Land Use Prediction Using Land Transformation Model (LTM)

LAND TRANSFORMATION MODEL (LTM) FOR SEMENIYH BASIN

(MALAYSIA)

October 31st 2006

Maryam Adel SAHARKHIZ

HUMANS ARE CHANGING THE LANDSCAPE AT AN UNPRECEDENTED RATE. WHAT CAN WE EXPECT OUR FUTURE LANDSCAPES TO LOOK LIKE?

TOPIC OF TUTORIAL

Run the Land Transformation Model starting from land use maps and different drivers in GIS form.

Do a model run for Semeniyh Basin in Selangor

Predict future LandUse layout based on past land use data. (2006 and 2010)

OBJECTIVES

LTM BACKGROUND

We will model LandUse expansion in Semeniyh Basin using 2 land Use maps, one from 2006 and the other from 2010

After going through the Model we will be able to run the LTM on our study area, to forecast future land use changes in 2014.

Semeniyh Basin land use in 2006 (left) and 2010 (right)

CREATE DRIVERS = PREDICTOR VARIABLES

Driver layers represent phenomena that influence what are trying to model.

In this study, we assume that the following 6 drivers will influence urbanization an agriculture expansion in Semeniyh Basin:

Proximity to urban in 2006, to highways, to roads, to rivers, to Lake of Semeniyh and to inland lakes.

DRIVER CREATION

Drivers was created using Euclidean Distance of ArcGIS. It calculates, for each cell, the Euclidean distance to the closest source.

FORMAT LAND USE LAYERS After Diver’s creation two land use layers were

reclassified to zeros and ones, ones being the class wanted to model. In this case we are modeling urbanization and agriculture expansion so we reclass all urban and agricultures pixels to 1 rest to zero. Semeniyh

LanduseBase in 2006 (left) and LanduseFinal 2010 (right)

PREPARE EXCLUSIONARY LAYER Exclusionary cells are cells which we don’t want

to include in the analysis, i.e. cells which the LTM will never “see”.

In our dataset we excluded water pixels, Agricultures and urban in 2006 as we did not want urban and Agriculture to expand to those locations

exclusionary cells Reclassed as 4, rest of the data as 0.

All data layers need to be exported to ascii files which will be readable by the Neural Network.

EXCLUSIONARY LAYER

PREPARING THE NEURAL NETWORK (NN)

Step 1: Create inputfile.txt

Step 2: Create network file

Step 3: Create pattern file

Step 4: Batchman _ Training

Step 5: Testing

Step 6: Forecasting

STEP 1) CREATE INPUTFILE.TXT At first step we tells the NN which files it needs to get

information from for the predictor variables

STEP 2) CREATE NETWORK FILE

Gives the structure of the NN by following syntax:

Createnet 6 6 1 ltm.net

STEP 3) CREATE PATTERN FILES

Keeps track of which cell has what values in the various base and driver layers as well as the output LTM layer

Createpattern.6.5 inputfile.txt v

STEP 4) BATCHMAN _ TRAINING Different cycles are as Outputs, and learns

from the patterns in the data. It run by bellow commentBatchman –q –f train.bat > traincycles.csv The rms for each of these cycles is recorded in

the traincycles.csv file

traincycles.csv file

CREATE REAL CHANGE MAP

After running step 4 the number of new urban cells between 2006& 2010 was calculated and saved in Real Change raster layer:

Record # of 1s

STEP 5) TESTING FIRST STEP: CREATE PATTERN First RERUN createpattern Syntax this time

with inputfile-test.txt createpattern.6.5 inputfile-test.txt v

CHANGE THIS to 1 in your inputfile.txt file and save it as inputfile-test.txt

STEP 5) TESTING SECOND STEP: BATCHMAN _ TESTING

Another step in order to Testing process

Based on batchman –f batch-test.bat at the command prompt

res_10000.asc and ts_10000.asc are results of Batchman testing

CALCULATE PERCENT CORRECT METRIC

To estimate Spatial Accuracy, file0123 layer was created from ts10000 and RealChange layers as follow. The numbers 0,1,2,3 represent the following:

0 = no real change and no predicted change = True Negative

1 = no real change but change predicted by the model = False N

2 = real change but not predicted by the model = False Positive

3 = real change and predicted change = True Positive

file0123 layer

The Percent Correct Metric (PCM) is just the number of 3’s divided by the number of cells that transition (here 207551)

Sixty to 80% accuracy is

considered an exceptional model.

40% to 60% is acceptable.

CALCULATE PERCENT CORRECT METRIC

PCM = (144933/ 207551) * 100 = 69.83% spatial accuracy

LTM_stats.txt is including of PCM

for all training files.

Kappa = 0.658229

STEP 6: FORECASTING After Testing step, using inputfile-forecast.txt as well as

following comments forecast layer has been created Syntax: Createpattern.6.5 inputfile-forecast.txt Then: asciits2.3 fullreference.txt res_10000

landusefinal.asc ts_10000F.asc 1 12072

FORECASTING RESULTS

Result of forecasting saved in ts_10000F file into ArcMap

BREAKDOWN OF LTM STEPS

createnet

parameters

parameters

batchman

Train.bat or test.bat

Network file (.net)

result file (.res)

asciits

parameters

Time step

pattern files (.pat)createpat

Inputfile (.txt)

GIS driving variable layers as

ASCII grids(.asc)

Convert to

GIS

Create 0123 file Priority

2

1

3

4

5 Kappa

Step 1: Create inputfile.txt

Step 2: Create network file

Step 3: Create Pattern File

Step 4: Batchman Training

Step 5: Testing

Create Pattern

asciits2.3

Forecasting Map

Step 6: Forecasting