Water Quality Predication

T.E. sensor lab project report submitted in

fulfilment of the requirements of the
degree of

Information Technology
By

Omkar Jadhav [EU1214016](15)

Viraj Bamne [EU1214013](01)
Ritesh chaubey [EU1214041](04)
Surendra gupta [EU1214017] (11)
Under the guidance of

Mrs. Pratiksha Patil

Assistant Professor

Department of Information Technology

St. John College of Engineering and Management, Palghar

University of Mumbai
2023–2024
 CERTIFICATE
This is to certify that the T.E. mini-project entitled “Water Quality Predication ” is a bonafide
work of “Surendra Gupta” (EU1214016) (11) , “Omkar jadhav” (EU1214020) (15), and “Viraj
bamne” (EU1214033) (01) , “Ritesh chaubey” (EU1214035) (04) submitted to University of
Mumbai in Partial fulfilment of the requirement for the award of the degree of “Information
Technology “ Engineering” during the academic year 2023-24.

Mrs. Pratiksha patil

Guide

Dr. Arun Saxena Dr. G.V. Mulgund

Head of Department Principal

ii
 T.E. Sensor lab project Report Approval

This mini-project synopsis entitled water quality prediction using sensor by Omkar
Jadhav, Ritesh Chaubey, Viraj Bamne, Surendra Gupta is approved for the degree of
Information Technology Engineering from University of Mumbai.

Examiners

1.

2.

Date:

Place:
 Abstract
Turbidity is a concept that is significant when discussing liquids since it is
crucial to understanding liquid dynamics and is used to assess the cleanliness of
the water. How clear or hazy a liquid is depends on the amount or degree of
turbidity in it. This occurs due to the air being compressed, which is full of
numerous tiny invisible particles that resemble white smoke. The light waves
scatter when they travel through liquids, since these small particles are present a
liquid's turbidity is directly inversely correlated with the number of free
suspended particles, meaning that as the number of particles raises, so will the
turbidity. So let's talk about what turbidity is and how to use an Arduino to test
the turbidity of a liquid in this lesson. It is possible to connect a pH meter to an
Arduino board and read the pH-value of the water to further assess the water
purity. The evaluation of the degree to which suspended particles in water reduce
transparency. The TSS (Total Suspended Solids) could be estimated using a
measurement of turbidity. To determine the condition of the water, the Arduino
turbidity sensor monitors turbidity. TSS concentration has an impact on light
transmittance and scattering rates, which can be employed to find out whether
there are any suspended particles in water.

iv
 Table of Contents
Abstract iv

List of Figures vii

Chapter 1 Introduction 1

1.1 Motivation 2

1.2 Problem Statement 2

2
1.3 Objective

2
1.4 Scope
Chapter 2 Review of Literature 4

Chapter 3 Requirement and cost Analysis 5

3.1 Sensor Requirements 5

Chapter 4 Report on Present Investigation 6

4.1 Proposed System 6

4.1.1 Block diagram of Proposed System 6

4.2 Implementation 7

4.2.1 Pseudo code 7

4.2.4 Screenshots of the output with description 9

Chapter 5 Results and Discussion 11

Chapter 6 Conclusion 12

6.1 Conclusion 12

References 13

v
 List of Figures
Figure No. Figure Name Page No.

4.1 Block diagram 6

4.2.2 Circuit Diagram 9

vi
 Chapter 1
Introduction

Water is a highly significant need of every single living being. With an increase in the human population, the
requirement for preserving water assets is acquiring greater significance. Several parameters are used for
identifying water quality based on the samples' water level, pH level, turbidity, and salt content.
The machine learning techniques are combined with a GIS based on data availability and quality. Machine
learning algorithms must account for spatial autocorrelation and temporal dynamics to predict water quality.
Incorporating spatial analysis techniques within GIS, such as geostatistics, can help capture these variations
and improve the accuracy of predictions. By addressing these problems, robust machine learning and GIS-
based frameworks can be determined for water quality index calculation, aiding in efficient water
management and decision-making processes. Water quality analysis plays a vital role in assessing and
monitoring the health and safety of water sources. It involves evaluating various physical, chemical, and
biological parameters to determine whether the water quality meets the required standards for its intended
use, such as drinking purposes, recreational activities, and ecosystem preservation. Traditional water
quality monitoring systems have relied on conventional laboratory-based methods in which water samples
are collected from various resources and transported to the laboratory for analysis. Water samples are
collected manually from different points of interest, such as rivers, lakes, and wells, and detailed studies are
performed using specialized equipment and techniques in laboratory conditions. The obtained data is
analyzed and interpreted to assess the water quality. It is compared against the established standards or
guidelines to meet the criteria for its designated purpose. The limitations of traditional laboratory-based
water quality monitoring systems are that they are time-consuming and costly, lack real-time monitoring,
and are inaccessible to remote locations.

