SlideShare a Scribd company logo
Comparison of ANN Algorithm
for Water Quality Prediction of
River Ganga
Aradhana Giri and N.B. Singh
Department of Civil Engineering, Institute of Engineering and Technology
Lucknow, UP, India
Presented By:
Suresh Pokharel (074MSCSK015)
M.Sc. in Computer System and Knowledge Engineering
Institute of Engineering, Pulchowk Campus 1
Introduction
● Maintaining the Availability and Quality of the freshwater
resources : A vital environmental challenge
● Human actions in urban areas surrounding the Ganga River (i.e.
Kanpur, Allahabad, Varanasi etc.) generates severe impact.
Causes of Water Pollution:
- Rapid increase in population
- Rising standards of living
- Exponential growth of Industrialization 2
Introduction to Ganga River
● The most worshipped river of the Hindus
● One of the most polluted river of the country
● 25 big cities located along its bank
● 95% of the sewage enters directly to the river
● Total length: 2525 KM (Gangotri to Gangasagar)
● Highly Polluted: 600 KM
3
Ganga River : National River of India
4
A man cleaning garbage along the banks of the river
Ganges in Kolkata, India, April 9, 2017. 5
Objective
To develop two different ANN models and compare their
performances to evaluate the current situation and
predict the behaviour of water quality with respect to
changes in pollutant loads and hydrological conditions
6
Gathered Data
● Hydro Meteorological data
● Quality Measurement in River
● Land use
● Management practices on land
● Point pollution measurement
● Flow and water level data
7
Table: PRIMARY WATER QUALITY CRITERIA FOR
DESIGNATED (BEST - USE - CLASSES)
Source: http://www.uppcb.com/river_quality.htm
8
Source: http://www.uppcb.com/pdf/march24april18.pdf
9
Dissolved Oxygen
● Dissolved oxygen refers to the level of free,
non-compound oxygen molecule present in water
● Fish and aquatic animals cannot split oxygen from water
(H2O) or other oxygen-containing compounds.
● Measured in units of milligrams of gas per liter of water –
mg/L. (parts per million or ppm).
10
How Temperature affects water quality?
● Temperature impacts both the chemical and biological
characteristics of surface water
● Warm water is less capable of holding dissolved oxygen.
● Low dissolved oxygen levels leave aquatic organisms in a
weakened physical state and more susceptible to
disease, parasites, and other pollutants.
11
Source: US Geographical Survey (https://water.usgs.gov/edu/temperature.html)
Artificial Neural Network Model
Monthly data of previous 5 years (2008 to 2012) are measured with
attributes:
● Temperature
● Flow rate
● BOD (Biochemical Oxygen Demand)
● DO (Dissolved Oxygen)
Implementation Platform: MATLAB NN Toolbox
Data Source: Uttar Pradesh Pollution Control Board (UPPCB)
12
Division of Data
Training Data : 70%
Testing Data : 30%
Input_Train: 1x42
Output_Train: 1x42
Input_validation: 1x18
Output_validation: 1x18
13
Training Algorithms
Back Propagation:
Backpropagation works by
using a loss function to
calculate how far the
network was from the target
output.
14
Training Algorithm - 1
Gradient Descent with adaptive learning:
● Function name: traingda
● A network training function that updates weight and bias values
according to gradient descent with adaptive learning rate.
● Backpropagation is used to calculate derivatives of performance
dperf with respect to the weight and bias variables X.
● Each variable is adjusted according to gradient descent:
dX = alpha*d(perf)/dX
● Gradient Descent has a problem of getting stuck in Local Minima
15
Activation Function for GDA
For Hidden Layer
real-valued function ф whose value depends only on the distance
Gaussian radial basis function
r = |x-xi
| ф = e-(εr)^2
For Output Layer
Linear activation function
Transfer Function
Hyperbolic Sigmoid Tangent function ( tansig )
16
Training Algorithm - 2
Levenberg Marquardt Back Propagation:
● The LM curve-fitting method : combination the gradient descent method and the
Gauss-Newton method.
Backpropagation is used to calculate the Jacobian jX of performance perf with
respect to the weight and bias variables X.
Each variable is adjusted according to Levenberg-Marquardt,
jj = jX * jX
je = jX * E
dX = -(jj+I*mu)  je where E is all errors and I is the identity matrix.
Function in Matlab: trainlm
Source: https://www.mathworks.com/help/deeplearning/ref/trainlm.html
17
Activation Function for LM
For Hidden Layer
Tanh (Hyperbolic Tangent function)
f(x) = 1 — exp(-2x) / 1 + exp(-2x)
-1 < output < 1
For Output Layer
Linear activation function
Transfer Function
Log Sigmoid Transfer function (logsig )
18
Testing
● Test with unknown data set
● After training with each ANN
configuration, Performance evaluation
methods used :
Correlation Coefficient
Mean Square Error (MSE)
Root Mean Square Error (RMSE) Xi
: Real ith data
Yi
: ith Estimate
N : NUmber of Xi, Yi
X
̄ : Average of X
19
Results
Fig. Comparison between output of Levenberg Marquardt (LM) backpropagation and Gradient Descent with
adaptive learning (GDA) rate backpropagation
20
21
Results (contd ...)
Best Trained R = 0.9860
Best Validation R = 0.9800
Best Output vs. Target = 0.9919
● In comparison to GDA, result of LM is found to be more
accurate
● LM is faster as compared to GDA
22
References
1. Giri, Aradhana, and N. B. Singh. "Comparison of Artificial Neural Network
Algorithm for Water Quality Prediction of River Ganga." Environmental
Research Journal 8.2 (2014): 55-63.
2. Webb, Bruce W., and Franz Nobilis. "Long-term changes in river temperature
and the influence of climatic and hydrological factors." Hydrological Sciences
Journal 52.1 (2007): 74-85.
3. Zhang, Guoqiang, B. Eddy Patuwo, and Michael Y. Hu. "Forecasting with
artificial neural networks:: The state of the art." International journal of
forecasting 14.1 (1998): 35-62.
4. Maier, Holger R., and Graeme C. Dandy. "Neural networks for the prediction
and forecasting of water resources variables: a review of modelling issues and
applications." Environmental modelling & software 15.1 (2000): 101-124.
23
Thank You!
24

