nextgis/molusce

Modules for Land Use Change Simulations

MOLUSCE

MOLUSCE (Modules for Land Use Change Simulations)

Plugin provides a set of algorithms for land use change simulations such as ANN, LR, WoE, MCE as well as validation using kappa statistics.

Developed by Asia Air Survey (http://www.asiaairsurvey.com) and NextGIS (http://nextgis.com).

Homepage: https://github.com/nextgis/molusce

Quickhelp (PDF):

• English: https://github.com/nextgis/molusce/tree/master/doc/en
• Portuguese: http://ecojustus.com.br/molusce-guia-rapido/
• Russian: http://gis-lab.info/qa/molusce-intro-ru.html

License

This program is licensed under GNU GPL v2 or any later version

Commercial support

Need to fix a bug or add a feature to MOLUSCE?

We provide custom development and support for this software. Contact us to discuss options!

molusce's Issues

Prevent simulation if raster geometries do not match

Even when "check geometry" fails, it allows to proceed. Still when trying to run the simulation, it is crashing. As simulation part can not be performed if geometries do not match, the module should not allow to start simulation unless check passes.

MOLUSCE error

I tried using the molusce plugin to forecast the water index (NDWI) for my study area. Can I use this plugin for this purpose? When I feed the initial year indices it shows the following error "The raster has a lot of variables. Does the raster store a nominal variable?" I have divided the index values into 4 classes.

MOLUSCE Simulated map does not show changes using Multi Criteria Evaluation Method

I use an initial map from 2007 and a final map from 2010 and two variables in order to predict a map for 2013, using the Multi Criteria Evaluation method. When I do the simulation for 2013, the map that I get is exactly the same that the one used as a final map (2010). This happens both using only two categories (0-no artificial use; 1-artificial use) and using 4 categories.
What could be the problem?

Stochastic simulations

Hi,

I've been using MOLUSCE to simulate land uses. I wonder how does the software perform the cellular automata simulations. If I'm right the land use transitions are based on a 'potential transition value', calculated via any transition model implemented, for each cell which is a probability to change to another land use. So I would expect each time the simulation is run it gets slightly different results based on the potential transitions, but I get always the same results.

Does the software perform any kind of mean of the results? Or is it implementing a deterministic algorithm? And the main question, is it possible to simulate different results based on the potential transition values?

Cheers

Dani

MOLUSCE Transition Matrix table (Area Changes)

Is it possible to modify transition matrix table?

What are the effect of these changes on MOLUSCE?

Moved from here: https://hub.qgis.org/issues/9878

Molusce tab not highlighted and cannot be used

I have an issue using the molusce plugging on my QGIS 2.18.11. The tabs for evaluating correlation, area changes, transition potential modelling, cellular automata simulation and validation are not highlighted and could not be used. its only inputs and messages tabs that are highlighted on the task bar. Can anyone kindly help me with this? Thank you in advance

Pyhton Memory Error while running MOLUSCE plugin

I have been trying to use MOLUSCE plugin. The plugin shows Python Memory error when I tried to train the ANN for Transition Potential Modelling. I saw a suggestion for using appropriate coordinate system for the raster data sets which will use the Earth as a flat surface. So I converted all my raster to same UTM projection. Same problem occurred again at the same step. The error code looks like following:
2019-08-28T11:39:14 1 Traceback (most recent call last):
File "C:/Users/GISLab08/.qgis2/python/plugins\molusce\neuralnetworkwidget.py", line 138, in trainNetwork
samples=self.plugin.spnSamplesCount.value()
File "C:/Users/GISLab08/.qgis2/python/plugins\molusce\algorithms\models\mlp\manager.py", line 341, in setTrainingData
f.normalize(mode = 'mean')
File "C:/Users/GISLab08/.qgis2/python/plugins\molusce\algorithms\dataprovider.py", line 257, in normalize
stat = self.getBandStat(i)
File "C:/Users/GISLab08/.qgis2/python/plugins\molusce\algorithms\dataprovider.py", line 163, in getBandStat
result['mean'] = np.ma.mean(band)
File "C:\PROGRA2\QGIS21.18\apps\Python27\lib\site-packages\numpy\ma\core.py", line 6354, in call
return method(*args, **params)
File "C:\PROGRA2\QGIS21.18\apps\Python27\lib\site-packages\numpy\ma\core.py", line 5065, in mean
dsum = self.sum(axis=axis, dtype=dtype)
File "C:\PROGRA2\QGIS21.18\apps\Python27\lib\site-packages\numpy\ma\core.py", line 4820, in sum
result = self.filled(0).sum(axis, dtype=dtype)
File "C:\PROGRA2\QGIS21.18\apps\Python27\lib\site-packages\numpy\ma\core.py", line 3635, in filled
result = self._data.copy('K')
MemoryError

