Week 5 Proposed Work and Implementation

I have already already did a part of work like literature review, analysis a table, part of project proposal and proposed solution. please kindly go through them and need to write a report on Application of Neural Networks in weather forecasting.Need to write a report, Annotated Bibliography and PPT on Applications of artificial neural networks in weather fore casting. I will provide all the required documents. I need everything without plagiarism.Report should be of at least 5000 words. I will provide the 16 journal papers which i have reffered to write the leterature review.I am attaching a report, annotated Bibliography and PPT works of my friend for reference.
analysis_table.docx

analysistable.docx

Don't use plagiarized sources. Get Your Custom Essay on
Week 5 Proposed Work and Implementation
Just from $13/Page
Order Essay

literature_review_week4.docx

project_proposal_and_plan.docx

what_to_do.docx

Unformatted Attachment Preview

Surname 1
Proposed Work and Implementation for Flood Prediction.
Week 5_ Create Flowchart & Different Evaluation Tables by Analysing the Major Features/Factors in your project
Table 1
Table Name
Goal of this Table
Quality monitoring
1
Surname 2
The main purpose or aim of this table below is to provide an analysis of all models that were
used during the research based on their quality of monitoring quality. This will assist in
extracting the most suitable model in solving the stated research problem.
Input for this Table
Output of this Table
Results Discussion Place the Table Here
The input for the table is the complete set of
The output of the table is the second best and
ANN’s combined data sets based on RFFA
academic research information and data
the best model which is applicable in solving
model is the best in terms of accuracy in
collected data. This data is obtained from
a problem associated to the research and is
predicting the regions’ rainfall. Moreover, this
academic articles, journals and other sources.
useful in analysing the occurrence of
design model is probably successful and
droughts and floods
superior in training learners as well as
predicting flash floods.
The Created Table
2
Surname 3
SPEI-6 software
Faisal, M., Nazir,
H. M., Hussain,
T., Shad, M. Y.
and Hussain Gani,
S.
3
Map-reading
Accuracy
Efficiency
Recoverability
errors
Monitoring
Absence of potential
Correctness
Performance
Geographic
Uptime
Ali, Z., Hussain, I.,
Monitoring
Performance
Database performance
Usability
Broken Links
Author
Full Page Load Time
Model
Surname 4
Using an algorithm
Saurabh,
K.,
&
Dimri, A. P
Ensemble methods
Maqsood, I., Khan,
M. R., and
Abraham, A
Improved
rainfall Dinu, C., Drobot,
forecast method
R., Pricop, C., and
Blidaru, T. V.
CAPSO-MLP
Beheshti,
Z.,
Firouzi,
M.,
Shamsuddin, S. M.,
Zibarzani, M., and
Yusop, Z.
4
Surname 5
ANN based RFFA
Aziz, K., Rahman,
model
A., Fang, G., and
Shrestha, S.
Experimentations
Young, C. C., and
methods
Liu, W. C
Mathematical
Khedhiri, S.
analysis tools
BP-ANN model
Jinlong Gao,
Xiaodong Huang,
Xiaofang Ma,
Qisheng Feng,
Tiangang Liang,
Hongjie Xie
5
Surname 6
Bayesin Network
Gary
Weymouth,
Newham,
T.
Peter
Rodney
Potts, John Bally,
Ann E. Nicholson
And Kevin B. Korb
B-smog model
Jiaoyan
Chen,
Huajun
Chen,
Daning Hu, Jeff Z.
Pan, Yalin Zhou
Using
regression
nonlinear
M. Rezaeianzadeh,
H. Tabari, A. Arabi
6
Surname 7
Yazdi, S. Isik and
L. Kalin
Uses MI Technique
Babel, M. S.,
Badgujar, G. B., &
Shinde, V. R.
Shinde
DBM model
P.J.
Smith,
L.
Panziera and K.J.
Beven
Thunderstorm
Waylon
neural networks
and Philippe Tissot
The RCM model
Silvia Bar betta and
Tommaso
Collinsa
Mora
marco
7
Surname 8
Table 2
Table Name
Analysis Reliability
Goal of this Table
The main purpose of this table is to obtain the most appropriate model in solving the problem
associated to this research. This will assist in coming up with the best model for analysing the
occurrence of droughts and floods.
Input for this Table
Output of this Table
Results Discussion Place the Table Here
ANN’s combined data sets based on RFFA
The input of the table is the academic content
that had been collected for the evaluation of
The output of the table would help to analyse
model is the best in terms of accuracy in
the predicting the occurrence of floods and
the occurrence of droughts and floods.
predicting the regions’ rainfall. Moreover,
droughts.
this design model is probably successful and
8
Surname 9
superior in training learners as well as
predicting flash floods.
The Created Table
SPEI-6 software
Validity
Effectiveness
Ali, Z., Hussain, I.,
Faisal, M., Nazir,
H. M., Hussain,
T., Shad, M. Y.
9
Potency
Data Collection
Efficiency
Author
Analysis of data
Model
Surname 10
and Hussain Gani,
S.
Using an algorithm
Saurabh,
K.,
&
Dimri, A. P
Ensemble methods
Maqsood, I., Khan,
M. R., and
Abraham, A
Improved
rainfall Dinu, C., Drobot,
forecast method
R., Pricop, C., and
Blidaru, T. V.
CAPSO-MLP
Beheshti,
Z.,
Firouzi,
M.,
Shamsuddin, S. M.,
10
Surname 11
Zibarzani, M., and
Yusop, Z.
ANN based RFFA
Aziz, K., Rahman,
model
A., Fang, G., and