1.1 Motivation
 Water Quality Monitoring: Turbidity is a key parameter in assessing water quality By measuring the
turbidity of water, we can get a sense of the number of suspended particles in it, which often correlates
with the level of pollutants.
 Educational Purpose: This project can serve as a great learning experience for students or hobbyists
interested in environmental science, electronics, and programming. It provides hands-on experience with
Arduino programming, sensor interfacing, and data analysis.
 Environmental Impact: Regular monitoring of water bodies can help in early detection of pollution,
enabling timely action to prevent further damage. This project could be a step towards more widespread,
decentralized environmental monitoring.
 Innovation and Research: This project can be a base for more complex systems, like an IoT-based
water quality monitoring system.
 Community Health: In many parts of the world, access to clean water is a major issue. A low-cost,
easy-to-use turbidity sensor can help communities monitor their water sources and take necessary
actions if the water quality deteriorates.

1
1.2 Problem Statement
The degradation of water quality in natural and man-made aquatic systems poses significant challenges to
environmental sustainability and human well-being. Traditional methods of water quality monitoring often
rely on periodic sampling and laboratory analysis, which can be time-consuming, costly, and limited in
spatial coverage. As a result, there is a growing need for innovative approaches that enable continuous,
real-time monitoring of key water quality parameters. This problem statement highlights the importance of
leveraging sensor technology for water quality prediction, identifies key challenges, and outlines the
objectives of the proposed study. It provides a clear direction for addressing the complexities associated
with real-time water quality monitoring and management.

1.3 Objectives
The primary objective of this project is to develop a predictive model that utilizes sensor data to forecast
water quality parameters in [specify the target water bodies or locations]. By accurately predicting water
quality trends and detecting anomalies, this model aims to support proactive decision-making for water
resource management and environmental protection efforts.

1.4 Scope
Brief overview of turbidity as a key parameter in water quality assessment. Importance of turbidity
measurement in various industries. To evaluate the performance of turbidity sensors in measuring water
clarity. To compare different turbidity measurement technologies. Definition and significance of turbidity.
Current methods and technologies used for turbidity measurement. Description of the turbidity sensor
technology, including its design and operational principles. Calibration and validation procedures for the
turbidity sensor. Detailed layout of the sensor system, including the Arduino microcontroller and sensor
modules. Explanation of the data acquisition process from the turbidity sensor. Techniques for interpreting
the sensor data. Conversion of sensor readings into turbidity units (NTU). Presentation of the findings from
the sensor data. Discussion on the accuracy, reliability, and limitations of the turbidity sensor. Exploration
of practical applications of turbidity sensors in water treatment, environmental monitoring, and industrial
processes.

2
 Chapter 2
Review of Literature

Sr.no Journal Title Author Conclusion

1 INTERNATIO ARDUINO- Zin Mar Lay, Turbidity sensor is useful for measuring
NAL BASED Sandar Lwin water quality measurement in effluent
JOURNAL DETECTION measurement, sediment research,
FOR OF WATER laboratory research in river , streams,
INNOVATIVE QUALITY BY sea, and waste water
RESEARCH TURBIDITY
IN SENSOR
MULTIDISCIP
LINARY
FIELD

2 International Turbidity Daneshwari To determine the condition of the water,

Research Sensor and N. Kori, the Arduino turbidity sensor monitors
Journal of Arduino for Rajashekarapp turbidity.
Engineering Water a
and Quality
Technology Measurement
(IRJET)
3 International Arduino Uno- Zulfi Azhar In the test, clear water produces a
Journal of based water voltage value of 4.55 volts with an NTU
Engineering & turbidity meter , Mhd. Irwan value of close to 0 while the test results
Technology using LDR Dwitama of cloudy and dark water samples yield
Harahap a voltage value of 0.06 volts with an
and LED NTU value close to 500. The equation
sensors for obtaining the value of NTU is y = -
111.25x + 506.67. This tool can be used
to determine the water turbidity level.

3
 Chapter 3
Requirement and cost Analysis

❖ Sensors Requirements
 Turbidity sensor
 Microcontroller
 Arduino uno
 Power supply
 Breadboard

❖ Sensors Requirements cost

 Turbidity sensor – 300rs-800rs
 Arduino uno – 500rs-1000rs
 LCD Display -- 400rs -600rs
 Power supply – 200rs-500rs
 Breadboard – 100rs-200rs
Total Estimated Cost- 3100rs

❖ Software Requirements
 Arduino IDE

4
 Chapter 4
Report on Present Investigation

4.1 Proposed System

( 4.1.1 Block diagram of Proposed System )

5
 Chapter 4
Report on Present Investigation

4.2

4.)1.2 Circuit Diagram

(Fig 4.1.2 Circuit Diagram)

(Fig 4.1.3 Circuit Diagram 2)

 Pseudo code

// Define the pin where the turbidity sensor is connected

int turbiditySensorPin = A0;

// Variable to store the turbidity value

int turbidityValue = 0;

void setup() {
// Initialize serial communication at 9600 bits per second
Serial.begin(9600);
}

void loop() {
// Read the value from the turbidity sensor
turbidityValue = analogRead(turbiditySensorPin);