MOLUSCE plugin pythan memory error

hello guys, I m using Qgis 2.16 in windows 10. In using Molusce plugin i am facing problem in Validation tab the error shows is:-
MemoryError
Traceback (most recent call last):
File "C:/Users/gaurav jaiswal/.qgis2/python/plugins\molusce\moluscedialog.py", line 648, in startValidation
self.eb = EBudget(reference, simulated)
File "C:/Users/gaurav jaiswal/.qgis2/python/plugins\molusce\algorithms\models\errorbudget\ebmodel.py", line 90, in init
self.Sj[j] = 1.0*binaryzation(S, [j])
File "C:\PROGRA2\QGIS 2.16\apps\Python27\lib\site-packages\numpy\ma\core.py", line 3947, in rmul
return multiply(other, self)
File "C:\PROGRA2\QGIS 2.16\apps\Python27\lib\site-packages\numpy\ma\core.py", line 966, in call
result = self.f(da, db, *args, **kwargs)
MemoryError

Python version: 2.7.4 (default, Apr 6 2013, 19:54:46) [MSC v.1500 32 bit (Intel)]
QGIS version: 2.16.3 Nødebo, 7d00cae

I m not able to proceed further pls help me
Gaurav

Molusce documentation

hi all, firstly ı need documentation to learn molusce. any suggestions ı will be appreciated.

MOLUSCE: Edit curves line and axes parameter error in canvas matplotlib

Curves line and axes parameter function in Transition Potential Modeling tab is not working.

Moved from: https://hub.qgis.org/issues/9728

Wrong raster

Traceback (chamada mais recente passada):
Arquivo "C: /Users/win7/.qgis2/python/plugins \ molusce \ moluscedialog.py" linha 467, em createChangeMap
self.analyst = AreaAnalyst (self.inputs [ "inicial"], self.inputs [ "final"])
Arquivo "C: /Users/win7/.qgis2/python/plugins \ molusce \ algoritmos \ modelos \ area_analysis \ manager.py", linha 62, em init
AreaAnalizerError levantar ( "Lista de categorias do primeiro raster não contém uma categoria da segunda raster")
AreaAnalizerError

Thanks !

The MOLUSCE plugin predict the same area that the final map of Land Use

MOLUSCE creates the prediction map the same as the final land use map. I have land use maps for the year 2003 and 2010. The map of the simulation should be for the year 2017.

QGIS Molusce plugin error: Change area crosstable is not being created!

File "C:/Users/shinj/.qgis2/python/plugins\molusce\algorithms\models\crosstabs\model.py", line 125, in getSumRows

crosstable = self.getCrosstable()

File "C:/Users/shinj/.qgis2/python/plugins\molusce\algorithms\models\crosstabs\model.py", line 86, in getCrosstable

if self._T == None:

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

Error updating tables when there is only one land use class in input raster

Hi.

I have two very big land use raster. I can 'update tables' in the 'area changes' tab but it takes too long to do the simulations. Then I clipped the rasters to speed it up, but I get the following error when I click 'update tables':

Ha ocurrido un error mientras se ejecutaba el código de Python:

Traceback (most recent call last):
File "/Users/dani/.qgis2/python/plugins/molusce/moluscedialog.py", line 413, in updateStatisticsTableDone
self.__drawTransitionStat()
File "/Users/dani/.qgis2/python/plugins/molusce/moluscedialog.py", line 1027, in __drawTransitionStat
stat = self.inputs["crosstab"].getTransitionStat()
File "/Users/dani/.qgis2/python/plugins/molusce/algorithms/models/crosstabs/manager.py", line 91, in getTransitionStat
deltas = finalArea - initArea
ValueError: operands could not be broadcast together with shapes (30) (29)

Versión de Python:
2.7.10 (default, Oct 23 2015, 18:05:06)
[GCC 4.2.1 Compatible Apple LLVM 7.0.0 (clang-700.0.59.5)]

