Mostly river water level and flood forecasting
methods are based
on gauging stations measurements at
discrete locations, which limits
their capability to provide accurate and timely data over large extent, also
limited or no data available on remote locations. So here we present an idea to
use high resolution satellite images for real time mapping of river water level.
In this project, we developed a Web based GIS system for mapping river water level,
early warning and mapping for flood disasters. To improve flood forecasting/warning,
we developed a decision support system (DSS) for flood monitoring and prediction
that integrates GIS, satellite image processing and hydrological modelling. We
present the methodology for data integration, floodplain delineation, and
online map interfaces. Our Web based GIS system can dynamically display
observed and predicted water levels for decision makers and the general public.
The users can access a Web-based GIS system which models current flood events
and displays satellite imagery and 3D visualization integrated with the flood
plain area. The output from the hydrological modeling will be used for flooding
prediction for the next 1 day to 2 days (24 and 48 hours) along the lower Indus
River. In this stage river water level analysis has been achieved, work on the
hydrological modelling is in progress to acquire river water stage & flood
level and the prediction.
Keywords: Hydrological modelling, GIS
based system, morphology, satellite imagery, 3D visualization.
Droughts and floods are both water-related
natural disasters which have a widespread effect on environmental factors and
activities like human life, agriculture, vegetation, local economies and wild
life. These both are natural disasters which are thought to be beyond human
control, but drought is the one of the most important weather-related natural
disaster which is often aggravated by human action. Drought affects a very
large area for months and even for years. So it has a severe impact on regional
food production, life expectancy of the entire populations and overall economic
performance of large regions or countries. If we observe the recent data
large-scale severe droughts have been observed in different areas of the world
encompassing all continents leading to economic and natural resources loss,
this destruction lead to food shortages and starvation of masses. On the other
hand floods are the most devastating natural hazards in the world. Floods were
most baleful than any other natural disaster both in claiming more lives and
causing more property damage.
For effective management of disaster users like top
level policy makers at the national and international organizations, middle level
policy makers at local levels consultants, researchers, relief agencies and
local producers which includes farmers, water managers suppliers and traders
are interested in reliable, accurate and
timely information of drought and flood. The disaster management activities can
be grouped into three major phases: The Preparedness phase in which prediction
and risk zone are identified, identification is done long before the actual
disaster event occur; in Prevention
phase different activities are carried out like, monitoring, early warning
& Forecasting, and preparation of contingency plans that should be taken up
just before or during the event; and the Response/Mitigation phase includes the
activities which are done damage
assessment and relief management.
Though flood cannot be stop but
their effect can be minimized if we have proper data, so in this project our
objective is to map the river flow data on geographical information system. As
rivers cover a large geographical area so we can obtain data using remote
sensing techniques and distribute information to control stations rapidly over
large areas by means of satellites or transponders mounted on drones or aircraft.
A satellite orbits the Earth, can explore the whole surface in a few days and
repeat its survey of the same area at regular intervals. For these satellite
images we will use publically available high resolution images like NASA MODIS,
The proposed project models a particular area on the GIS and
collect relevant data like satellite images of high resolution at different
time period. The backend processing application will take these images as
input; image will go through multiple stages of processing and output of this
will be quantifiable data along will the geo location. The front end GIS based
web or mobile application will take date from the data base and model it on the
geographical information system.
Fig. 1. GIS
based Prediction system block diagram
2.1. Satellite Image Processing Research
Satellite image processing techniques will be used for effective
management of water bodies on land and used for decision making for disaster
management. An extensive research has been done for identifying and designing the
best suited algorithm for analyzing and processing the high resolution
satellite images. The process of identifying the stage of a river using
satellite images is a difficult process, because the images captured from satellite
are remotely sensed at a very long distance. We utilize the Support Vector
Machine algorithm for this purpose. The work is divided into three phases the
training phase, analysis phase and the testing phase. In the training phase, water
region is extracted from the image and the stage of river is identified both by
training two different ANNs. In the testing process, the input raw river image was
passed through different process first image filtration to de-noised and
morphological operation was carried out on the de-noised image. After that the
river image was segmented into water regions with the aid of the ANN. Finally
in the analysis phase, the stage of the river water was categorized on scale of
three whether river is in Normal, drought or flood condition.