More Related Content

Similar to Comparison of ANN Algorithm for Water Quality Prediction of River Ganga

Use of Evolutionary Polynomial Regression (EPR) for Prediction of Total Sedim...
Use of Evolutionary Polynomial Regression (EPR) for Prediction of Total Sedim...Use of Evolutionary Polynomial Regression (EPR) for Prediction of Total Sedim...
Use of Evolutionary Polynomial Regression (EPR) for Prediction of Total Sedim...
CSCJournals
 
710201911
710201911710201911
710201911
IJRAT
 
Application of artificial neural network in metropolitan landscape
Application of artificial neural network in metropolitan landscapeApplication of artificial neural network in metropolitan landscape
Application of artificial neural network in metropolitan landscape
IAEME Publication
 
Adaptive modified backpropagation algorithm based on differential errors
Adaptive modified backpropagation algorithm based on differential errorsAdaptive modified backpropagation algorithm based on differential errors
Adaptive modified backpropagation algorithm based on differential errors
IJCSEA Journal
 
PREDICTING RIVER WATER QUALITY ppt presentation
PREDICTING  RIVER  WATER QUALITY  ppt presentationPREDICTING  RIVER  WATER QUALITY  ppt presentation
PREDICTING RIVER WATER QUALITY ppt presentation
vaddepallysandeep122
 
Hassan - Condor _48_x_36
Hassan - Condor _48_x_36Hassan - Condor _48_x_36
Hassan - Condor _48_x_36
Hassan Tavakol-davani
 
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
MLconf
 
Swift Parallel Scripting for High-Performance Workflow
Swift Parallel Scripting for High-Performance WorkflowSwift Parallel Scripting for High-Performance Workflow
Swift Parallel Scripting for High-Performance Workflow
Daniel S. Katz
 
A Brain Computer Interface Speller for Smart Devices
A Brain Computer Interface Speller for Smart DevicesA Brain Computer Interface Speller for Smart Devices
A Brain Computer Interface Speller for Smart Devices
Mahmoud Helal
 
Improving Distributed Hydrologocal Model Simulation Accuracy Using Polynomial...
Improving Distributed Hydrologocal Model Simulation Accuracy Using Polynomial...Improving Distributed Hydrologocal Model Simulation Accuracy Using Polynomial...
Improving Distributed Hydrologocal Model Simulation Accuracy Using Polynomial...
Putika Ashfar Khoiri
 
