About the Number of iterations in the simulation tab

QGIS Plugins MOLUSCE
1

Good day, everyone. First of all, I’m sorry for the long chat. I am an undergraduate student, and I have a study where I am going to use y2019, y2022, and y2025 to predict y2028, y2031, and y2034. And my scope and delimitation was a business-as-usual scenario. (Still inputting in the Set separate spatial variables version for simulation factors: dasymetric map of y2022, prox to builtup y2022)
Regarding the MOLUSCE, I am confused with the number of iterations in the simulation tab.

  1. How does MOLUSCE process the number of iterations of simulation?
  2. Does it remembers the first iteration and use that as an initial step to forecast the 2nd iteration, and remember the 2nd iteration to forecast the 3rd iteration, and so on?
    I am confused about this.
  3. Do I need to make a step-wise method (note sure what to call it) to create more simulations? Just like in the study “Spatiotemporal Change Analysis and Prediction of Future Land Use and Land Cover Changes Using QGIS MOLUSCE Plugin and Remote Sensing Big Data: A Case Study of Linyi, China.”
    “After obtaining satisfactory results from the model validation, we employed LULC data from 2010 and 2020 to forecast the LULC in 2030, and the LULC of 2000 and 2020 for 2040. The predicted data for 2030 and 2040 were used to forecast LULC for 2050.”
  4. Do I need to do this as well?
2

This was answered here:

The logic here is quite straightforward. The number of iterations always refers to the current initial and final years set in the inputs tab.

If you have 2019 and 2022 there, then iterations= 1 will produce forecast for 2025, iterations=2 for 2028 etc., but all based on the spatial variables set in the current molusce session.

If you want to use separate versions of factors on each step, then you should always use iterations number = 1, each time setting up a separate molusce session. In such a case you also could save the model got on the first session, and then reuse it for different years (using proper versions of spatial variables each time)