Professional Documents
Culture Documents
Last Document
Last Document
Faculty of Engineering
Proved by:
Supervised by:
Prof-Samih Al Rawashdeh
First and foremost , praises and thanks to the God , the Almighty , for His
showers of the blessings throughout our application work to complete the
application successfully .
We would like to express our deep and sincere gratitude to our research super
visor , Prof Samih Al Rawashdeh ; forgiving us the opportunity to do our
application . His dynamic , vision , sincerity and motivation have deeply inspired
us .
2
Table of Content
References …………………………………………..………………(39)
3
Abstract
The paper presents a methodology for study area classification. First, it describes
the geology for the study area and Geographic information system.
This allowed determination of specific method realizations that show the best
classification result; all intermediate results are recorded.
4
Chapter One: Introduction
geology is the study of the structure, evolution and dynamics of the Earth and its
natural mineral and energy resources. Geology investigates the processes that have
shaped the Earth through its 4500 million (approximate!) year history and uses the
rock record to unravel that history. It is concerned with the real world beyond the
laboratory and has direct relevance to the needs of society.
5
1.2 Introduction to GIS
The key word to this technology is Geography – this means that some portion
of the data is spatial. This means that the data is in some way referenced to
locations on the earth. Coupled with this data is usually tabular data known as
attribute data.
6
Chapter Two: Methodology
In this section, we briefly review the advantages and limitations when using
either Supervised or Un-Supervised classification methods in document
classification. Then we will discuss the Object-based image analysis.
7
2.3 Object-based image analysis (OBIA)
8
2.4 Indices
An indexed image uses direct mapping of pixel values to color map values.
The color of each image pixel is determined by using the corresponding value of X
as an index into map . A color map is often stored with an indexed image and is
automatically loaded with the image when you use the imread function.
The relationship between the values in the image matrix and the colormap
depends on the class of the image matrix. If the image matrix is of class single or
double, it normally contains integer values 1 through p, where p is the length of the
colormap. the value 1 points to the first row in the colormap, the value 2 points to
the second row, and so on. If the image matrix is of class logical, uint8 or uint16,
the value 0 points to the first row in the colormap, the value 1 points to the second
row, and so on.
9
The following figure illustrates the structure of an indexed image. In the
figure, the image matrix is of class double, so the value 5 points to the fifth row of
the colormap.
10
Chapter Three: Materials and data
We have chosen five images to cover the area during the period from 2004
to 2020. All images were taken to the same area to show the changes during the
period.
We used PCI-Geomatica to classify the images and find the cover area and
compare them to find the changes happened in the study area. Then we used
ArcGIS to build all maps.
11
3.2 Software to be used
PCI Geomatica
12
ArcGIS
Esri also provides server side ArcGIS software for web maps, known
as ArcGIS Server.
ArcGIS Pro is a 64-bit GIS software that is the more modern version
of ArcGIS Desktop. Unlike ArcGIS Desktop, the ArcCatalog and ArcMap
functionalities are accessed through the same application, most commonly
through the Catalog pane. The graphics requirements for ArcGIS Pro are
considerably higher than for ArcGIS Desktop in order to support the
upgraded visualization. ArcGIS Pro also supports streamlined workflows
that involve publishing and consuming feature layers using ArcGIS Online.
Voxel layers are 3D representations of data over space and time and are
saved in a netCDF file. Voxel layers are used to visualize complex layers
such as atmospheric and oceanic data or space-time cubes. These layers are
used to analyze spatial patterns of data in specific situations. Voxel layers
generally encompass extensive areas and slices can be used to delineate
areas of the layer that need further analysis. Voxels can be shown with other
geospatial data to further visualize the study area.
13
Trace networks are used to evaluate connectivity models like railroads.
Edges and junctions along with network attributes are used to understand the
movement of goods through the network. The connectedness of the network
is established based on the concurrence of geometric features. Trace
networks are used alongside network topology to make more tools available
such as trace and validation.
14
Link analysis develops a network of connected of objects and determines
the patterns that exist. Link analysis is done to find what patterns in a
network are most important and finds new patterns that were previously
unknown. Link analysis uses link charts to visualize the network. Link charts
represent the objects in a network using nodes and these nodes can be
people, buildings, or devices. Objects are usually moving such as people or
vehicles, and link charts show how they interact with each other over both
space and time. Link analysis is done to better understand the network. This
is done by finding the shortest path between nodes, showing what nodes
have the strongest connections, and finding the nodes that are nearest to each
other.