// Convert the analog value to NTU (Nephelometric Turbidity Units)

float NTU = convertToNTU(turbidityValue);

// Print the NTU value to the serial monitor

Serial.print("Turbidity: ");
Serial.print(NTU);
Serial.println(" NTU");

// Wait for a second before reading the value again

delay(1000);
}

// Function to convert analog value to NTU

float convertToNTU(int analogValue) {
// Placeholder for the actual conversion logic
// This will depend on the calibration of your specific sensor
// and the voltage to NTU relationship
// For example:
// NTU: 500 Voltage: 3.27V
// NTU: 50 Voltage: 4.10V
// NTU: 0.5 Voltage: 4.21V
// You'll need to create a function that maps these values correctly

float NTU = 0; // Initialize NTU variable

// Add conversion logic here
return NTU;
}
4.3 Implementation
4.3.1 Screenshots of the output with description:

( Fig 4.2.1 Project Model)

4.3.2 Sensor Screenshot

( Fig. 4.2.2 Sensor Model )

11
 Chapter 5
Results and Discussion

Water quality prediction leveraging sensor data represents a pivotal advancement in environmental
monitoring and management strategies. By harnessing the capabilities of sensor technology, this approach
enables real-time or near real-time monitoring of key water quality parameters, including pH, turbidity,
dissolved oxygen, temperature, conductivity, and contaminant levels. The continuous data streams
collected by sensors offer a wealth of information about the allowing for the development of predictive
models that forecast water quality conditions with remarkable accuracy. These models not only provide
insights into current water quality status but also offer valuable foresight into future trends and potential
pollution events. By integrating anomaly detection algorithms, these systems can promptly identify
abnormal patterns or sudden deviations from expected water quality norms, enabling proactive
interventions to mitigate environmental risks and safeguard public health. Furthermore, the predictive
capabilities of these models empower stakeholders, including water resource managers, environmental
agencies, and policymakers, with actionable insights for decision-making.

11
 Chapter 6
Conclusion
.

In conclusion, water quality prediction utilizing sensor technology represents a transformative approach to
environmental monitoring and management. By harnessing real-time or near real-time data collection
capabilities, these systems offer unprecedented insights into the dynamics of water quality parameters. The
development of predictive models enables not only the assessment of current water quality conditions but
also the anticipation of future trends and potential pollution events. Integration with anomaly detection
algorithms further enhances the system's ability to proactively identify and address environmental risks,
safeguarding both ecosystem health and public well-being. Through actionable insights provided to
stakeholders, including water resource managers, environmental agencies, and policymakers, these
predictive systems support informed decision-making and effective management interventions. By
optimizing monitoring strategies, implementing early warning systems, and fostering collaborative
partnerships, water quality prediction with sensor data contributes to the sustainable management and
protection of freshwater resources. Moving forward, continued advancements in sensor technology, data
analytics, and stakeholder engagement will further enhance the efficacy and applicability of these
predictive systems, ensuring the resilience and longevity of our water ecosystems in the face of evolving
environmental challenges.

12
 References

[1] G.M. Snoek, “Walmart Sales Analysis And Prediction”, IEEE TRANSACTIONS ON PATTERN
ANALYSIS AND MACHINE INTELLIGENCE, VOL. 32, NO.9, SEPTEMBER 2010
[2] Rashmi Jeswami, “Predicting Walmart Sales, Exploratory Data Analysis , And Walmart sales Dashboard”
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL 35, NO.
5, MAY 2013
[3] Gurudevi, Rashmi Patil ” Walmart Sales Forecasting using Machine learning” IEEE TRANSACTIONS
ON AUTOMATION SCIENCE AND ENGINEERING, VOL. 4, NO. 1, JANUARY 2007
[4] Zhao, J., Tang, W., Fang, X., Wang, J., Liu, J., Ouyang, H., ... & Qiang, J. (2015, October). A novel
electricity sales forecasting method based on clustering regression and time-series analysis. In
Proceedings of the 2015
[5] International Conference on Artificial Intelligence and Software Engineering. Singh, D., & Singh, B.
(2020).“Investigating the impact of data normalization on classification performance” Applied Soft
Computing, 97, 105524).

1
3
 Acknowledgement

Today, we cannot find appropriate words that will express deep sense of gratitude and satisfaction. We are
indebted to our inspiring guide Mrs. Pratiksha Patil who have extended all the valuable guidance giving
constant encouragement through various difficult stages for development of the project. We would also like
to acknowledge the patience that our ever-beloved parents have shown during our efforts and the
encouragement we have received from them.

Thus, we have fully obliged and convey our thanks to the teaching and as well as non- teaching staff of the
department. Special thanks to all the lab assistants for helping us with problems developed in the lab and
assisting, helping us to solve any problems generated on the spot. Last but not the least we would like to
thank all direct and indirect identities of the college with whom we took the strides for this successful
project.

14