Image Data Gathering
One of the most important thing in our project is the
high-resolution satellite image data, which is publically available on
different platforms some are:
NASA MODIS Imagery SPOT Imagery JAXA’s Global ALOS 3D
World NOAA Data Access Viewer
– Discover Authoritative Datasets Global Land Cover
Facility – Derived Satellite Data
Low fidelity prototypes have
been designed, some basic prototypes are shown below:
Fig. 2. River Geographical Map
Fig. 3. High
resolution Satellite Image
An algorithm has been developed which is able to
identify the water bodies in the high resolution satellite images with an
accuracy of over 90%. In order to understand the flood dynamics and
hydrological exchange between river and related floodplains, it relies on the
data gathered of water levels at discrete locations on main channel. But due to
vast expansion of the river basins we have limited gauging stations and river
passes through locations where it’s difficult to have these stations, so some
other techniques must be implied in order to improve the spatial sampling, like
radar remote sensing using interferometric phase measurements this can improve
the spatial sampling, but the phase is temporally incoherent over open water so
this technique is used to determine water levels.
Satellite images are processed and passed through these
different stages to extract the river stage.
Complete flow is shown with Image Processing steps shown
in blue box:
2.4.1 Image Acquisition
image from open access NASA database
Fig. 6. This is a moderate
resolution satellite image
The image is passed through
different steps to extract the river stage.
2.4.2. Image Filtration:
Filtering is used to modify and enhance the image by
removing the unwanted pixel values in the image. For example, you can filter out
an image to emphasize certain features or remove other features. Image
processing operations implemented with filtering include smoothing, sharpening,
and edge enhancement.
In image processing filtering is a neighborhood
operation, in which the value of each pixel in the output image is calculated by
applying some algorithm to the values of the pixels in the neighborhood of the
corresponding input pixel. A pixel’s neighborhood is the surrounding pixels,
defined by their locations relative to that pixel.
Lab color space Conversion
Lab color space describes mathematically all perceivable colors in the three dimensions
L for lightness and ‘a’ and ‘b’ for the color opponents green–red and
blue–yellow. The Lab color space exceeds the gamut of the RGB and CMYK color
models. One of the most important attributes of the Lab model is device
independence. For the conversion of RGB image to the Lab color format below
giver equations are used.
After conversion to CIE Lab color image look like:
Fig. 7. CIE color converted Image.
processing and computer vision,
anisotropic diffusion, is a technique which is used to reduce image noise without
removing substantial parts of the image content, mostly edges, lines or other details that are
important for the analysis of the image. In Anisotropic diffusion we creates a scale space, in which
an image generates a parameterized family of consecutively more and more
blurred images based on the result of diffusion process. Each of the resulting
images in this family are given as a convolution between the
image and a 2D isotropic. The following equation details
the segmentation process.
Equation 2. Delta Function
applied to Image.
Where div is short for the divergence operator, ?
stands for the Laplacian, ? for the gradient and c(x,y,t) is the diffusion
coefficient. c(x,y,t) is used to control the rate of diffusion and it is
selected as a function of the image gradient in order to conserve edges in the image.
The segmented image is converted
into binary image which will be used for further processing. A binarization is
a method of binarizing an image by extracting lightness (brightness & density)
as a feature amount from the image. In binarization pixel image is converted into
binary image. When a pixel is selected
in an image, sensitivity is added to or subtracted from the value concerning
the Y value of the selected pixel to set a threshold value range. Next, when
another pixel is selected, the sensitivity is added to or subtracted from the
value concerning the Y value of the selected pixel and a new threshold value
range is set containing the calculation result and the already setup threshold
value range. The pixel with the value concerning the Y value of any pixel in
the image within the threshold value range is extracted as the same brightness
as the selected pixel and the extraction result is displayed. The output image
after binarization contain only black and white image.