A Hybrid Formulation between Differential Evolution and Simulated Annealing A...
A Hybrid Formulation between Differential Evolution and Simulated Annealing A...A Hybrid Formulation between Differential Evolution and Simulated Annealing A...
A Hybrid Formulation between Differential Evolution and Simulated Annealing A...
TELKOMNIKA JOURNAL
 
APPLICATION OF GENE EXPRESSION PROGRAMMING IN FLOOD FREQUENCY ANALYSIS
APPLICATION OF GENE EXPRESSION PROGRAMMING IN FLOOD FREQUENCY ANALYSISAPPLICATION OF GENE EXPRESSION PROGRAMMING IN FLOOD FREQUENCY ANALYSIS
APPLICATION OF GENE EXPRESSION PROGRAMMING IN FLOOD FREQUENCY ANALYSIS
Mohd Danish
 
Mathematical modeling and parameter estimation for water quality management s...
Mathematical modeling and parameter estimation for water quality management s...Mathematical modeling and parameter estimation for water quality management s...
Mathematical modeling and parameter estimation for water quality management s...
Kamal Pradhan
 
Hourly Groundwater Modelling In Tidal Lowlands Areas Using Extreme Learning M...
Hourly Groundwater Modelling In Tidal Lowlands Areas Using Extreme Learning M...Hourly Groundwater Modelling In Tidal Lowlands Areas Using Extreme Learning M...
Hourly Groundwater Modelling In Tidal Lowlands Areas Using Extreme Learning M...
IJERDJOURNAL
 
“DESIGN OF WATER DISTRIBUTION NETWORK FOR DARFAL VILLAGE BY EPANET 2.0 SOFTWARE”
“DESIGN OF WATER DISTRIBUTION NETWORK FOR DARFAL VILLAGE BY EPANET 2.0 SOFTWARE”“DESIGN OF WATER DISTRIBUTION NETWORK FOR DARFAL VILLAGE BY EPANET 2.0 SOFTWARE”
“DESIGN OF WATER DISTRIBUTION NETWORK FOR DARFAL VILLAGE BY EPANET 2.0 SOFTWARE”
IRJET Journal
 
Energy management system
Energy management systemEnergy management system
Energy management system
AmishaSrivastava26
 
[Hydro]geological analysis using open source app: case Cikapundung River
[Hydro]geological analysis using open source app: case Cikapundung River[Hydro]geological analysis using open source app: case Cikapundung River
[Hydro]geological analysis using open source app: case Cikapundung River
Dasapta Erwin Irawan
 
DEM GENERATION AND RIVER ANALYSIS USING HEC-RAS MODEL, HARIDWAR DISTRICT, UTT...
DEM GENERATION AND RIVER ANALYSIS USING HEC-RAS MODEL, HARIDWAR DISTRICT, UTT...DEM GENERATION AND RIVER ANALYSIS USING HEC-RAS MODEL, HARIDWAR DISTRICT, UTT...
DEM GENERATION AND RIVER ANALYSIS USING HEC-RAS MODEL, HARIDWAR DISTRICT, UTT...
IRJET Journal
 
power electronics manual
power electronics manualpower electronics manual
power electronics manual
m.pal pandian
 
A Case Study of Economic Load Dispatch for a Thermal Power Plant using Partic...
A Case Study of Economic Load Dispatch for a Thermal Power Plant using Partic...A Case Study of Economic Load Dispatch for a Thermal Power Plant using Partic...
A Case Study of Economic Load Dispatch for a Thermal Power Plant using Partic...
International Journal of Science and Research (IJSR)
 

Similar to Comparison of ANN Algorithm for Water Quality Prediction of River Ganga (20)

Use of Evolutionary Polynomial Regression (EPR) for Prediction of Total Sedim...
Use of Evolutionary Polynomial Regression (EPR) for Prediction of Total Sedim...Use of Evolutionary Polynomial Regression (EPR) for Prediction of Total Sedim...
Use of Evolutionary Polynomial Regression (EPR) for Prediction of Total Sedim...
 