Versión de QGIS:
2.8.1-Wien Wien,

Ruta de Python: ['/Applications/QGIS.app/Contents/MacOS/../Resources/python/plugins/processing', '/Users/dani/.qgis2/python/plugins/esstoolkit/external', '/Applications/QGIS.app/Contents/MacOS/../Resources/python', u'/Users/dani/.qgis2/python', u'/Users/dani/.qgis2/python/plugins', '/Applications/QGIS.app/Contents/MacOS/../Resources/python/plugins', '/Library/Frameworks/SQLite3.framework/Versions/C/Python/2.7', '/Library/Frameworks/GEOS.framework/Versions/3/Python/2.7', '/Library/Python/2.7/site-packages/numpy-override', '/Library/Python/2.7/site-packages/matplotlib-override', '/Library/Frameworks/GDAL.framework/Versions/1.11/Python/2.7/site-packages', '/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python27.zip', '/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7', '/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/plat-darwin', '/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/plat-mac', '/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/plat-mac/lib-scriptpackages', '/System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python', '/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/lib-tk', '/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/lib-old', '/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/lib-dynload', '/System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python/PyObjC', '/Library/Python/2.7/site-packages', u'/Users/dani/.qgis2//python', '/Applications/QGIS.app/Contents/Resources/python/plugins/fTools/tools', '/Users/dani/SIG/proyectos']

Better error message for missing class situation

If one class is missing from one of the input maps there is an Python error message (see #12).

MOLUSCE should provide more user friendly message in this case. Something like:

Classes do not match. Consider sending the pixels with the class that is missing to NODATA

Future Warning

Once again me... This time appears this message:

warning:/home/miguel/.qgis2/python/plugins/molusce/algorithms/models/crosstabs/model.py:86: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.
			  if self._T == None:
traceback:  File "/home/miguel/.qgis2/python/plugins/molusce/molusce.py", line 111, in run
			    d.exec_()
			  File "/home/miguel/.qgis2/python/plugins/molusce/algorithms/models/crosstabs/manager.py", line 48, in __crosstableFinished
			    self.crossTableFinished.emit()
			  File "/home/miguel/.qgis2/python/plugins/molusce/moluscedialog.py", line 444, in updateStatisticsTableDone
			    self.__drawTransitionStat()
			  File "/home/miguel/.qgis2/python/plugins/molusce/moluscedialog.py", line 1058, in __drawTransitionStat
			    stat = self.inputs["crosstab"].getTransitionStat()
			  File "/home/miguel/.qgis2/python/plugins/molusce/algorithms/models/crosstabs/manager.py", line 79, in getTransitionStat
			    initArea = tab.getSumRows()
			  File "/home/miguel/.qgis2/python/plugins/molusce/algorithms/models/crosstabs/model.py", line 125, in getSumRows
			    crosstable = self.getCrosstable()
			

I checked my rasters and take away "Non Data" pixels, but continues showing the message. I'm f ### g desperate about this.

Any help?
Thanks

Please update home page

Current link is broken.
Thanks.

area changes not calculating

I have two urban area maps-1991 and 2006. The area changes calculates them as having the same land area and there is no change between them. I have the no data value set at 0 for each one. What is going wrong?

Cannot install MOLUSCE with QGIS 2.18

Hello,

I am trying to install the plugin on QGIS 2.18 Windows 7 64-bit machine but cannot. The error received relates to an encoding error (see attached), but when I include the relevant statement:

#!/usr/bin/env python

-- coding: utf-8 --

It still will not work. Any ideas?

AttributeError

Been trying to crack it the whole day. Exported the raster both in ArcGIS and QGIS, still get the same error. Everything is fine until i get to the CA simulation and get the following error:

An error has occurred while executing Python code:

AttributeError: 'NoneType' object has no attribute 'getBandGradation'
Traceback (most recent call last):
File "C:/Users/Nemanja Nikolic/.qgis2/python/plugins\molusce\moluscedialog.py", line 528, in simulationDone
grad = res.getBandGradation(1)
AttributeError: 'NoneType' object has no attribute 'getBandGradation'

And this is in from the message tab:

