Water pollution has become a major environmental concern due to rapid industrialization, urbanization, and

agricultural activities. Traditional water quality monitoring methods are time-consuming and lack real-time

capabilities. This paper presents an IoT-based smart water quality surveillance system using a remotely controlled boat

integrated with sensors and wireless communication. The system utilizes an ESP32 microcontroller to measure

parameters such as pH, turbidity, total dissolved solids (TDS), and temperature. The collected data is transmitted in

real time to the Blynk IoT platform for remote monitoring and analysis. The boat can be navigated using a mobile

application, enabling monitoring in remote and hazardous locations. The proposed system provides a cost-effective,

efficient, and scalable solution for continuous water quality monitoring and environmental protection.

water pollution. This contamination not only disturbs aquatic ecosystems but also poses serious health risks to

humans by spreading waterborne diseases such as cholera, typhoid, and hepatitis. Therefore, maintaining and

monitoring water quality has become a critical global concern.

Traditional water quality monitoring methods involve manual collection of samples followed by laboratory

analysis. Although these methods provide accurate results, they are time-consuming, labor - intensive, and do

not offer real-time monitoring. Additionally, these methods are limited to specific locations and cannot

effectively capture rapid or dynamic changes in water conditions. Monitoring remote or hazardous water bodies

such as deep lakes, polluted rivers, and reservoirs is also difficult and unsafe using conventional approaches. As

a result, there is a need for a more efficient, automated, and real-time monitoring system.

With the advancement of Internet of Things (IoT) technology, smart and continuous monitoring systems have

Several researchers have worked on water quality monitoring using IoT and embedded systems.

Lakshmikantha et al. proposed an IoT-based system for real-time monitoring using pH and turbidity sensors.

Aslam and Hassan developed a remote-controlled boat system for water monitoring applications.

Shukla et al. introduced an autonomous water monitoring system for remote areas.

Metkari et al. designed an IoT-based pollution monitoring boat for real-time data collection.

Most existing systems either focus only on stationary monitoring or require complex infrastructure. The proposed

system improves efficiency by integrating real-time monitoring, remote navigation, and IoT-based data

visualization in a cost-effective and user-friendly solution.

The proposed system uses sensors such as pH, turbidity, TDS, and temperature to collect real-time water quality

data. These sensors are interfaced with the ESP32 microcontroller, which processes and transmits the data via

Wi-Fi to the Blynk IoT platform. The data is displayed on a mobile application for remote monitoring. The boat

is controlled through a smartphone using an L298N motor driver, enabling movement across different locations.

A threshold-based alert system is implemented to notify users when parameters exceed safe limits, ensuring

efficient and reliable water quality monitoring.

The system consists of four main layers:

1. Input Layer: Sensors (pH, Turbidity, TDS, Temperature)

The processed data is transmitted via Wi-Fi to the Blynk IoT platform for real-time monitoring.

The L298N motor driver controls the DC motors, enabling remote navigation of the boat through a mobile

application.

Block diagram of Smart Water Quality Surveilliance System

A. Hardware Components

The proposed system consists of the following hardware components:

1. ESP32 Microcontroller

7. DC Motors with Propellers

The system operates using an ESP32 microcontroller, which acts as the central processing unit. It collects real-

time data from sensors such as pH, turbidity, TDS, and temperature. The acquired data is processed and

transmitted to the cloud platform via Wi-Fi for remote monitoring.

The user controls the movement of the boat through a mobile application. The control signals are received by

the ESP32 and executed using the L298N motor driver, which drives the DC motors. This enables the boat to

The sensors continuously monitor water quality parameters, and the system generates alerts when any parameter

exceeds predefined safe limits. This ensures efficient, real-time, and reliable water quality monitoring.

ESP32 microcontroller and Wi-Fi connectivity. The boat responded efficiently to remote control commands,

enabling smooth navigation across the water body. Additionally, stable communication with the IoT platform

ensured continuous monitoring without interruptions.

The collected data was analyzed based on key water quality parameters. The pH value indicates the acidity or

alkalinity of water, which is essential for determining its suitability. Turbidity reflects the clarity of water and

helps identify the presence of suspended particles. Total Dissolved Solids (TDS) indicate the level of dissolved

impurities and contamination. Temperature plays a significant role in affecting aquatic life and influences other

chemical and biological processes in water.

3. Sustainability: The integration of solar-harvesting modules ensures a reduced carbon footprint and extends

the operational window without frequent manual charging.

4. Economic Feasibility: The use of off-the-shelf sensors and open-source IoT architecture significantly

reduces the Capital Expenditure (CAPEX) compared to industrial-grade static monitoring stations.

Despite its efficacy, the current prototype is subject to certain technical constraints:

1. Network Dependency: The system relies heavily on Wi-Fi/Internet availability. Data packets may be lost in

2. Power Management: Although solar-supported, the peak power consumption of the propulsion motors limits

Future iterations of this research will focus on enhancing the autonomy and range of the system:

1. Geospatial Mapping: Integrating GPS modules to correlate water quality data with precise geographical

2. Long-Range Communication: Implementation of LoRa WAN (Long Range Wide Area Network) or GSM to

3. Predictive Analytics: Utilizing Machine Learning (ML) algorithms to predict future contamination trends

4. Swarm Robotics: Developing a multi-agent system where multiple boats coordinate to cover vast reservoirs