710201911
710201911710201911
710201911
 
Application of artificial neural network in metropolitan landscape
Application of artificial neural network in metropolitan landscapeApplication of artificial neural network in metropolitan landscape
Application of artificial neural network in metropolitan landscape
 
Adaptive modified backpropagation algorithm based on differential errors
Adaptive modified backpropagation algorithm based on differential errorsAdaptive modified backpropagation algorithm based on differential errors
Adaptive modified backpropagation algorithm based on differential errors
 
PREDICTING RIVER WATER QUALITY ppt presentation
PREDICTING  RIVER  WATER QUALITY  ppt presentationPREDICTING  RIVER  WATER QUALITY  ppt presentation
PREDICTING RIVER WATER QUALITY ppt presentation
 
Hassan - Condor _48_x_36
Hassan - Condor _48_x_36Hassan - Condor _48_x_36
Hassan - Condor _48_x_36
 
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
Hanjun Dai, PhD Student, School of Computational Science and Engineering, Geo...
 
Swift Parallel Scripting for High-Performance Workflow
Swift Parallel Scripting for High-Performance WorkflowSwift Parallel Scripting for High-Performance Workflow
Swift Parallel Scripting for High-Performance Workflow
 
A Brain Computer Interface Speller for Smart Devices
A Brain Computer Interface Speller for Smart DevicesA Brain Computer Interface Speller for Smart Devices
A Brain Computer Interface Speller for Smart Devices
 
Improving Distributed Hydrologocal Model Simulation Accuracy Using Polynomial...
Improving Distributed Hydrologocal Model Simulation Accuracy Using Polynomial...Improving Distributed Hydrologocal Model Simulation Accuracy Using Polynomial...
Improving Distributed Hydrologocal Model Simulation Accuracy Using Polynomial...
 
A Hybrid Formulation between Differential Evolution and Simulated Annealing A...
A Hybrid Formulation between Differential Evolution and Simulated Annealing A...A Hybrid Formulation between Differential Evolution and Simulated Annealing A...
A Hybrid Formulation between Differential Evolution and Simulated Annealing A...
 
APPLICATION OF GENE EXPRESSION PROGRAMMING IN FLOOD FREQUENCY ANALYSIS
APPLICATION OF GENE EXPRESSION PROGRAMMING IN FLOOD FREQUENCY ANALYSISAPPLICATION OF GENE EXPRESSION PROGRAMMING IN FLOOD FREQUENCY ANALYSIS
APPLICATION OF GENE EXPRESSION PROGRAMMING IN FLOOD FREQUENCY ANALYSIS
 
Mathematical modeling and parameter estimation for water quality management s...
Mathematical modeling and parameter estimation for water quality management s...Mathematical modeling and parameter estimation for water quality management s...
Mathematical modeling and parameter estimation for water quality management s...
 
Hourly Groundwater Modelling In Tidal Lowlands Areas Using Extreme Learning M...
Hourly Groundwater Modelling In Tidal Lowlands Areas Using Extreme Learning M...Hourly Groundwater Modelling In Tidal Lowlands Areas Using Extreme Learning M...
Hourly Groundwater Modelling In Tidal Lowlands Areas Using Extreme Learning M...
 
“DESIGN OF WATER DISTRIBUTION NETWORK FOR DARFAL VILLAGE BY EPANET 2.0 SOFTWARE”
“DESIGN OF WATER DISTRIBUTION NETWORK FOR DARFAL VILLAGE BY EPANET 2.0 SOFTWARE”“DESIGN OF WATER DISTRIBUTION NETWORK FOR DARFAL VILLAGE BY EPANET 2.0 SOFTWARE”
“DESIGN OF WATER DISTRIBUTION NETWORK FOR DARFAL VILLAGE BY EPANET 2.0 SOFTWARE”
 
Energy management system
Energy management systemEnergy management system
Energy management system
 
[Hydro]geological analysis using open source app: case Cikapundung River
[Hydro]geological analysis using open source app: case Cikapundung River[Hydro]geological analysis using open source app: case Cikapundung River
[Hydro]geological analysis using open source app: case Cikapundung River
 
DEM GENERATION AND RIVER ANALYSIS USING HEC-RAS MODEL, HARIDWAR DISTRICT, UTT...
DEM GENERATION AND RIVER ANALYSIS USING HEC-RAS MODEL, HARIDWAR DISTRICT, UTT...DEM GENERATION AND RIVER ANALYSIS USING HEC-RAS MODEL, HARIDWAR DISTRICT, UTT...
DEM GENERATION AND RIVER ANALYSIS USING HEC-RAS MODEL, HARIDWAR DISTRICT, UTT...
 
power electronics manual
power electronics manualpower electronics manual
power electronics manual
 
A Case Study of Economic Load Dispatch for a Thermal Power Plant using Partic...
A Case Study of Economic Load Dispatch for a Thermal Power Plant using Partic...A Case Study of Economic Load Dispatch for a Thermal Power Plant using Partic...
A Case Study of Economic Load Dispatch for a Thermal Power Plant using Partic...
 

