LAND COVER PREDICTION OF INDRAMAYU REGENCY USING THE CELLULLAR AUTOMATA METHOD AND ITS RELATION TO THE REBANA PRIORITY AREA DEVELOPMENT PLAN
Industrial Estate (KPI) have the potential to trigger land conversion and threaten Food Agricultural Land (LP2B). An accurate land cover prediction method is needed to control land conversion. The study aims is to predict the land cover of Indramayu Regency in 2031 using the Cellular Automata (CA...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Subjects: | |
| Online Access: | https://digilib.itb.ac.id/gdl/view/74258 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Industrial Estate (KPI) have the potential to trigger land conversion and threaten
Food Agricultural Land (LP2B). An accurate land cover prediction method is
needed to control land conversion. The study aims is to predict the land cover of
Indramayu Regency in 2031 using the Cellular Automata (CA) method and to
analyze its relation to the Rebana KPI development plan. Land cover maps is
produced based on Landsat satellite imagery with hybrid classification
(supervised and unsupervised) using training sample images of NDBI, NDVI,
NDWI, Google Earth, and field surveys. The CA method is carried out using an
Artificial Neural Network algorithm based on the business as usual scenario and
the KPI scenario built in 2026 and 2031. The variables of distance to roads, to
existing settlements, to coastlines and population density, are used as driving
factors of land cover change. This study also analyzes the suitability of 2031 land
cover against LP2B and KPI. A land cover map is produced with a good accuracy
of 64.45% (overall accuracy). The 2011-2016 land cover image is used as a
transition rule for prediction of 2031 land cover. Land change in 2011-2016 and
prediction of 2031 land cover (in all scenarios) show a significant increase in
built-up area and decrease in agricultural land. There was an increase in built-up
land of 34,212.71 hectares (business as usual), 45,116.35 hectares (2026 KPI
scenario), and 51,915.26 hectares (2031 KPI scenario) or respectively 517.97%,
683.08%, and 786.02% of land built up by 2021. There has been a decline in
agricultural land of 31,121.28 hectares (business as usual), 38,087.00 hectares
(2026 KPI scenario), 42,879.49 hectares (2031 KPI scenario) or a row of 21.74% ,
25.21%, and 29.96% of the agricultural land area in 2021. Analysis on LP2B land
shows a decrease in agricultural land of 21.06% of the agricultural land area in
2021 (business as usual scenario), 26.73% (KPI scenario 2026), and 29.01%
(2031 KPI scenario). On KPI land, it shows that KPI has the potential to cause
conversion of agricultural land area of 12,282.62 hectares or 61.86% of the total
KPI or 9.76% of the total LP2B. In addition, 7,176.45 hectares (36.14% of the
total KPI) are located in water body which is prone to flooding and can threaten
the preservation of water resources. Policies are needed to control land conversion
and land use management to optimize LP2B and KPI. The data and methods
developed in this study can be used to develop policies for controlling land
conversion and spatial planning in Indramayu Regency |
|---|