was prepared by digitizing maps, by compiling information onto a planimetric correct base and digitizing, or by revising digitized maps using remotely sensed and other information. This data set consists of georeferenced digital map data and computerized attribute data. The map data are in a soil survey area extent format and include a detailed, field verified inventory of soils and miscellaneous areas that normally occur in a repeatable pattern on the landscape and that can be cartographically shown at the scale mapped.

Sixty one soils (soil types) represent the range of soils found across South Australia’s agricultural lands. Mapping shows the most common soil within each map unit, while more detailed proportion data are supplied for calculating respective areas of each soil type (spatial data statistics).

The Harmonized World Soil Database version 2.0 (HWSD v2.0) is a unique global soil inventory providing information on the morphological, chemical and physical properties of soils at approximately 1 km resolution. Its main objective is to serve as a basis for prospective studies on agro-ecological zoning, food security and climate change. The Harmonized World Soil Database (HWSD) was established in 2008 by the International Institute for Applied Systems Analysis (IIASA) and FAO, and in partnership with International Soil Reference and Information Centre (ISRIC), the European Soil Bureau Network (ESBN) and the Institute for Soil Sciences Chinese Academy of Sciences (CAS). The data entry and harmonization within a Geographic Information System (GIS) was carried out at IIASA, with verification of the database undertaken by all partners. HWSD was then updated in 2013 (HWSD v1.2) and in 2023 (HWSD v2.0). This updated version (HWSD v2.0) is built on the previous versions of HWSD with several improvements on (i) the data source that now includes several national soil databases, (ii) an enhanced number of soil attributes available for seven soil depth layers, instead of two in HWSD v1.2, and (iii) a common soil reference for all soil units (FAO1990 and the World Reference Base for Soil Resources). This contributes to a further harmonization of the database. The GIS raster image file is linked to the soil attribute database. The HWSD v2.0 soil attribute database provides information on the soil unit composition for each of the near 30 000 soil association mapping units. The HWSD v2.0 Viewer, provided with the database, creates this link automatically and provides direct access to the soil attribute data and the soil association information. Note: - A tutorial for accessing HWSD ver. 2.0 using R (prepared by David Rossiter, June 2023) has been added as an 'associated resource' (NOTE: Needs the SQLite version of HWSD v2 as provided below). - Soil property estimates in HWSDv2 were derived from Batjes (2016), Geoderma (https://doi.org/10.1016/j.geoderma.2016.01.034).

This data set is a digital soil survey and generally is the most detailed level of soil geographic data developed by the National Cooperative Soil Survey. The information was prepared by digitizing maps, by compiling information onto a planimetric correct base and digitizing, or by revising digitized maps using remotely sensed and other information. This data set consists of georeferenced digital map data and computerized attribute data. The map data are in a soil survey area extent format and include a detailed, field verified inventory of soils and miscellaneous areas that normally occur in a repeatable pattern on the landscape and that can be cartographically shown at the scale mapped. A special soil features layer (point and line features) is optional. This layer displays the location of features too small to delineate at the mapping scale, but they are large enough and contrasting enough to significantly influence use and management. The soil map units are linked to attributes in the National Soil Information System relational database, which gives the proportionate extent of the component soils and their properties.

This a Dataset Consisting of four types of soil images consisting of over 350 images Alluvial Soil - 195 Black Soil - 68 Cinder Soil - 30 Red Soil - 75

This data set is a digital soil survey and generally is the most detailed level of soil geographic data developed by the National Cooperative Soil Survey. The information was prepared by digitizing maps, by compiling information onto a planimetric correct base and digitizing, or by revising digitized maps using remotely sensed and other information. This data set consists of georeferenced digital map data and computerized attribute data. The map data are in a soil survey area extent format and include a detailed, field verified inventory of soils and miscellaneous areas that normally occur in a repeatable pattern on the landscape and that can be cartographically shown at the scale mapped. A special soil features layer (point and line features) is optional. This layer displays the location of features too small to delineate at the mapping scale, but they are large enough and contrasting enough to significantly influence use and management. The soil map units are linked to attributes in the National Soil Information System relational database, which gives the proportionate extent of the component soils and their properties.

