What's New in IDRISI Selva

IDRISI Selva is the 17th version of the IDRISI GIS and Image Processing software. This version includes a variety of enhancements to the display subsystem of the IDRISI suite, including image pyramids and support for large images. Significant additions and enhancements have been made to both Land Change Modeler and to Earth Trends Modeler.

Download the What’s New Brochure for more detail on this latest version of IDRISI.

Land Change Modeler Enhancements

The Land Change Modeler has become a major tool for many of our users and with this release we have expanded and enhanced its capabilities. These include:

  • A new REDD tab to support projects aimed at Reducing Emissions from Deforestation and Forest Degradation. The new REDD tab is intended to support the various methodologies being reviewed and approved by the Verified Carbon Standard (VCS) for the voluntary market. The REDD tab facilitates the estimation of baseline emissions from various carbon pools and allows the calculation of deferred emissions and carbon credits.

  • A pioneering new land cover change modeling procedure, SimWeight, a machine learning procedure that has proven to yield results that rival that of the Multi-Layer Perceptron (MLP) with minimal (and easily understood) parameters.

  • Changes have been made to the MLP neural network modeling procedure. We have resolved the major issue of exposing the explanatory power of the independent variables and opening the black-box associated with this routine. The user now has feedback on both the general model and the independent variables. General model information now includes a skill measure to accompany the overall accuracy level of the model. The skill measure is based on the analysis of the validation data. The most significant addition is a sensitivity analysis of the independent variables used in the model. This analysis evaluates the quality of the independent variables and those that could be excluded from the model.

  • A new land cover preprocessing procedure called Harmonize that coordinates the land cover layers in terms of their spatial characteristics, background masks and categorizations.

  • An integrated link to the popular MAXENT procedure for species distribution modeling.

Earth Trends Modeler Enhancements

With the Selva release we have incorporated a major expansion of our spectral decomposition capabilities in Earth Trends Modeler, continuing IDRISI’s ground breaking leadership in Earth System Information Science for climate change and ecosystem dynamics.

  • Principal Components Analysis (PCA) and Empirical Orthogonal Teleconnection (EOT) analysis now offer extended modes where multiple data series can be analyzed simultaneously.

  • Multichannel Singular Spectrum Analysis (MSSA) and Multichannel Empirical Teleconnection analysis are now included analyzing patterns that evolve in space and time.

  • All Principal Components Analysis procedures now offer both T-mode and S-mode orientations for analysis – the first GIS/Image Processing software system to offer both.

  • Both Principal Components Analysis (PCA) and Empirical Orthogonal Teleconnection (EOT) analysis now have the option to uncenter the analysis, i.e., the option to remove the mean from a data set.

  • A new procedure for Canonical Correlation Analysis (CCA).

  • A change to the Fourier-PCA routine to perform the analysis in S-mode rather than in T-mode.

  • A Contextual Mann-Kendall (CMK) trend significance measure has been added to the Seasonal Trend Analysis procedure.

  • When viewing one-dimensional time series graphs, such as from PCA, you can now interactively slide the second series forwards or backwards in time and display the lagged correlation between the two series.

  • For missing data interpolation we have extended the linear interpolation option to allow bridging over gaps of any specified duration (as opposed to just one-time-slice gaps).

  • The Inverse PCA denoising option now also offers a choice between S-mode and T-mode.

  • The Generate/Edit series options now also include a spatial subsetting tool.

Display Enhancements

Probably the most immediately noticeable features of Selva are the new display elements. These include:

  • An auto-arrange feature whereby IDRISI automatically arranges map elements such as titles, legends, scale bar, insets, etcetera.

  • The Composer window has changed; besides a new a new interface design, it is sizeable in order to better handle long file names and compositions with many layers.

  • Map windows can now be very simply resized by pulling out or pushing in the lower-right corner.

  • With the Selva edition, IDRISI breaks through the Windows 32-bit display architecture, with the ability to now display images much greater that 32,000 rows and columns, depending on your hardware.

  • To support the rapid display of large images, IDRISI has also introduced support for an image pyramid – a multiple resolution image that allows the rapid display of large images regardless of the level of zoom.

  • Another new display feature is the ability to display vector fields. The inputs can be of two types – a magnitude and direction force pair (such as slope and aspect) or as the X and Y (U and V) components of the force.

New Analytical Modules

Changes have also been made to the extensive set of independent analytical modules IDRISI provides. These and other additions include:

  • A Radial Basis Function (RBF) neural network classifier has been added to complement the existing suite of neural network classifiers.

  • A Chain Clustering procedure has been added to the basic clustering tools available in IDRISI.

  • A Durbin-Watson module has been added independently of ETM to map locations where serial correlation is present.

  • A new high-precision rank-and-slice technique has been added to help support decision making procedures. It pulls out the top ranked pixels according to a specified threshold and is incorporated in to Land Change Modeler for land allocation and as a stand-alone module.

  • A revised PCA module offering distinctions between S-mode and T-mode even for multivariate cases not involving time series. The options for standardized/unstandardized, centered/ uncentered and forward/inverse transformation are also included.

  • A general purpose Canonical Correlation Analysis procedure has been added for the analysis of pairs of data sets.

New or Revised Import/Export Modules

  • Support for KML files (Keyhole Markup language, used by Google) has now been extended to include the import and export of point, line and polygon files as well as raster images.

  • An import routine to convert MODIS tiled imagery to IDRISI raster format. The files are imported and then the tiles are mosaicked, with options to mosaic tiles of different geographic extent.

  • The import utility for MODIS Quality Control data has been extended. Quality control maps can now be generated for vegetation indices using MODIS collection 5, land surface temperature collections 4 and 5, and Albedo collection 5.

Improved Modules

Every so often we take the opportunity to substantially revise modules that we think could benefit from a different approach. With the Selva release, we have focused on the core of the distance-based routines – DISTANCE, COST, VARCOST, DISPERSE and BUFFER. The optimization is substantial, with most routines running considerably faster.


An example of temporal profiling (of NDVI anomalies in southeast Massachusetts) followed by subsequent analysis of its relationship with global sea surface temperatures using the linear modeling tool. 

Back to Top

Image Segmentation Analysis using Aerial Imagery (.5 m) with IDRISI Taiga

The SEGMENTATION module creates an image of segments that have spectral similarity across many input bands. The image on the left uses a larger similarity threshold than the one on the right, resulting in more generalized, less homogeneous segments. Using this threshold, the image allows for segments that wholly contain building objects.  

Back to Top


Validation allows you to assess the quality of your prediction model. In this example, a model was developed to predict forest cover loss to 2004 based on historical patterns. We predicted from a known state in 2001 to 2004 and validated the prediction map to a known state in 2004. The validation map shows the hits (green), misses (red), and false alarms (yellow) of our model.   

Back to Top

Clark University