[Sun Oct 30 2016 20:08:01] Start logging
[Sun Oct 30 2016 20:08:05] Set intial layer to g100_00_AdmBelgrade
[Sun Oct 30 2016 20:08:06] Set final layer to g100_06_AdmBelgrade
[Sun Oct 30 2016 20:08:13] Added factor layer WaterDist
[Sun Oct 30 2016 20:08:36] Change Map is created
[Sun Oct 30 2016 20:08:39] Class statistics and transition matrix are updated
[Sun Oct 30 2016 20:08:42] Init ANN model
[Sun Oct 30 2016 20:08:42] Set training data
[Sun Oct 30 2016 20:08:43] Start trainig ANN model
[Sun Oct 30 2016 20:14:09] ANN model trained
[Sun Oct 30 2016 20:15:13] Simulation process is started
[Sun Oct 30 2016 20:15:13] ERROR: An unknown error occurs during ANN prediction
[Sun Oct 30 2016 20:15:13] ERROR: An unknown error occurs during simulation

Thanks
Nemanja

P.S. Using CORINE 2000 and 2006 tiff 100x100 files

Error with calculate area changes in QGIS v2.6

I get the next error in calculate area changes with QGIS v2.6:

Ha ocurrido un error mientras se ejecutaba el código de Python:

Traceback (most recent call last):
File "/home/samtux/.qgis2/python/plugins/molusce/moluscedialog.py", line 393, in >updateStatisticsTableDone
self.__drawTransitionStat()
File "/home/samtux/.qgis2/python/plugins/molusce/moluscedialog.py", line 1007, in >__drawTransitionStat
stat = self.inputs["crosstab"].getTransitionStat()
File "/home/samtux/.qgis2/python/plugins/molusce/algorithms/models/crosstabs/manager.py", line >91, in getTransitionStat
deltas = finalArea - initArea
ValueError: operands could not be broadcast together with shapes (3,) (4,)

LULC prediction using MOLUSCE shows Value error: operands could not be broadcast together with shapes (13,)(14,) in area change tab

Hi, i am a PhD student and working on LULC changes. I am trying to use MOLUSCE. When I go to "Area Changes" tab, and I press the "Update tables" or "Create changes map", I always get the same python error message: -Python code: Value error: operands could not be broadcast together with shapes (13,)(14,). would you help me? Thank you

scipy.optimize missing - QGIS 2.0 - Win 7 64bit

When MOLUSCE is installed in a windows 7 64bit environment, the library scipy.optimize is missing.
Package missing for a 64bit architecture?

QGIS minidump when trying to save plot from validation module

MOLUSCE is creating a QGIS minidump crash when I try to save the plot from validation procedure. Everything else is running apparently smoothly.
Running QGIS 2.14.3 x64 on Windows 10 laptop.

Error in getCrossTable

I get this error when I try to obtain the Area Changes:
File "C:/Users/usuario/.qgis2/python/plugins\molusce\algorithms\models\crosstabs\model.py", line 86, in getCrosstable
if self._T == None:
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
Could you help me?
Thank you

Ines

Area Changes error

Hello,
When I use 'molusce' plugin I get the following error in the area changes section and I do not know how to fix this. If you could help me that would be great!

Traceback (most recent call last):
File "C:/Users/Sultan/.qgis2/python/plugins\molusce\moluscedialog.py", line 444, in updateStatisticsTableDone
self.__drawTransitionStat()
File "C:/Users/Sultan/.qgis2/python/plugins\molusce\moluscedialog.py", line 1058, in __drawTransitionStat
stat = self.inputs["crosstab"].getTransitionStat()
File "C:/Users/Sultan/.qgis2/python/plugins\molusce\algorithms\models\crosstabs\manager.py", line 79, in getTransitionStat
initArea = tab.getSumRows()
File "C:/Users/Sultan/.qgis2/python/plugins\molusce\algorithms\models\crosstabs\model.py", line 125, in getSumRows
crosstable = self.getCrosstable()
File "C:/Users/Sultan/.qgis2/python/plugins\molusce\algorithms\models\crosstabs\model.py", line 86, in getCrosstable
if self._T == None:
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

Factors raster is not set. Please specify them and try again

how i can define this factors ?

Geometries are different!!

Hi all.

I'm trying to use molusce but I'm getting some troubles. When I add spatial variables and click 'check geometry' I got a message which said that geometries of the initial raster and the one used as spatial variable are different.

How can I fix it?

Thanks.