15
Chapter Four: Processing
a) Shape: Shapes of training areas are not important provided that shape does
not prohibit accurate delineating and positioning of outlines of regions on
digital images. Usually it is easiest to define rectangular or polygonal areas;
as such shapes minimize the number of vertices that must be specified.
16
Selection of appropriate classification algorithm
This is a widely used decision rule based on simple Boolean "and/or" logic.
Training data in n spectral bands are used in performing the classification.
Brightness values from each pixel of the multispectral imagery are used to
produce an n-dimensional mean vector.
17
2. Minimum Distance to Mean Classification Algorithm:
The maximum likelihood decision rule assigns each pixel having pattern
measurements or features X to the class c whose units are most probable or
likely to have given rise to feature vector x. It assumes that the training data
statistics for each class in each band are normally distributed, that is, Gaussian.
In other words, training data with bi-or trimodal histograms in a single band are
not ideal. In such cases, the individual modes probably represent individual
classes that should be trained upon individually and labeled as separate classes.
This would then produce unimodal, Gaussian training class statistics that would
fulfill the normal distribution requirement.
18
Classification Accuracy Assessment:
The assumed true map may be derived from in situ investigation or quite
often from the interpretation of remotely sensed data obtained at a larger scale
or higher resolution.
This type of error analysis compares the accuracy of the remote sensing
derived classification map pixel by pixel with the assumed true land use map.
First, it is possible to conduct a sitespecific error evaluation based only on the
training pixels used to train the classifier in a supervised classification. This
simply means that those pixel locations i, j used to train the classifier are
carefully evaluated on both the classified map from remote sensing data
products and the assumed true map. If training samples are distributed
randomly throughout the study area, this evaluation may consider representative
of the study area. If they act biased by the analyst a prior knowledge of where
certain land cover types exist in the scene. Because of this bias, the
classification accuracy for pixels found within the training sites are generally
19
higher than for the remainder of the map because these are the data locations
that were used to train the classifier.
Conversely if others test locations in the study area are identified and
correctly labeled prior to classification and if these are not used in the training
of the classification algorithm they can be used to evaluate the accuracy of the
classified map. This procedure generally yields a more credible classification
accuracy assessment. However additional ground truth is required for these test
site coupled with problem of determining how many pixels are necessary in
each test site class. Also the method of identifying the location of the test sites
prior to classification is important since many statistical tests require that
locations be randomly selected (e .g using a random number generator for the
identification off unbiased row and column coordinates) so that the analyst does
not bias their selection.
Once the Criterion for objectively identifying the location of specific pixels
to be compared is determined, it is necessary to identify the class assigned to
each pixel in both the remote sensing derived map and the assumed true map.
These data are tabulated and reported in a contingency table( error matrix),
where overall classification accuracy and misclassification between categories
are identified.
20
Classification error matrix:
21
Selection of Spectral Indices
Spectral indices are combinations of the pixel values from two or more
spectral bands in a multispectral image. Spectral indices are designed to
highlight pixels showing the relative abundance or lack of a land cover type of
interest in an image.
22
With satellite images, agri software providers can significantly expand
their existing pool of aerial data, as well as save their time and resources,
while end-users can access more data faster. Thus, vegetation indices in
remote sensing are useful in the distant high-level analysis of the crop state. If
any issue arises, farmers can double-check only the spotted areas instead of
inspecting the whole field.
Among the typical spectral vegetation indices, NDVI is one of the most
suitable to track crop development dynamics since it measures photo
synthetically active biomass in plants. However, this vegetation index is quite
sensitive to soil brightness and atmospheric effects, mitigated in other indices
like EVI, SAVI, ARVI, GCL, or SIPI.
Key fact: NDVI is the most common vegetation index in remote sensing. It can
be used throughout the whole crop production season except when vegetation
cover is too scarce, so its spectral reflectance is too low.
When to use: NDVI values are the most accurate in the middle of the season at
the stage of active crop growth.
When to use: ReCI values are most useful at the stage of active vegetation
development but are not suitable for the season of harvesting.
23
3. Normalized Difference Red Edge Vegetation Index (NDRE)
The NDRE index combines the Near-infrared (NIR) spectral bands and a
specific band for the narrow range between the visible red and the red-NIR
transition zone (the so-called red-edge region). For the best data precision, it is
recommended to use NDRE in combination with NDVI.
Key fact: The given vegetation index applies for high-density canopy cover.
When to use: NDRE is typically used to monitor crops that have reached the
maturity stage.
