MOLUSCE – quick and convenient analysis of land cover changes

Important: MOLUSCE is for QGIS 2.x only. We don’t provide support for MOLUSCE.

Together with Asia Air Survey we’ve developed MOLUSCE (Modules for Land Use Change Simulations) – a new tool based on QGIS that allows to perform quick and convenient analysis of land cover changes.

A researcher who analyses changes in landscape through time often deals with questions like:

  • What are the changes and where did they happen?
  • Which factors can explain the changes and strong is their explanatory power?
  • What changes are expected in future and where?

The answer for the first question can be obtained by visual estimation, but to answer other questions one will need to set hypothises, verify them, derive conclusions and see how they meet the reality.

MOLUSCE is a toolbox to partially automate the process of answering such questions.

700px-Molusce-ANN

Briefly, the workflow consists of the following steps:

  1. Obtain landcover map for few time slices and  a set of potential explanatory variables;
  2. Calculate probabilities of transitions from class to class;
  3. Build a model using ANN, logistic regression, Weights of evidence or Multi-criteria evaluation to describe transitions based on factor variables;
  4. Use this model for forecasting;
  5. Validate the result with real data.

Find more information in GIS-Lab article (Russian, autotranslated).

122 responses to “MOLUSCE – quick and convenient analysis of land cover changes”

  1. kimara says:

    Hi when I am uploading my inputs into MOLUSCE it is giving me memory error “Memory error occurred. Perhaps the system is low on memory” . Please advise how I may go about resolving this issue.Thanks

  2. ASHIK MAHMUD says:

    IS THE TEMPORAL GAP FROM PAST TO PRESENT AND PRESENT TO FUTURE SIMULATION FIXED FOR MOLUSCE ?

  3. Warren says:

    Hi there. Thanks for all the information on MOLUSCE thus far. I am busy preparing all my layers and was wondering where I could find a tutorial for preparing my spatial variables, i.e., how each input spatial variable should be classed. Any help would be greatly appreciated 🙂

  4. َAzin says:

    hello
    1-how can i use 3 or 4 period of a Urban to train Ann? for example 1980,1990 , 2000, 2010 then Validate with 2018 .
    2-how can i select the epoch or epochs to simulate ?
    for example Molusce determine simulate map of 2020,2030,2040,2050
    3- wich time molusce simulate for me ?
    Best regards

  5. َAzin1 says:

    hello
    1-how can i use 3 or 4 period of a Urban to train Ann? for example 1980,1990 , 2000, 2010 then Validate with 2018 .
    2-how can i select the epoch or epochs to simulate ?
    for example Molusce determine simulate map of 2020,2030,2040,2050
    3- wich time molusce simulate for me ?
    Best regards

  6. siham says:

    Hi,
    please what’s the difference between the four models (ANN, WOE, LR, MCE), i run all of them for a land cover map,but it gives me the same area for land cover for each map
    Thank you

  7. palarifeendu says:

    I have a problem during map validation for prediction purpose in QGIS 2.18 (validate the simulated map with the actual map). It showed an error message “error occurred while executing python code.” I have added the screenshot and the message is yellow highlighted. Please, suggest me to overcome the problem.

  8. palarifeendu says:

    The problem is different geometry of reference and simulated map. I have prepared initial, final map and variables in same geometry which are matched. But, the simulated map’s geometry is different. How to solve this problem?

  9. Salsabeel says:

    I’m trying to use MOLUSCE Plugin for prediction of Land use expansion, I prepared and added the variables’ layers required for it but at 3rd step that is ‘Area Changes’ when I try to ‘Update Table’, ValueError keeps occurring.

    “ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()”

    I’m new to QGIS and don’t know Python either, could anyone suggest a solution to this problem? I’m using QGIS 2.18.28 and Land cover data for 1998 and 2008 with road distance and DEM variables.

  10. IZZATI says:

    Hai.. i’m worried about my data because i just have 3 data landuse.. land-use 1966,1997 and 2015 . I’m trying to use MOLUSCE plugin for the land use simulation but could’t find the exact year to predict cause the big gap between year.

Leave a Reply

Your email address will not be published. Required fields are marked *