Shrestha, S.
Experimentations
Young, C. C., and
methods
Liu, W. C
Mathematical
Khedhiri, S.
analysis tools
BP-ANN model
Jinlong Gao,
Xiaodong Huang,
Xiaofang Ma,
Qisheng Feng,
11
Surname 12
Tiangang Liang,
Hongjie Xie
Bayesin Network
Gary
Weymouth,
Newham,
T.
Peter
Rodney
Potts, John Bally,
Ann E. Nicholson
And Kevin B. Korb
B-smog model
Jiaoyan
Chen,
Huajun
Chen,
Daning Hu, Jeff Z.
Pan, Yalin Zhou
12
Surname 13
Using
nonlinear
regression
M. Rezaeianzadeh,
H. Tabari, A. Arabi
Yazdi, S. Isik and L.
Kalin
Uses MI Technique
Babel, M. S.,
Badgujar, G. B., &
Shinde, V. R.
Shinde
DBM model
P.J.
Smith,
L.
Panziera and K.J.
Beven
Thunderstorm
Waylon
Collinsa
neural networks
and Philippe Tissot
13
Surname 14
The RCM model
Silvia Bar betta and
Tommaso
Mora
marco
Table 3
Table Name
Response and recovery analysis
Goal of this Table
The table below will facilitate analysis of the sixteen models applied during the research
based on the respective recovery and response of the obtained output in the process of
obtaining the solution to the research problem.
Input for this Table
Output of this Table
Results Discussion Place the Table Here
Input for the table is the academic information This output of the table is an analysis of the
ANN’s combined data sets based on RFFA
used to analyse the research situation.
model is the best in terms of accuracy in
best model which is most appropriate in
14
Surname 15
Moreover, the information is used for the
analysing the recovery and response for the
predicting the regions’ rainfall. Moreover,
analysis of the models in the table.
models.
this design model is probably successful and
superior in training learners as well as
predicting flash floods.
The Created Table
SPEI-6 software
Faisal, M., Nazir,
H. M., Hussain,
15
Authenticity
Accuracy
Management of Data
Situational
Correctness
Validity
Accuracy
Ali, Z., Hussain, I.,
Quality
Performance
Response Time
Usability
Heat Maps
Author
Clicks
Model
Surname 16
T., Shad, M. Y.
and Hussain Gani,
S.
Using an algorithm
Saurabh,
K.,
&
Dimri, A. P
Ensemble methods
Maqsood, I., Khan,
M. R., and
Abraham, A
Improved
rainfall Dinu, C., Drobot,
forecast method
R., Pricop, C., and
Blidaru, T. V.
CAPSO-MLP
Beheshti,
Z.,
Firouzi,
M.,
16
Surname 17
Shamsuddin, S. M.,
Zibarzani, M., and
Yusop, Z.
ANN based RFFA
Aziz, K., Rahman,
model
A., Fang, G., and
Shrestha, S.
Experimentations
Young, C. C., and
methods
Liu, W. C
Mathematical
Khedhiri, S.
analysis tools
BP-ANN model
Jinlong Gao,
Xiaodong Huang,
Xiaofang Ma,
17
Surname 18
Qisheng Feng,
Tiangang Liang,
Hongjie Xie
Bayesin Network
Gary
Weymouth,
Newham,
T.
Peter
Rodney
Potts, John Bally,
Ann E. Nicholson
And Kevin B. Korb
B-smog model
Jiaoyan
Chen,
Huajun
Chen,
Daning Hu, Jeff Z.
Pan, Yalin Zhou
18
Surname 19
Using
nonlinear
regression
M. Rezaeianzadeh,
H. Tabari, A. Arabi
Yazdi, S. Isik and L.
Kalin
Uses MI Technique
Babel, M. S.,
Badgujar, G. B., &
Shinde, V. R.
Shinde
DBM model
P.J.
Smith,
L.
Panziera and K.J.
Beven
Thunderstorm
Waylon
Collinsa
neural networks
and Philippe Tissot
19
Surname 20
The RCM model
Silvia Bar betta and
Tommaso
Mora
marco
Week 6_ Propose New Solution
A. If you Propose Hybrid Solution
20
Surname 21
Current Solution
1
Author Name and Published year
System Components
How is the System Work
Ali, Z., Hussain, I., Faisal, M.,
Multilayer perceptron neural network
First drought indices are the typical tools used in
Nazir, H. M., Hussain, T., Shad, M.
(MLPNN) algorithm
assessing the drought conditions around the world and a
Y., & Hussain Gani, S. (2017
few of them are as follows: Rainfall Anomaly Index.
and monthly time series data of Standardized
Secondly, Applied Markov chain on SPI to characterize
Precipitation Evapotranspiration Index (SPEI).
the stochasticity of drought and predict three months
ahead of drought. Thirdly, In this particular case, the
forward neural network topology with back propagation
learning algorithm was used. The variables assortment
process was imitated. Then, Formulation of training,
testing and validation. Finally, Architecture of iterations.
Features/Characteristics
Advantages
Limitations and Challenges
21
Surname 22
Improving the accuracy to estimate
Relate current measures with proposed
Archaic method of predicting draughts, it only provides a
and predict future draughts in an
measures, the newer system has ability to
temporary drought warning system, several researchers
accurate manner.
adaptively determine pattern from data such as
described the problem in finding the appropriate network
rainfall, considers previous data and relates to
size for predicting real-world time series, identifying the
projected possible outcomes to modify results
accurate variables is not easy and this process can be
and improve accuracy, this process ensures that
tedious and a complex algorithm is used.
accurate and test effective variables are selected
and the use of iteration was applied to check the
consistency and note weather changes.
Diagram of this system
22
Surname 23
Current Solution 2
Author Name and Published year
System Components
How is the System
Work