Key fact: Since MSAVI is adjusted to soil effects and is sensitive to early
vegetation in the field, it works even when the earth is hardly covered with
crops.
When to use: MSAVI is useful at the very beginning of crop production season
– when seedlings start to establish.
24
Other Indices
25
4. Bare Soil Index (BSI):
Bare Soil Index (BSI) is a numerical indicator that combines blue, red,
near infrared and short wave infrared spectral bands to capture soil variations.
These spectral bands are used in a normalized manner. The short wave
infrared and the red spectral bands are used to quantify the soil mineral
composition, while the blue and the near infrared spectral bands are used to
enhance the presence of vegetation (GU, 2019).
Normalize Difference Water Index (NDWI) is use for the water bodies
analysis. The index uses Green and Near infra-red bands of remote sensing
images. The NDWI can enhance water information efficiently in most cases.
It is sensitive to build-up land and result in over-estimated water bodies. The
NDWI products can be used in conjunction with NDVI change products to
assess context of apparent change areas (Bahadur, 2018).
26
7. Normalized Difference Glacier Index (NDGI):
27
Chapter Five: Results and Discussion
By using NDBI-Index we can see the water bodies where as higher value
represent build-up areas.
28
5.1.2 NDMI - Index
29
5.1.3 2004 - Map
Map in figure “ 5-3 ” shows the study area on 2004, most of the area was
soil and vegetation.
30
5.1.4 2008 - Map
Map in figure “ 5-4 ” shows the study area on 2008, most of the area was
soil and vegetation.
This image had taken in the summer, this is why the vegetation cover is
smallest than the last image.
31
5.1.5 2012 - Map
You can notice that urban area is in increase and the soil of type 3
is in increase, which means the chemical state of the area is changed .
32
5.1.6 2016 - Map
33
5.1.7 2020 - Map
Most of the area changed and covered by urban area and the soil type is
changed as well.
34
5.1.8 Analysis Map
After study completed we noticed that the area is under the risk of
desertification. It receives little rainfall, with 200-250mm a year. With high
temperatures and People are turning away from farming and start working in the
industrial city in “Al-Qastal”. And most of its soil chemical structure changed and
its salinity increased.
35
5.1.9 The proportion of classes in study area
2020 2004
Vegeta Vegeta
tion tion
Urban Urban
Soil Soil
Figure “4-9” Show the percentage of all classes in the study area as a chart
“The proportion of classes”
As a result, the study area is under a huge desertification risk due to various
factors including climatic variations and human activities and soil pollution cue to
industry city in the area. Or, to put it in another way, desertification results in
persistent degradation of dry land and fragile ecosystems due to man-made
activities and variations in climate.
Jordan could face decreasing water supplies, viable farmland and food, if the
arid and semi-arid lands of the country suffer from further degradation and become
more desert-like. “If these arid areas desertify, we will have a problem with food
security,” says Dr Jawad Al-Bakri, Associate Professor at the University of
Jordan’s Department of Land, Water and Environment and co-director of a NATO-
sponsored project aimed at addressing these challenges through remote-sensing
technology.
36
Several studies have shown that Jordan is at risk of rapid desertification. It
receives little rainfall, with 90 per cent of the country receiving less than 200mm a
year. Deforestation, soil erosion, inappropriate land use and cultivation practices,
climate change and drought all contribute to increasing desertification. Rapid
urbanisation has also taken a toll.
Less arable land and fewer farmers could also mean decreased food
production. “As a result of such reductions, food insecurity and poverty will
continue to increase” points out Dr Ayman Suleiman, Associate Professor at the
University of Jordan’s Department of Land, Water and Environment.
A project funded under NATO’s Science for Peace and Security (SPS)
Programme is attempting to address these threats. Scientists are conducting
research in the Yarmouk Basin, a 1400 square kilometre area in the Badia region.
Most of the area is at risk for high rates of soil loss by wind and water, which can
lead to desertification.
“In this project, we are trying to come up with ways by which we can monitor
desertification as it is happening. That way suitable prevention measures will be
targeted at the right place and at the right time,” says Dr Suleiman.
37
Chapter Six: Conclusion and Recommendation
We can use these areas and plant them with perennial trees, which can live and
rise in very low amount of water in order to; save the soil, climate, the atmosphere
and decrease the effects of smoke that comes from industry.
38
References
3. Wikipedia: https://en.wikipedia.org/wiki/Geology
4. https://www.memr.gov.jo/EBV4.0/Root_Storage/EN/Project/summary_
of_mineral_resources_in_Jordan.pdf
6. https://geology.com/
39