More from Suresh Pokharel

Sequential and Parallel Searching Algorithms
Sequential and Parallel Searching AlgorithmsSequential and Parallel Searching Algorithms
Sequential and Parallel Searching Algorithms
Suresh Pokharel
 
Information System Architecture
Information System ArchitectureInformation System Architecture
Information System Architecture
Suresh Pokharel
 
Application of Knowledge Engineering in Legal Data : A case study of the info...
Application of Knowledge Engineering in Legal Data : A case study of the info...Application of Knowledge Engineering in Legal Data : A case study of the info...
Application of Knowledge Engineering in Legal Data : A case study of the info...
Suresh Pokharel
 
Case Based Reasoning
Case Based ReasoningCase Based Reasoning
Case Based Reasoning
Suresh Pokharel
 
CNN based Handwritten Signature Recognition
CNN based Handwritten Signature RecognitionCNN based Handwritten Signature Recognition
CNN based Handwritten Signature Recognition
Suresh Pokharel
 
Study of Vitellogenin Motif
Study of Vitellogenin MotifStudy of Vitellogenin Motif
Study of Vitellogenin Motif
Suresh Pokharel
 
Task programming in cloud computing
Task programming in cloud computingTask programming in cloud computing
Task programming in cloud computing
Suresh Pokharel
 
Gene Identification in Alzheimer Disease Using Bioinformatics Analysis
Gene Identification in Alzheimer Disease Using Bioinformatics AnalysisGene Identification in Alzheimer Disease Using Bioinformatics Analysis
Gene Identification in Alzheimer Disease Using Bioinformatics Analysis
Suresh Pokharel
 
Conditional Random Fields
Conditional Random FieldsConditional Random Fields
Conditional Random Fields
Suresh Pokharel
 
Principal component analysis and lda
Principal component analysis and ldaPrincipal component analysis and lda
Principal component analysis and lda
Suresh Pokharel
 

More from Suresh Pokharel (10)

Sequential and Parallel Searching Algorithms
Sequential and Parallel Searching AlgorithmsSequential and Parallel Searching Algorithms
Sequential and Parallel Searching Algorithms
 
Information System Architecture
Information System ArchitectureInformation System Architecture
Information System Architecture
 
Application of Knowledge Engineering in Legal Data : A case study of the info...
Application of Knowledge Engineering in Legal Data : A case study of the info...Application of Knowledge Engineering in Legal Data : A case study of the info...
Application of Knowledge Engineering in Legal Data : A case study of the info...
 
Case Based Reasoning
Case Based ReasoningCase Based Reasoning
Case Based Reasoning
 
CNN based Handwritten Signature Recognition
CNN based Handwritten Signature RecognitionCNN based Handwritten Signature Recognition
CNN based Handwritten Signature Recognition
 
Study of Vitellogenin Motif
Study of Vitellogenin MotifStudy of Vitellogenin Motif
Study of Vitellogenin Motif
 
Task programming in cloud computing
Task programming in cloud computingTask programming in cloud computing
Task programming in cloud computing
 
Gene Identification in Alzheimer Disease Using Bioinformatics Analysis
Gene Identification in Alzheimer Disease Using Bioinformatics AnalysisGene Identification in Alzheimer Disease Using Bioinformatics Analysis
Gene Identification in Alzheimer Disease Using Bioinformatics Analysis
 
Conditional Random Fields
Conditional Random FieldsConditional Random Fields
Conditional Random Fields
 
Principal component analysis and lda
Principal component analysis and ldaPrincipal component analysis and lda
Principal component analysis and lda
 

Recently uploaded

New techniques for characterising damage in rock slopes.pdf
New techniques for characterising damage in rock slopes.pdfNew techniques for characterising damage in rock slopes.pdf
New techniques for characterising damage in rock slopes.pdf
wisnuprabawa3
 