Dinu, C., Drobot, R., Pricop, C., & Blidaru, T. V. (2017).
Radar technology
The study area is
http://web.b.ebscohost.com.ezproxy.csu.edu.au/ehost/pdfviewer/pdfviewer?vid=0&sid=b6df5c3f-
identified, the primary
1c34-4299-a557-19046ff5232d%40sessionmgr101
data is observed and
23
Surname 24
recorded, results are
recorded, ANN
training and validation,
and Validation of
ANN.
Features/Characteristics
Advantages
Limitations and
Challenges
The improved rainfall forecast method is developed.
24
This limits the scope
The region is still too
of study to a certain
wide to effectively
region, used to
cover, the comparison
simulate the regions
used trial and error
weather behaviour,
method, only extensive
the process improves
iterations give accurate
the accuracy of the
answers and the
Surname 25
results and actual
maximum discharge
records were used to
could not be simulated.
run the calculations
and simulations.
Diagram of this system
25
Surname 26
Proposed work
Name your proposal
Proposed System Components
How is the proposed System Work
system/method/tool/…
Application of artificial neural
ANNs, comparative analysis
ANN based RFA modeling using RFA Comparison tools
networks in regional flood
frequency analysis: a case study for
Australia.
Features/Characteristics
Advantages
Limitations and Challenges
The comparison of ANN model and
The region under study was selected and it was
The region selected was still wide; Some errors that were
the combined data sets indicate that
limited to region with dense gauge stations;
considered minor were still recorded; The extensions and
ANN based RFFA model is the
This comment would be used to ascertain that
multiple stations would lead to bulky calculations; The
best in accuracy of predicting
high-quality data was recorded; The balance
stations eliminated represented geographical regions and
rainfall in a given region. The
ensures that longer period for better quality and
26
Surname 27
model can therefore be used in
multiple stations for weighting are used; This
so the overall results would not reflect the actual results
successful training of learners.
was a method of eliminating gauge stations with
of the region.
extremities.
Analyse your proposed solution
Your Proposed work Discussion
Expected Results of proposed solution
The comparison of ANN model
It is easy to model regional rainfall patterns that
ANN’s combined data sets based on RFFA model is the
and the combined data sets indicate
are accurate compared to rainfall patterns usable
best in terms of accuracy in predicting the regions’
that ANN based RFFA model is the
in one region.
rainfall. Moreover, this design model is probably
best in accuracy of predicting
successful and superior in training learners as well as
rainfall in a given region. The
predicting flash floods.
model can therefore be used in
successful training of learners.
Diagram of this system
27
Surname 28
Week 7-to-Week 9_Implementing your Proposed Solution
Step Name
Model design, Data Base design, …etc>
Process you need to work on the input to
Goal of this step
To create a prototype for the situation
The output (Result) of this stage
accomplish the goal
28
Input you need to accomplish the goal
Rainfall intensity data
Result Discussion
Surname 29
The tools used to assess this work include regional
Comparative and regional wise rainfall
ANN’s combined data sets based on
meteorology department. The works adds value to
analysis
RFFA model is the best in terms of
ANNs when used to assess rainfall in a wide region
accuracy in predicting the regions’
through the use of RFFA.
rainfall. Moreover, this design model is
probably successful and superior in
training learners as well as predicting
flash floods
Diagrams/Figures of Outputs
Week 10 Evaluate your Proposed Solution.
29
Surname 30
Proposed and Previous Work Comparison
Work Goal
Previous Work_1 (Author Name
Previous Work_2 (Author Name and
and Publication Year)
Publication Year)
Gao, J., Huang, X., Ma, X.,
Dinu, C., Drobot, R., Pricop, C., &
To develop flood quantile estimates
Feng, Q., Liang, T., & Xie, H.
Blidaru, T. V. (2017).
that are accurate for un-stationed
(2017)
System’s Components
Proposed Work
The Artificial Neural Network
regions
Radar technology
(BP-ANN) is more effective
compared to the traditional
methods of measuring the rate of
snow; the model has the capacity
to make accurate predictions. It is
also raster-based and can
30
ANNs, comparative analysis
Surname 31
efficiently tell the level of damage
at 500 m pixel resolution.
System’s Mechanism
Use of Back Propagation
Modeling hydrological processes.
Artificial Neural Network (BP-
ANN based RFA modeling using
RFA Comparison tools
ANN) to predict snow disaster in
pastoral areas and therefore avoid
the damages that result from it.
Features/Characteristics
BP-ANN model is different from
The improved rainfall forecast
The experiments could yield a good
the previously published models
method is developed.
learning performance.
since it has a high generalization
capacity. It also has an overall
accuracy of 80 precent which is
higher than the earlier models.