Error with Logistic Regression

Hello, first of all thanks for providing this tool.
I simulated a land use change with the following characteristics: 6 explanatory variables, a 2007 raster and a 2014 raster.
It seems that I have a problem with the training algorithm. When I trained the model with Logistic Regression, 2 pixels neighbour, 100 iterations max. and only 10 samples it worked perfect. (obviously 10 samples points are way too little, I just did it to see if it could read well and process every step).
But when I tried to train the same land use change with the same explanatory variables, but changing the sample size from 10 to 1000, after training the model, there was an attribute error: 'NoneType' object has no attribute 'T'.
In short words, once it finished the training, it tried to show coefficients of the model, so it went to get them with the function model.getCoef(), which eventually called self.logreg.get_weights().T but that function did not return anything. Why is that?
It is particularly weird that it worked fine for 10 samples but it couldn't do it for 1000 samples.
Please help me, i dont know what else to do.

The traceback is as follows:

File "C:/Users/kmdua/.qgis2/python/plugins\molusce\logisticregressionwidget.py", line 115, in __trainFinished
self.showCoefficients()
File "C:/Users/kmdua/.qgis2/python/plugins\molusce\logisticregressionwidget.py", line 131, in showCoefficients
coef = model.getCoef()
File "C:/Users/kmdua/.qgis2/python/plugins\molusce\algorithms\models\lr\lr.py", line 65, in getCoef
return self.logreg.get_weights().T
AttributeError: 'NoneType' object has no attribute 'T'

Issue adding tiff image to initial in molusce plugin

I have a vector file which i converted to raster from arcmap in tiff file format. I uploaded the tiff file in qgis in which I intended to use the molusce plugin. When I tried to add the tiff file in the initial of molusce plugin I got the message as "The raster have lots of different values.Does the raster store a nominal variable ?"

Can any one please suggest me why I am getting this message.

Thank you.

Results in Transition Potential Modelling

how interpret the results in the transition potential modelling? how to know the confidence intervals? in the technical information methods and algorithms does no

t appear

TypeError: QgsCollapsibleGroupBox.setSettings(QgsSettings): argument 1 has unexpected type 'QSettings'

Hi there!
Anytime that I try to open the molusce tool I face this error message!

TypeError: QgsCollapsibleGroupBox.setSettings(QgsSettings): argument 1 has unexpected type 'QSettings' 
Traceback (most recent call last):
  File "C:/Users/Jomehzadeh/.qgis2/python/plugins\molusce\molusce.py", line 109, in run
    d = moluscedialog.MolusceDialog(self.iface)
  File "C:/Users/Jomehzadeh/.qgis2/python/plugins\molusce\moluscedialog.py", line 110, in __init__
    self.grpSampling.setSettings(self.settings)
TypeError: QgsCollapsibleGroupBox.setSettings(QgsSettings): argument 1 has unexpected type 'QSettings'

OS version Windows 10
Python version: 2.7.5
QGIS version: 2.18.14 Las Palmas

I appreciate any help!
Best regards!

QGIS ANN simulation results show little to no changes

Hello!
I seem to have a problem with simulation using ANN transition potential modelling. I have a two land cover maps from 2003 and from 2018 (both integer) and a set of factors (11 factors both integer and float). Problem is - with Logistic regression and WoE I do get more or less desired results (changes are simulated in all land cover classes), but with ANN changes are very limited, sometimes ignoring whole classes. I know it is supposed to 'learn' from past development of land covers. But I think in my case that it ignores the past development of the urban cover, urban sprawl basically, sprawl which continiues to happen and I expected that to show in the simulation for year 2033.

I tried changing the count of samples, count of hidden layers, learning rate, left it training overnight, but all the results are still looking very similar - with very little changes being simulated. What could be the problem? May be something wrong with my inputs? Here is a link to my inputs.
https://www.dropbox.com/sh/iudnonedzuc5lrq/AAC8jZ01oJDuLHp24Oco1Ijca?dl=0

there are two inputs for initial and final years (2003/2018_smaller_int), the rest 11 are factors (like distance to roads/, rivers, tehnical infrastructure, schools, bus stops, as well as zoning, population location/count of registered firms)

Would be very thankful if you would try to see where the problem could be.

Error just from adding in the first raster layer

Hi,
I have just begun using MOLUSCE so apologies for any incorrect terminology or understanding. I am trying to conduct a change detection analysis from a 1995 land cover classification raster to a 2015 raster. I open MOLUSCE and select the 1995 year and get the following error:

Python error: An error has occurred while executing Python code: See message log (Python Error) for more details.