The morphological operation is applied
to smooth the image for extracting the intended information. The impacts of the
morphological operation are on the application for example in machine vision
and object detection in which we may utilize it to classify the structure in
image. Morphological operation is utilized to distinguish boundaries or objects
or object present in an image. For this, we apply the “imclose” function that is
used to morphological closes the image. The following equation details the
Equation. 3. Image segmentation
expression Here st is structuring element which is required by which the morphological
operation is applied.
Image after morphological operation
Fig. 8. Morphological Image
So as to identify the stage of Support Vector Machine
(SVM) technique is employed, SVM is trained by a set of water identifies images.
Support Vector Machine is a machine learning method that classifies binary
classes by finding and using a class boundary the hyper plane maximizing the
margin in the given training data. The training data samples along the hyper
planes close to the class boundary are called support vectors, and the margin
is the distance between the class boundary, support vectors and hyper-planes.
The SVM work on the basis of the decision boundaries defined by the decision planes.
A decision plane separates between assets of objects having different class
memberships. SVM is a one of the very useful technique for data classification.
For classification task training and testing date is utilized which consists of
some data instances. Each instance in the training set contains one “target
value” (class labels) and several “attributes” (features). Image with
identifies stages of river water.
Fig. 9. River water levels
This paper presents the idea for the
integration of satellite imagery, hydrological modeling and geographical
information system to come up with a decision support system which will be used
for continuously monitoring the river water level. By processing the satellite
imagery we can extract the river stage over the entire spatial range from where
the river passes. Using historical date we can also predict the next stage for
next 24 to 48 hours.
The system for flood events
prediction and monitoring integrated with the web map interface will
facilitates in monitoring, prediction and decision making of the flooding
events. It works as an early warning and mapping of flood disasters.
Laurence C. Smith, “Satellite Remote Sensing of
River Inundation Area, Stage, And Discharge: A Review”, Hydrological
Processes, Vol. 11, pp.1427-1439, 1997
Flood Forecasting GIS Water-Flow Visualization
Enhancement (WaVE): A Case Study Timothy R. Petty1, Nawajish Noman2, Deng
Ding2, John B. Gongwer3
DROUGHTS & FLOODS ASSESSMENT AND MONITORING
USING REMOTE SENSING AND GIS by A.T.
Nipuni Hettiarachchi “Water Level Forecasting and
Flood Warning System A Neuro-Fuzzy Approach”, International Conference in
Video Image and Signal Processing, At India
Michael T. Coe, “Calculation of river discharge
and prediction of lake height from satellite radar altimetry: Example for the
Lake Chad basin”, Water Resources Research, Vol. 40, 2004
D. Mioc “EARLY WARNING AND MAPPING FOR FLOOD
DISASTERS”, The International Archives of the Photogrammetry, Remote Sensing
and Spatial Information Sciences. Vol. XXXVII. Part B4. Beijing 2008
HJ Barneveld “APPLICATION OF SATELLITE DATA FOR IMPROVED FLOOD
FORECASTING AND MAPPING”, 4th International Symposium on Flood Defence: Managing
Flood Risk, Reliability and Vulnerability
Toronto, Ontario, Canada, May
R. Loren and D. B. Benson (eds.), Introduction to String Field Theory, 2nd
edn. (Springer-Verlag, New York, 1999).
R. M. Karp, Reducibility among combinatorial
problems, in Complexity of Computer
Computations (Plenum, New York, 1972), pp. 85–104.
R. Loren and D. B. Benson, Deterministic flow-chart
interpretations, J. Comput. System Sci.
27(2) (1983) 400–433.
R. Loren, J. Li and D. B. Benson, Deterministic
flow-chart interpretations, in Proc. 3rd
Int. Conf. Entity-Relationship Approach, eds. C. G. Davis and R. T. Yeh
(North-Holland, Amsterdam, 1983), pp. 421–439.