31
Surname 32
This makes it the most favorable
choice among its competitors.
Cost
Costs incurred are relatively low
It is considerably expensive due to
The comparative nature of the study
because the Back Propagation
ANN training and validation as well
makes it to be considerably
Artificial Neural Network (BP-
as the wide area covered to obtain
expensive
ANN) to predict snow disaster is
weighted rainfall data.
more effective.
Speed
Fast
Moderate
Fast
Security
Secured
Secured
Secured
Performance
The research plays a significant
The radar based observations can be
part in providing early warnings
sued to train ANN for better results
and therefore the herders are able
especially in areas with few weather
to take precautions and
stations.
accordingly save their animals
32
Surname 33
from perishing on account of
snow disaster.
Advantages
Herders secure their animals prior This limits the scope of study to a
The region under study was selected
to the fall of snow; Increased
certain region; Used to simulate the
and it was limited to region with
productivity as individuals can
regions weather behaviour.
dense gauge stations; This comment
plan their schedules in regard to
would be used to ascertain that high-
farming and herding; Fewer
quality data was recorded; The
damages experienced.
balance ensures that longer period
for better quality and multiple
stations for weighting are used; This
was a method of eliminating gauge
stations with extremities.
33
Surname 34
Limitations/Disadvantages The model is not fully reliable,
The region is still too wide to
The region selected was still wide;
and can at times give the wrong
effectively cover; The comparison
Some errors that were considered
predictions; Most of the times the
used trial and error method;
minor were still recorded; The
amount of snow is quite high and
extensions and multiple stations
prior knowledge on the snow
would lead to bulky calculations;
disaster does not help much to
The stations eliminated represented
avert the damages.
geographical regions and so the
overall results would not reflect the
actual results of the region.
Platform
Journals and articles provided the
Radar technology and simulations
The platform used to assess this
information on the issue of
work include regional meteorology
herders in Qinghai Province in
department.
China, as well as the BP-ANN
34
Surname 35
model that is used to predict snow
disaster.
Number of examples
4
4
4
Identifying probable consequence
Tables of trained ANN results
Comparison of rainfall patterns.
The research plays a significant
The radar based observations can be
It is easy to model regional rainfall
part in providing early warnings
sued to train ANN for better results
patterns that are accurate compared
and therefore the herders are able
especially in areas with few weather
to rainfall patterns usable in one
to take precautions and
stations.
region
applied to each work
Results
of floods.
Results Discussion
accordingly save their animals
from perishing on account of
snow disaster
35
Surname 36
36
Student Name & CSU
ID
Project Topic Title
1. Analysis table of literature collection
Work and
Author
Work
Goal
Forecasting
Drought Using
Multilayer
Perceptron
Artificial
Neural
Network
Model.
Predraught
assessmen
t and
estimation
of the
effects of
the
draught
Ali, Z.,
Hussain, I.,
Faisal, M.,
Nazir, H. M.,
Hussain, T.,
Shad, M. Y.,
and Hussain
Gani, S.
Innovation
use of
multilayer
perceptron
neural
network
(MLPNN)
algorithm
to develop
a draught
forecastin
g system.
System’s
Components
Multilayer
perceptron
neural
network
(MLPNN)
algorithm
And monthly
time series
data of
Standardized
Precipitation
Evapotranspir
ation Index
(SPEI).
System’s
Mechanism
Using the
monthly
(MLPNN)
algorithm on
periodic
data of SPEI
(Standardize
d
Precipitation
Evapotransp
iration
Index) to
predict
forecasting
depending
on its
performance
. Once the
forecast is
executed,
management
planner and
water
related
resources
Features
Cost
/Characteris
tics
Improving
The cost is
the accuracy relatively
to estimate
affordable
and predict
future
draughts in
an accurate
manner.
Performanc
e
Ability to
accurately
predict
future
draughts
using the
SPEI-6
software
Advantages
Relate current
measures with
proposed
measures
The newer
system has
ability to
adaptively
determine
pattern from
data such as
rainfall
Considers
previous data
and relates to
projected
possible
outcomes to
modify results
and improve
accuracy.
This process
ensures that
Page 1 of 14
Limitations
/Disadvantages
Platform
Archaic method
of predicting
draughts
Applied
Markov
chain on
SPI to
characteriz
e the
stochastici
ty of
drought
and
predict
three
months
ahead of
drought
It only provides
a temporary
drought warning
system
Several
researchers
described the
problem in
finding the
appropriate
network size for
predicting realworld time series
Identifying the
accurate
variables is not
easy
can be taken
into action
in ahead.
accurate and
test effective
variables are
selected
This process can
be tedious and a
complex
algorithm is …
Purchase answer to see full
attachment

