TOOLS
Our team developed geospatial tools to enhance your geospatial analysis, streamlining processes for greater speed, accuracy, and automation.
1. Optimal scaling of predictors for digital mapping of soil properties
Purpose and use: This script enhances soil property mapping accuracy by optimizing terrain attribute scaling using Random Forests (RF). It demonstrated the effectiveness of optimized scaling for nine soil properties.
The script resamples a digital elevation model (DEM) at multiple resolutions and finds the optimal scales for each terrain attribute specific to each soil property.
Inputs: DEM and geolocated points with soil properties measurements (.shp file).
Outputs: Raster file (.tif) of each terrain attribute optimally scaled for each soil property, and table with the associated optimal scales.
Programming environment: R
Status of work: Public domain
Reference: Dornik A, Cheţan MA, Drăguţ L, Dicu DD, Iliuţă A, 2022, Optimal scaling of predictors for digital mapping of soil properties, Geoderma (IF 6.1; AIS 1.221; Q1), 405:115453, DOI: 10.1016/j.geoderma.2021.115453
2. Transformation (normalization) of morphometric variables
Purpose and use: Automated procedures are developed to alleviate long tails in frequency distributions of morphometric variables. They minimize the skewness of slope gradient frequency distributions and modify the kurtosis of profile and plan curvature distributions towards that of the Gaussian (normal) model. Box-Cox (for slope) and arctangent (for curvature) transformations are used. The transforms are applicable to morphometric variables and many others with skewed or long-tailed distributions. It is suggested that such transformations should be routinely applied in all parametric analyses of long-tailed variables. Our Box-Cox and curvature automated transformations are based on a Python script, implemented as an easy-to-use script tool in ArcGIS.
Inputs: Slope raster or curvature raster; any other variables with skewed or long-tailed distributions.
Outputs: Normalized slope or curvature raster; a text file informing about transformation used and new skewness/kurtosis.
Programming environment: Python
Status of work: Public domain
Reference: Csillik, O., Evans, I.S., Dragut, L., Transformation (normalization) of slope gradient and surface curvatures, automated for statistical analyses from DEMs, Geomorphology (2015), doi: 10.1016/j.geomorph.2014.12.038
INSTRUCTIONS
WARNING: The current version has been tested on ArcGIS versions 10.1 and 10.2. It will not work for versions below 10.
To use the Transformation Toolbox for ArcMap, complete the following steps:
1. Download the Transformation Toolbox upper on this page.
2. Move the zip file to the directory where you want to store the toolbox.
3. Extract the contents of the zip file.
4. The tool needs to use numpy package for Python.
For ArcGIS version 10.1+, Python 2.7 is install by default and you can download numpy package from HERE.
For ArcGIS version 10.0, Python 2.6.5 is install by default and you can download numpy package from HERE.
5. Open ArcMap, and click Geoprocessing > ArcToolbox.
6. Right-click the ArcToolbox window, and click Add Toolbox.
7. In the Add Toolbox window, click the Connect to Folder icon and navigate to the location of the toolbox. Select the Transformation tools.tbx and click Open. The Transformation tools appears in the ArcToolbox window.
8. Start using the tools!
3. Automated Estimation of Scale Parameter (ESP2) tool
Purpose and use: This is an automated version of ESP. The tool works on multiple layers (maximum of 30) and produces fully automatically three scale levels, based on the concept of Local Variance (Woodcock and Strahler, 1987).
Status of work: Public Domain
The download package contains:
• ESP2_Estimation_Scale_Parameter_2.dcp (encrypted eCognition rule-set)
• ESP2_User_Guide.pdf
• ESP_Estimation_Scale_Parameter_Chart.exe (a stand-alone tool for visualizing and interpreting the results. This tool is programmed in .NET, therefore the .NET framework needs to be installed on your machine if you want to interpret the results (optional, for advanced users).
• ZedGraph.dll (a dynamic link library which is needed to run the ESP_Estimation_Scale_Parameter_Chart.exe tool)
Reference: Drăguţ, L., Csillik, O., Eisank, C., Tiede, D., 2014. Automated parameterisation for multi-scale image segmentation on multiple layers. ISPRS Journal of Photogrammetry and Remote Sensing 88, 119-127.
4. Estimation of Scale Parameter (ESP) tool
Purpose and use: Customized algorithm for eCognition 8 or Definiens Developer version 7 to help the user in estimating the appropriate scales for segmentation, based on the concept of Local Variance (Woodcock and Strahler, 1987). The tool performs iterative segmentations in user-defined increments and ranges and calculates local variance (LV) for each level. LV graphs are displayed in a stand-alone tool. A user guide is attached.
Programming environment: CNL (Cognition Network Language) & C#
Requirements: .NET framework
Status of work: Public Domain
Reference: Dragut, Lucian, Tiede, Dirk and Levick, Shaun R., 2010. ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data, International Journal of Geographical Information Science, Vol. 24, Iss. 6, 859-871
5. Physiographic Classification tool
Reference: Dragut, L., Eisank, C., 2012. Automated object-based classification of topography from SRTM data, Geomorphology, 141–142, 21-33.