And the message log says this Python code:

2017-12-06T16:19:13 1 Traceback (most recent call last):
File "C:/Users/yh800249/.qgis2/python/plugins\molusce\moluscedialog.py", line 215, in
setInitialRaster
initRaster = Raster(unicode(layer.source()),
maskVals=utils.getLayerMaskById(self.initRasterId))
File "C:/Users/yh800249/.qgis2/python/plugins\molusce\algorithms\dataprovider.py", line 54, in init
if self.filename: self._read()
File "C:/Users/yh800249/.qgis2/python/plugins\molusce\algorithms\dataprovider.py", line 287, in _read
self.bands = np.ma.zeros((data.RasterCount,self.geodata['ySize'], self.geodata['xSize']), dtype=float)
File "C:\PROGRA1\QGIS21.18\apps\Python27\lib\site-packages\numpy\ma\core.py", line 7887, in call
result = self._func.call(*args, **params).view(MaskedArray)
MemoryError

Can anyone suggest what I might be doing wrong?

Thanks

attribute error: set projection

hello, I was predicting the land use land cover using molusce plugin FROM QGIS, then at the cellula automata simulation stage I got the message copied below, please can someone assist me?. thanks you

<style> </style>

map = v.save(trans_prefix+'from'+str(initcat)+ 'to' +str(finalcat) + '.tif')
File "C:/Users/User/.qgis2/python/plugins\molusce\algorithms\dataprovider.py", line 347, in save
outRaster.SetProjection(geodata['proj'])
AttributeError: 'NoneType' object has no attribute 'SetProjection'

Update MOLUSCE

Please update molusce for QGIS 3.x

List of categories of the first raster doesn't contains a category of the second raster!

Am trying to predict Landuse changes using cellular automata(with the help of MOLUSCE) but this same error keeps on popping up no matter how many times i try. I am new to GIS hence i do not understand what this error actually reflects. Please help soon i have a deadline to meet.
LULC2000-10.zip

Check if scipy is installed

If scipy is not installed, the plugin crushes.

Check if scipy is installed; if it isn't then do not load logisticregression widget.

This shows up everytime i run the crosstable script. After adding the raster .

What should I do if one class is missing from one of the input maps

Corine layers: corine.zip

I'm trying to perform an analysis of land use/cover change detection using QGIS and MOLUSCE but I get an error message. I'm working with two CORINE raster layers (1990 vs 2006) and other two optional layers as a Spatial variables (distance to roads, distance to rivers). I successfully completed the "Inputs" and "Evaluating Correlation" tabs processes, but when I get to "Area Changes" tab, and I press the "Update tables" or "Create changes map", I always get the same python error message:

Here it goes the error log message:

2016-04-01T12:49:16 1 Traceback (most recent call last):
File "/home/lluis/.qgis2/python/plugins/molusce/moluscedialog.py", line 413, in updateStatisticsTableDone
self.__drawTransitionStat()
File "/home/lluis/.qgis2/python/plugins/molusce/moluscedialog.py", line 1027, in __drawTransitionStat
stat = self.inputs["crosstab"].getTransitionStat()
File "/home/lluis/.qgis2/python/plugins/molusce/algorithms/models/crosstabs/manager.py", line 91, in getTransitionStat
deltas = finalArea - initArea
ValueError: operands could not be broadcast together with shapes (25,) (21,)

I'm working with QGIS 2.14.1 and MOLUSCE 3.0.11 under Ubuntu 14.04 LTS. I've tried the same on a Windows machine with same error message.
Thanks.

Preparing the spatial variables in MOLUSCE

if I have the initial year 2010 LULC map and final as 2015 LULC map and spatial variables as; Distance to a road then, while inserting the spatial variables, how we have to insert i.e. separate for the initial year and final year or common for them? .Can anyone explain this issue?
With regards
Sijan Bhandari

Infinit loop in stratified sampling

Stratified sampling uses the next procedure:

For every transition classes repeat:
 1.  sample random pixel from input-output-factor rasters; get the neighbours of the pixel;
 2. check if all neighbors and inpit/output pixels are not Null.
 3. if all neighbor pixels are not Null, create input sample and add it to sample table
 4. repeat 1-3 until desired number of samples is not created.

(see https://github.com/nextgis/molusce/blob/master/algorithms/models/sampler/sampler.py#L326-L334)

So if a pixel of the transition class is located near raster boundaries, then at least one neighbor of the selected pixel lies outside => the pixel can't be used in sample => the pixel is skipped.