Order a unique copy of this paper
(550 words)

Approximate price: $22

Basic features
  • Free title page and bibliography
  • Unlimited revisions
  • Plagiarism-free guarantee
  • Money-back guarantee
  • 24/7 support
On-demand options
  • Writer’s samples
  • Part-by-part delivery
  • Overnight delivery
  • Copies of used sources
  • Expert Proofreading
Paper format
  • 275 words per page
  • 12 pt Arial/Times New Roman
  • Double line spacing
  • Any citation style (APA, MLA, Chicago/Turabian, Harvard)

Our guarantees

Delivering a high-quality product at a reasonable price is not enough anymore.
That’s why we have developed 5 beneficial guarantees that will make your experience with our service enjoyable, easy, and safe.

Money-back guarantee

You have to be 100% sure of the quality of your product to give a money-back guarantee. This describes us perfectly. Make sure that this guarantee is totally transparent.

Read more

Zero-plagiarism guarantee

Each paper is composed from scratch, according to your instructions. It is then checked by our plagiarism-detection software. There is no gap where plagiarism could squeeze in.

Read more

Free-revision policy

Thanks to our free revisions, there is no way for you to be unsatisfied. We will work on your paper until you are completely happy with the result.

Read more

Privacy policy

Your email is safe, as we store it according to international data protection rules. Your bank details are secure, as we use only reliable payment systems.

Read more

Fair-cooperation guarantee

By sending us your money, you buy the service we provide. Check out our terms and conditions if you prefer business talks to be laid out in official language.

Read more

Calculate the price of your order

550 words
We'll send you the first draft for approval by September 11, 2018 at 10:52 AM
Total price:
$26
The price is based on these factors:
Academic level
Number of pages
Urgency

Order your essay today and save 15% with the discount code ESSAYHELP