Indian Regions Soil Image Database (IRSID) : A dataset for classification of Indian soil types

Version 3.1 of the ISRIC-WISE database (WISE3) was compiled from a wide range of soil profile data collected by many soil professionals worldwide. All profiles have been harmonized with respect to the original Legend (1974) and Revised Legend (1988) of FAO-Unesco. Thereby, the primary soil data ─ and any secondary data derived from them ─ can be linked using GIS to the spatial units of the digitized Soil Map of the World as well as more recent digital Soil and Terrain (SOTER) databases through the soil legend code. WISE3 holds selected attribute data for some 10,250 soil profiles, with some 47,800 horizons, from 149 countries. Individual profiles have been sampled, described, and analyzed according to methods and standards in use in the originating countries. There is no uniform set of properties for which all profiles have analytical data, generally because only selected measurements were planned during the original surveys. Methods used for laboratory determinations of specific soil properties vary between laboratories and over time; sometimes, results for the same property cannot be compared directly. WISE3 will inevitably include gaps, being a compilation of legacy soil data derived from traditional soil survey, which can be of a taxonomic, geographic, and soil analytical nature. As a result, the amount of data available for modelling is sometimes much less than expected. Adroit use of the data, however, will permit a wide range of agricultural and environmental applications at a global and continental scale (1:500 000 and broader). Preferred citation: Batjes NH 2009. Harmonized soil profile data for applications at global and continental scales: updates to the WISE database. Soil Use and Management 5:124–127, http://dx.doi.org/10.1111/j.1475-2743.2009.00202.x

This data set is a digital soil survey and generally is the most detailed level of soil geographic data developed by the National Cooperative Soil Survey. The information was prepared by digitizing maps, by compiling information onto a planimetric correct base and digitizing, or by revising digitized maps using remotely sensed and other information. This data set consists of georeferenced digital map data and computerized attribute data. The map data are in a soil survey area extent format and include a detailed, field verified inventory of soils and miscellaneous areas that normally occur in a repeatable pattern on the landscape and that can be cartographically shown at the scale mapped. A special soil features layer (point and line features) is optional. This layer displays the location of features too small to delineate at the mapping scale, but they are large enough and contrasting enough to significantly influence use and management. The soil map units are linked to attributes in the National Soil Information System relational database, which gives the proportionate extent of the component soils and their properties.

This layer shows soil type, based on the result of a classification established from Kalimantan RePPProT data on 'SL_ORDER' field (1990, 1:250,000 scale) . This data was provided and processed by Daemeter Consulting. Soil categories from RePPProT were then re-classified by the World Resources Institute according to the FAO Digital Soil Map of the World, for use in the Suitability Mapper (2012). The FAO data is available at http://www.fao.org/geonetwork/srv/en/metadata.show?id=14116 . Data separated into categories: Inceptisol; Oxisol; Alfisol; Ultisol; Spodosol; Entisol; Histosol.

The soil data used in this map were obtained from profile observations and soil survey from IITA research sites over the last 10-15 years for Nigeria. Additional soil data was obtained from the ISRIC compilation of Africa Soil Profiles Database obtained from soil survey reports and field research conducted in Nigeria

This dataset is a digital soil survey and generally is the most detailed level of soil geographic data developed by the National Cooperative Soil Survey. The information was prepared by digitizing maps, by compiling information onto a planimetric correct base and digitizing, or by revising digitized maps using remotely sensed and other information. This dataset consists of georeferenced digital map data and computerized attribute data. The map data are in a soil survey area extent format and include a detailed, field verified inventory of soils and miscellaneous areas that normally occur in a repeatable pattern on the landscape and that can be cartographically shown at the scale mapped. A special soil features layer (point and line features) is optional. This layer displays the location of features too small to delineate at the mapping scale, but they are large enough and contrasting enough to significantly influence use and management. The soil map units are linked to attributes in the National Soil Information System relational database, which gives the proportionate extent of the component soils and their properties. SSURGO depicts information about the kinds and distribution of soils on the landscape. The soil map and data used in the SSURGO product were prepared by soil scientists as part of the National Cooperative Soil Survey.

