GIS Modeling

The modules found in the Modeling menu unleash the power of raster analysis in IDRISI. Most of these modules are also found elsewhere in the menu structure. Modules are organized into three groups: model deployment tools, empirical model development tools and environmental/simulation models.

Model Deployment ToolsIncludes modules for deploying conceptual, theoretical or existing mathematical or logical models.

Image Calculator - probably the most direct and easily understood model deployment tool. A mathematical and logical calculator that uses map layers as variables.
Macro Modeler - a very mature graphical modeling interface for more involved algorithmic models. Macro Modeler exposes all of IDRISI's GIS modules as objects that can be linked, dynamically and with feedbacks, with map layers in an algorithmic chain.
COM/API - for the most demanding of algorithmic modeling applications, or for the development of stand-alone modules as add-ons to IDRISI, a scripting language such as Python or a full programming language such as C++, Delphi or Visual Basic can be used. In these cases, users can access IDRISI though the industry-standard COM object model interface. Using COM, client applications can be written that control all aspects of IDRISI's operations.
Run Macro - macro scripting language for simpler modeling tasks.

There are also quick links to the main tools used for multi-criteria evaluation (MCE), WEIGHT, and FUZZY because of the frequency with which they are applied to create expert opinion models.

Empirical Model Development ToolsIncludes modules for the empirical development of models from exemplars. Modeling procedures are provided to analyze examples of known cases and their relationship between a phenomenon of interest and a set of explanatory variables, most commonly called training data. Depending on the nature of the data, models can be developed with Presence Data, Presence/Absence Data, or Abundance/Frequency/Value Data.

Presence Data - cases where we do not know where the phenomenon is, only when it occurs. A classic example of this is the modeling of species distributions from reports of animal sightings. Few techniques exist for handling data of this character. However, IDRISI provides the Mahalanobis Typicalities (MAHALCLASS) soft classifier (which requires prior signature analysis using the module MAKESIG) which works exceptionally with this kind of data.
Presence/Absence Data - cases where we have both presence and absence data for our exemplars. A wide range of modeling techniques can be applied including logistic (LOGISTICREG) and multinomial logistic (MULTILOGISTRICREG) regression, multivariate image classification procedures (BAYCLASS, FISHER) and machine learning techniques such as neural networks (MLP, SOM, Fuzzy ARTMAP) and classification trees (CTA).
Abundance/Frequency/Value Data - affords the use of tools such as single (REGRESS) or multivariate (MULTIREG) regression.

Environmental/Simulation Models

Includes a set of established models/modeling environments associated with specific application areas--land cover change, surface water runoff, and soil erosion--that have been implemented in the IDRISI system.

LCM (Land Change Modeler for Ecological Sustainability) - an integrated software environment for analyzing land cover change, projecting its course into the future, and assessing its implications for habitat and biodiversity change.
GEOMOD - a landuse change simulation model that predicts the locations of grid cells that change over time.
CA_MARKOV – a combined cellular automata / Markov change land cover prediction procedure that adds an element of spatial contiguity as well as knowledge of the likely spatial distribution of transitions to Markov change analysis.
RUSLE (Revised Universal Soil Loss Equation) - simulates farmland and rangeland nonchannelized soil loss by water.
RUNOFF - calculates the accumulation of rainfall units per pixel as if one unit of rainfall was dropped on every location.
SEDIMENTATION - evaluates the net soil movement (erosion or deposition) within patches, fields, or river basins (catchments).


The IDRISI Macro Modeler provides a graphic environment for the construction of models. Facilities are included for batch processing of multiple images through the same model and for iterative processing with the output of one iteration becoming an input to the next.


Complex models may be evaluated in one step using the Image Calculator. This set of screenshots shows the result of a multi-criteria vulnerability analysis for West Africa. Factors included cost-distance from markets (lower right).


IDRISI is 100% COM compliant, allowing programmers full control over its operation. The documentation for the Application Programming Interface is included with IDRISI and may be accessed from the Modeling menu.