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student MemberIEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
VICTOR MAESTRE RAMIREZ
 
22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt
KrishnaveniKrishnara1
 
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
ihlasbinance2003
 
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesHarnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Christina Lin
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
IJECEIAES
 
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Sinan KOZAK
 
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
IJECEIAES
 
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdfIron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
RadiNasr
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
insn4465
 
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
University of Maribor
 
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball playEric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
enizeyimana36
 
spirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptxspirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptx
Madan Karki
 
A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...
nooriasukmaningtyas
 
Textile Chemical Processing and Dyeing.pdf
Textile Chemical Processing and Dyeing.pdfTextile Chemical Processing and Dyeing.pdf
Textile Chemical Processing and Dyeing.pdf
NazakatAliKhoso2
 
International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...
gerogepatton
 
Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...
bijceesjournal
 
Question paper of renewable energy sources
Question paper of renewable energy sourcesQuestion paper of renewable energy sources
Question paper of renewable energy sources
mahammadsalmanmech
 
132/33KV substation case study Presentation
132/33KV substation case study Presentation132/33KV substation case study Presentation
132/33KV substation case study Presentation
kandramariana6
 
Embedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoringEmbedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoring
IJECEIAES
 

Recently uploaded (20)

New techniques for characterising damage in rock slopes.pdf
New techniques for characterising damage in rock slopes.pdfNew techniques for characterising damage in rock slopes.pdf
New techniques for characterising damage in rock slopes.pdf
 
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student MemberIEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
 
22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt
 
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
 
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesHarnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
 
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
 
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
 
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdfIron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
 
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
 
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball playEric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
Eric Nizeyimana's document 2006 from gicumbi to ttc nyamata handball play
 
spirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptxspirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptx
 
A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...
 
Textile Chemical Processing and Dyeing.pdf
Textile Chemical Processing and Dyeing.pdfTextile Chemical Processing and Dyeing.pdf
Textile Chemical Processing and Dyeing.pdf
 
International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...
 
Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...
 
Question paper of renewable energy sources
Question paper of renewable energy sourcesQuestion paper of renewable energy sources
Question paper of renewable energy sources
 
132/33KV substation case study Presentation
132/33KV substation case study Presentation132/33KV substation case study Presentation
132/33KV substation case study Presentation
 
Embedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoringEmbedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoring
 