Hydric soils are defined as those soils that are sufficiently wet in the upper part to develop anaerobic conditions during the growing season. The Hydric Soils section presents the most current information about hydric soils. The lists of hydric soils were created by using National Soil Information System (NASIS) database selection criteria that were developed by the National Technical Committee for Hydric Soils. These criteria are selected soil properties that are documented in Soil Taxonomy (Soil Survey Staff, 1999) and were designed primarily to generate a list of potentially hydric soils from the National Soil Information System (NASIS) database. It updates information that was previously published in Hydric Soils of the United States and coordinates it with information that has been published in the Federal Register. It also includes the most recent set of field indicators of hydric soils. The database selection criteria are selected soil properties that are documented in Soil Taxonomy and were designed primarily to generate a list of potentially hydric soils from soil survey databases. Only criteria 1, 3, and 4 can be used in the field to determine hydric soils; however, proof of anaerobic conditions must also be obtained for criteria 1, 3, and 4 either through data or best professional judgment (from Tech Note 1). The primary purpose of these selection criteria is to generate a list of soil map unit components that are likely to meet the hydric soil definition. Caution must be used when comparing the list of hydric components to soil survey maps. Many of the soils on the list have ranges in water table depths that allow the soil component to range from hydric to nonhydric depending on the location of the soil within the landscape as described in the map unit. Lists of hydric soils along with soil survey maps are good off-site ancillary tools to assist in wetland determinations, but they are not a substitute for observations made during on-site investigations. The list of field indicators of hydric soils — The field indicators are morphological properties known to be associated with soils that meet the definition of a hydric soil. Presence of one or more field indicators suggests that the processes associated with hydric soil formation have taken place on the site being observed. The field indicators are essential for hydric soil identification because once formed, they persist in the soil during both wet and dry seasonal periods. The Hydric Soil Technical Notes — Contain National Technical Committee for Hydric Soils (NTCHS) updates, insights, standards, and clarifications. Users can query the database by State or by Soil Survey Area. Resources in this dataset:Resource Title: Website Pointer to Hydric Soils . File Name: Web Page, url: https://www.nrcs.usda.gov/wps/portal/nrcs/main/soils/use/hydric/ Includes description of Criteria, Query by State or Soil Survey Area, national Technical Committee for Hydric Soils. Technical Notes, and Related Links. Report Metadata:

• Area_Symbol: A symbol that uniquely identifies a single occurrence of a particular type of area (e.g. Dane Co., Wisconsin is WI025).
• Area_Name: The name given to the specified geographic area.
• mukey: A non-connotative string of characters used to uniquely identify a record in the Mapunit table.
• Mapunit_SYM: The symbol used to uniquely identify the soil mapunit in the soil survey.
• Mapunit_Name: Correlated name of the mapunit (recommended name or field name for surveys in progress).
• Comp_Name_phase: Component name - Name assigned to a component based on its range of properties. Local Phase - Phase criterion to be used at a local level, in conjunction with "component name" to help identify a soil component.
• muacres: The number of acres of a particular mapunit.
• Comp_RV_Pct: The percentage of the component of the mapunit.
• majcompflag: Indicates whether or not a component is a major component in the mapunit.
• Comp_Acres: The number of acres of a particular component in a mapunit. ((muacres*comppct_r)/100)
• Comp_Landform: A word or group of words used to name a feature on the earth's surface, expressed in the plural form. Column Physical
• Hydric_Rating: A yes/no field that indicates whether or not a map unit component is classified as a "hydric soil". If rated as hydric, the specific criteria met are listed in the Component Hydric Criteria table.
• Hydric_criteria: Criterion code for the soil characteristic(s) and/or feature(s) that cause the map unit component to be classified as a "hydric soil." These codes are the paragraph numbers in the hydric soil criteria publication.