The problem appears when ALL pixels of a transition class lie near boundaries. In this case we get infinite loop.

User guide and technical manual from MOLUSCE plugin menu

And I am waiting for MOLUSCE user guide. Wiki page said that in January 2014, a technical manual and user guide will be released and accesible directly from MOLUSCE plugin menu, but I didn't find it.

Moved from: https://hub.qgis.org/issues/9728

Installing molusce plugin in qgis 2.18.28 in mx linux 19

I try to install molusce plugin. I read that this plugin is trusted. When I continue to install, there is a message : The plugin is broken. Python said: Error Reading metadata: general. How to solve this?

Conflict PyQt4 and PyQt5 in Manjaro Linux

Thank for this excellent module. For Manjaro Linux, I require PyQt4 and PyQt5 libraries, however qgis closes when I try to enable Mollusce module. The error is as follows:

This plugin is broken
the PyQt5.QtCore and PyQt4.QtCore Both modules wrap the QObject class

Error on Create Change map in area changes tab in QGIS 2.8.3 using Molusce plugin

I am predicting the Land change using Molusce plugin but as i update table and create change map got the following error. the geometry of my raster are matched and all are in either signed or unsigned integers.

An error has occured while executing Python code:

Traceback (most recent call last):
File "C:/Users/MinJa/.qgis2/python/plugins\molusce\moluscedialog.py", line 467, in createChangeMap
self.analyst = AreaAnalyst(self.inputs["initial"], self.inputs["final"])
File "C:/Users/MinJa/.qgis2/python/plugins\molusce\algorithms\models\area_analysis\manager.py", line 62, in init
raise AreaAnalizerError("List of categories of the first raster doesn't contains a category of the second raster!")
AreaAnalizerError

Python version:
2.7.5 (default, May 15 2013, 22:44:16) [MSC v.1500 64 bit (AMD64)]

QGIS version:
2.8.3-Wien Wien, 313a6bc

I will be very thankful if anyone can help me out to resolve the issue

Trouble installing MOLUSCE on Ubuntu 16.04 LTS

Hi group,

I'm working on Qgis wien 2.8 and I've just upgraded my Ubuntu version to 16.04 LTS. When I try to install MOLUSCE I get this error message "cannot import name NavigationToolbar2QTAgg" Does anybody know what is this error message about and how can I fix it?
Thanks for your help!

Molusce Qgis

I would like to perform a change prediction using the Molusce plugin, but I'm facing challenges in matching the geometry of different rasters: the initial and final raster, as well as the spatial variables. Is there a simple way to match the geometry of these rasters simultaneously? It's important to note that I'm still learning and not yet an expert in this field. Thank you.

MOLUSCE prediction is same as final layer

Hello all. I am using temporal landcover data and slope as input and using ANN for modelling but the prediction raster does not change and same as the final.

Deprecation Warning

I don't understand what happen but this messages appears when I tried to do the logistic regression in the transitional potencial modelling module. The conditions that I selected were 1500 Iterations and 2 Neighbourhood:

This in the Python Warnings

warning:C:/Users/judab/.qgis2/python/plugins\molusce\moluscedialog.py:1473: DeprecationWarning: QgsProject.dirty() is deprecated
			  QgsProject.instance().dirty(True)
			
			traceback:  File "C:/Users/judab/.qgis2/python/plugins\molusce\molusce.py", line 111, in run
			    d.exec_()
			  File "C:/Users/judab/.qgis2/python/plugins\molusce\moluscedialog.py", line 483, in changeMapDone
			    self.applyStyle(layer, colorRamp)

And this in the Python Error Console

Traceback (most recent call last):
			  File "C:/Users/judab/.qgis2/python/plugins\molusce\algorithms\models\lr\lr.py", line 272, in startTrain
			    self.setTrainingData()
			  File "C:/Users/judab/.qgis2/python/plugins\molusce\algorithms\models\lr\lr.py", line 235, in setTrainingData
			    self.sampler.setTrainingData(state, output, shuffle=False, mode=mode, samples=samples)
			  File "C:/Users/judab/.qgis2/python/plugins\molusce\algorithms\models\sampler\sampler.py", line 284, in setTrainingData
			    self.data = np.zeros(samples, dtype=[('coords', float, 2), ('state', float, self.stateVecLen),('factors',  float, self.factorVectLen), ('output', float, self.outputVecLen)])
			MemoryError

Thanks for you help...