Comparison of ANN Algorithm for Water Quality Prediction of River Ganga

  • 1. Comparison of ANN Algorithm for Water Quality Prediction of River Ganga Aradhana Giri and N.B. Singh Department of Civil Engineering, Institute of Engineering and Technology Lucknow, UP, India Presented By: Suresh Pokharel (074MSCSK015) M.Sc. in Computer System and Knowledge Engineering Institute of Engineering, Pulchowk Campus 1
  • 2. Introduction ● Maintaining the Availability and Quality of the freshwater resources : A vital environmental challenge ● Human actions in urban areas surrounding the Ganga River (i.e. Kanpur, Allahabad, Varanasi etc.) generates severe impact. Causes of Water Pollution: - Rapid increase in population - Rising standards of living - Exponential growth of Industrialization 2
  • 3. Introduction to Ganga River ● The most worshipped river of the Hindus ● One of the most polluted river of the country ● 25 big cities located along its bank ● 95% of the sewage enters directly to the river ● Total length: 2525 KM (Gangotri to Gangasagar) ● Highly Polluted: 600 KM 3
  • 4. Ganga River : National River of India 4
  • 5. A man cleaning garbage along the banks of the river Ganges in Kolkata, India, April 9, 2017. 5
  • 6. Objective To develop two different ANN models and compare their performances to evaluate the current situation and predict the behaviour of water quality with respect to changes in pollutant loads and hydrological conditions 6
  • 7. Gathered Data ● Hydro Meteorological data ● Quality Measurement in River ● Land use ● Management practices on land ● Point pollution measurement ● Flow and water level data 7
  • 8. Table: PRIMARY WATER QUALITY CRITERIA FOR DESIGNATED (BEST - USE - CLASSES) Source: http://www.uppcb.com/river_quality.htm 8
  • 10. Dissolved Oxygen ● Dissolved oxygen refers to the level of free, non-compound oxygen molecule present in water ● Fish and aquatic animals cannot split oxygen from water (H2O) or other oxygen-containing compounds. ● Measured in units of milligrams of gas per liter of water – mg/L. (parts per million or ppm). 10
  • 11. How Temperature affects water quality? ● Temperature impacts both the chemical and biological characteristics of surface water ● Warm water is less capable of holding dissolved oxygen. ● Low dissolved oxygen levels leave aquatic organisms in a weakened physical state and more susceptible to disease, parasites, and other pollutants. 11 Source: US Geographical Survey (https://water.usgs.gov/edu/temperature.html)
  • 12. Artificial Neural Network Model Monthly data of previous 5 years (2008 to 2012) are measured with attributes: ● Temperature ● Flow rate ● BOD (Biochemical Oxygen Demand) ● DO (Dissolved Oxygen) Implementation Platform: MATLAB NN Toolbox Data Source: Uttar Pradesh Pollution Control Board (UPPCB) 12
  • 13. Division of Data Training Data : 70% Testing Data : 30% Input_Train: 1x42 Output_Train: 1x42 Input_validation: 1x18 Output_validation: 1x18 13
  • 14. Training Algorithms Back Propagation: Backpropagation works by using a loss function to calculate how far the network was from the target output. 14
  • 15. Training Algorithm - 1 Gradient Descent with adaptive learning: ● Function name: traingda ● A network training function that updates weight and bias values according to gradient descent with adaptive learning rate. ● Backpropagation is used to calculate derivatives of performance dperf with respect to the weight and bias variables X. ● Each variable is adjusted according to gradient descent: dX = alpha*d(perf)/dX ● Gradient Descent has a problem of getting stuck in Local Minima 15
  • 16. Activation Function for GDA For Hidden Layer real-valued function ф whose value depends only on the distance Gaussian radial basis function r = |x-xi | ф = e-(εr)^2 For Output Layer Linear activation function Transfer Function Hyperbolic Sigmoid Tangent function ( tansig ) 16
  • 17. Training Algorithm - 2 Levenberg Marquardt Back Propagation: ● The LM curve-fitting method : combination the gradient descent method and the Gauss-Newton method. Backpropagation is used to calculate the Jacobian jX of performance perf with respect to the weight and bias variables X. Each variable is adjusted according to Levenberg-Marquardt, jj = jX * jX je = jX * E dX = -(jj+I*mu) je where E is all errors and I is the identity matrix. Function in Matlab: trainlm Source: https://www.mathworks.com/help/deeplearning/ref/trainlm.html 17
  • 18. Activation Function for LM For Hidden Layer Tanh (Hyperbolic Tangent function) f(x) = 1 — exp(-2x) / 1 + exp(-2x) -1 < output < 1 For Output Layer Linear activation function Transfer Function Log Sigmoid Transfer function (logsig ) 18
  • 19. Testing ● Test with unknown data set ● After training with each ANN configuration, Performance evaluation methods used : Correlation Coefficient Mean Square Error (MSE) Root Mean Square Error (RMSE) Xi : Real ith data Yi : ith Estimate N : NUmber of Xi, Yi X ̄ : Average of X 19
  • 20. Results Fig. Comparison between output of Levenberg Marquardt (LM) backpropagation and Gradient Descent with adaptive learning (GDA) rate backpropagation 20
  • 21. 21
  • 22. Results (contd ...) Best Trained R = 0.9860 Best Validation R = 0.9800 Best Output vs. Target = 0.9919 ● In comparison to GDA, result of LM is found to be more accurate ● LM is faster as compared to GDA 22
  • 23. References 1. Giri, Aradhana, and N. B. Singh. "Comparison of Artificial Neural Network Algorithm for Water Quality Prediction of River Ganga." Environmental Research Journal 8.2 (2014): 55-63. 2. Webb, Bruce W., and Franz Nobilis. "Long-term changes in river temperature and the influence of climatic and hydrological factors." Hydrological Sciences Journal 52.1 (2007): 74-85. 3. Zhang, Guoqiang, B. Eddy Patuwo, and Michael Y. Hu. "Forecasting with artificial neural networks:: The state of the art." International journal of forecasting 14.1 (1998): 35-62. 4. Maier, Holger R., and Graeme C. Dandy. "Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications." Environmental modelling & software 15.1 (2000): 101-124. 23