Criteria:

1. All Histels except Folistels and Histosols except Folists; or
2. Map unit components in Aquic suborders, great groups, or subgroups, Albolls suborder, Historthels great group, Histoturbels great group, or Andic, Cumulic, Pachic, or Vitrandic subgroups that: a. Based on the range of characteristics for the soil series, will at least in part meet one or more Field Indicators of Hydric Soils in the United States, or b. Show evidence that the soil meets the definition of a hydric soil;
3. Map unit components that are frequently ponded for long duration or very long duration during the growing season that: a. Based on the range of characteristics for the soil series, will at least in part meet one or more Field Indicators of Hydric Soils in the United States, or b. Show evidence that the soil meets the definition of a hydric soil; or
4. Map unit components that are frequently flooded for long duration or very long duration during the growing season that: a. Based on the range of characteristics for the soil series, will at least in part meet one or more Field Indicators of Hydric Soils in the United States, or b. Show evidence that the soils meet the definition of a hydric soil.

This repository provides extended documentation, code, and updated links to access the Soil Landscapes of the United States (SOLUS) 100-meter soil property maps. It provides supporting materials for a peer reviewed paper (Nauman et al., Soil Science Society of America Journal, 1–20. https://doi.org/10.1002/saj2.20769) documenting the theory and novel application of hybridized legacy training datasets used to inform the machine learning models used to create the new soil property maps presented here. The SOLUS dataset includes 20 different soil properties (listed below) with most properties predicted for seven standard depths (0, 5, 15, 30, 60, 100, and 150 cm). Further details on these properties and all included files are available in the README.docx document. Also included is a git repository formatted as a hybrid R package that includes all code used to create the soil property maps. All SOLUS100 mapping layers are available as cloud optimized geotiffs at: https://storage.googleapis.com/solus100pub/index.html Metadata: https://storage.googleapis.com/solus100pub/SOLUS100_metadata_pub.html List of files at this URL are listed at: https://storage.googleapis.com/solus100pub/Final_Layer_Table_20231215.csv Note that many of the raster files are scaled by multipliers of 10, 100, or 1000 to store the values as integers to decrease file size. The ‘scalar’ field of the file list table (Final_Layer_Table_20231215.csv) files provide those values. The actual rasters must be divided by the scalars to get the actual units of the properties. To download files, simply concatenate the google API URL with a forward slash and the file name listed in the table into a browser (e.g. EC at 0 cm would be https://storage.googleapis.com/solus100pub/ec_15_cm_p.tif). To automate downloads, a loop in python, R or your language of choice that builds file download urls from the file list in the csv can be implemented. Alternatively, some GIS programs (e.g. QGIS) will let you visualize and interact with the files without downloading the files by entering the URL. All raster environmental covariates used in mapping are available here: https://storage.googleapis.com/cov100m/index.html Properties included in SOLUS100:

Bulk density (oven dry) Calcium carbonate Cation Exchange Capacity (pH 7) Clay Coarse sand Electrical Conductivity (sat. paste) Effective cation exchange capacity Fine sand Gypsum (in

The Soil Geographical Database of Eurasia at Scale 1:1,000,000 is part of the European Soil Information System (EUSIS). It is the resulting product of a collaborative project involving all the European Union and neighboring countries. It is a simplified representation of the diversity and spatial variability of the soil coverage. The methodology used to differentiate and name the main soil types is based on the terminology of the F.A.O. legend for the Soil Map of the World at Scale 1:5,000,000. This terminology has been refined and adapted to take account of the specificities of the landscapes in Eurasia. It is itself founded on the distinction of the main pedogenetic processes leading to soil differentiation: brunification, lessivage, podzolisation, hydromorphy, etc.

These Soil Mapping Data Packages include 1. a Soil Map dataset which includes the equivalents to Soil Project Boundaries, Soil Survey Spatial View mapping polygons with attributes from the Soil Name and Layer Files, plus + A Soil Site dataset which includes soil pit site information and detailed soil pit descriptions and any associated lab analyses, and + The Soil Data Dictionary which documents the fields and allowable codes within the data. The Soil Map geodatabase contains the 'best available' data ranging from 1:20,000 scale to 1:250,000 scale with overlapping data removed. The choice of the datasets that remain is based on connectivity to the soil attributes (soil name and layer files), map scale and survey date. (Note: the BC Soil Landscapes of Canada (BCSLC) 1:1,000,000 data has not been included in the Soil_Map or SIFT, but is available from: CANSIS. (A complete soils data package with overlapping soil survey mapping and BCSLC is available on request. Note that the soil survey data with attributes can also be viewed interactively in the [Soil Information Finder Tool](The Soil Map dataset is also available for interactive map viewing or as KMZs from the Soil Information Finder Tool website.

Soil Classification Datasets

Please ensure to cite the paper when utilizing the dataset in a research study. Refer to the paper link or BibTeX provided below.

This repository contains comprehensive datasets for soil classification and recognition research. The Original Dataset comprises soil images sourced from various online repositories, which have been meticulously cleaned and preprocessed to ensure data quality and consistency. To enhance the dataset's size and diversity, we employed Generative Adversarial Networks (GANs), specifically the CycleGAN architecture, to generate synthetic soil images. This augmented collection is referred to as the CyAUG Dataset. Both datasets are specifically designed to advance research in soil classification and recognition using state-of-the-art deep learning methodologies.

This dataset was curated as part of the research study titled "An advanced artificial intelligence framework integrating ensembled convolutional neural networks and Vision Transformers for precise soil classification with adaptive fuzzy logic-based crop recommendations" by Farhan Sheth, Priya Mathur, Amit Kumar Gupta, and Sandeep Chaurasia, published in Engineering Applications of Artificial Intelligence.

Links

• Paper: An advanced artificial intelligence framework integrating ensembled convolutional neural networks and Vision Transformers for precise soil classification with adaptive fuzzy logic-based crop recommendations
• Code: Development Code (model and recommendation system)

Application produced by this research is available at:

• Agro Companion: Agro Companion
• Server Code: Agro Companion Server

Note: If you are using any part of this project; dataset, code, application, then please cite the work as mentioned in the Citation section below.

Dataset

Both dataset consists of images of 7 different soil types.

The Soil Classification Dataset is structured to facilitate the classification of various soil types based on images. The dataset includes images of the following soil types:

• Alluvial Soil
• Black Soil
• Laterite Soil
• Red Soil
• Yellow Soil
• Arid Soil
• Mountain Soil

The dataset is organized into folders, each named after a specific soil type, containing images of that soil type. The images vary in resolution and quality, providing a diverse set of examples for training and testing classification models.

Original Dataset Details

• Total Images: 1189 images
• Image Format: JPG/JPEG
• Image Size: Varies
• Source: Collected from various online repositories and cleaned for consistency.

CyAUG Dataset Details

• Total Images: 5097 images
• Image Format: JPG/JPEG
• Image Size: Varies
• Source: Generated using CycleGAN to augment the original dataset, enhancing its size and diversity.

Input and Output Parameters

• Input Parameters:
  • Image: The images of the soils (JPG/JPEG format).
  • Label: The labels are in the format 'soil types' (folder names).
• Output Parameter:
  • Classification: The predicted class (soil type) based on the input image.

Citation

If you are using any of the derived dataset, please cite the following paper:

@article{SHETH2025111425,
  title = {An advanced artificial intelligence framework integrating ensembled convolutional neural networks and Vision Transformers for precise soil classification with adaptive fuzzy logic-based crop recommendations},
  journal = {Engineering Applications of Artificial Intelligence},
  volume = {158},
  pages = {111425},
  year = {2025},
  issn = {0952-1976},
  doi = {https://doi.org/10.1016/j.engappai.2025.111425},
  url = {https://www.sciencedirect.com/science/article/pii/S0952197625014277},
  author = {Farhan Sheth and Priya Mathur and Amit Kumar Gupta and Sandeep Chaurasia},
  keywords = {Soil classification, Crop recommendation, Vision transformers, Convolutional neural network, Transfer learning, Fuzzy logic}
}