Smart Agriculture System Final Year Project Using IoT, ESP32 & Source Code

Smart Agriculture System Project Guide for Final Year Students

A Smart Agriculture System is one of the best final-year project ideas for students who want a practical IoT project with real-world use. It combines sensors, automation, cloud storage, dashboards, and optional AI/ML features to monitor farm conditions and improve irrigation decisions.

Quick Answer: What Is a Smart Agriculture System?

A Smart Agriculture System is an IoT based agriculture monitoring and automation system that uses sensors to track soil moisture, temperature, humidity, rainfall, water level, and other field conditions. The system sends this data to a controller such as ESP32, Arduino, NodeMCU, or Raspberry Pi, then displays it on a web/mobile dashboard and can automatically control irrigation.

For final-year students, it is a strong project because it covers IoT, embedded systems, database management, dashboard development, automation, and source code implementation.

Project at a Glance

Item	Recommended Option
Project Type	IoT / Embedded / Web Dashboard
Difficulty Level	Beginner to Intermediate
Best For	B.Tech, BE, BCA, MCA, BSc IT, MSc IT
Core Hardware	ESP32, soil moisture sensor, DHT11/DHT22, relay, pump
Software Stack	Firebase/MySQL, HTML/CSS/JS, PHP/Python/Node.js
Main Output	Live sensor dashboard + automatic irrigation
Estimated Duration	7–15 days for basic version
Advanced Add-ons	Weather API, crop recommendation, pest detection, alerts

Why Smart Agriculture Is a Strong Final-Year Project

Traditional farming often depends on manual observation and fixed irrigation schedules. This can lead to overwatering, underwatering, poor crop monitoring, and delayed response to field problems.

A smart farming project using IoT solves this by collecting real-time data and converting it into useful actions. For example, when soil moisture drops below a threshold, the system can automatically turn on a water pump. Once moisture reaches the safe range, the pump turns off.

This project is also relevant in India because digital agriculture is becoming a national priority. The Digital Agriculture Mission includes AgriStack, Krishi Decision Support System, and Soil Profile Mapping to support data-driven farming services. Krishi-DSS integrates satellite, weather, soil, crop, reservoir, groundwater, and scheme data for agriculture decision support.

Smart Agriculture Project Abstract

This project aims to design and develop an IoT based Smart Agriculture System that monitors soil moisture, temperature, humidity, and water level in real time. The system uses sensors connected to a microcontroller to collect field data and send it to a database or cloud platform. A web dashboard displays live readings, irrigation status, and alerts. Based on moisture thresholds, the system automatically controls a water pump to improve irrigation efficiency and reduce manual effort.

Main Objectives of the Project

The main objective is to help farmers and students understand how IoT can improve field monitoring and irrigation control.

Key objectives include:

• Monitor soil moisture, temperature, humidity, and water level.
• Automate irrigation using a relay-controlled water pump.
• Store sensor data with timestamp and pump status.
• Display live readings on a dashboard.
• Send alerts for dry soil, high temperature, or low water level.
• Provide a scalable base for crop recommendation and AI farming modules.

Components Required for Smart Agriculture System

Component	Purpose	Approx. Use
ESP32 / NodeMCU	Main IoT controller	Reads sensors and sends data online
Soil Moisture Sensor	Detects soil dryness	Irrigation decision
DHT11 / DHT22	Measures temperature and humidity	Climate monitoring
Relay Module	Switches pump ON/OFF	Irrigation automation
Mini Water Pump	Supplies water	Demo irrigation
Water-Level Sensor	Checks tank level	Prevents dry pump run
Rain Sensor	Detects rainfall	Avoids unnecessary irrigation
Firebase / ThingSpeak / MySQL	Stores sensor data	Dashboard and reports
Web Dashboard	Shows output	User/admin interface

ESP32 is a strong choice because it supports Wi-Fi and Bluetooth connectivity, making it practical for IoT dashboards. Arduino Uno is beginner-friendly, but it requires an extra Wi-Fi/GSM module for online data transfer.

Smart Agriculture System Architecture

A good agriculture monitoring system project has four layers.

1. Sensor Layer

This layer collects physical field data. It includes soil moisture, DHT11/DHT22, water-level, rain, pH, NPK, and light sensors.

2. Controller Layer

The controller processes sensor values and applies decision logic. ESP32 or NodeMCU is best for IoT projects because Wi-Fi is built in. Arduino is suitable for offline or beginner demos.

3. Cloud / Database Layer

The system stores readings in Firebase, MySQL, MongoDB, or ThingSpeak. Firebase is useful when the dashboard needs real-time sync across devices. ThingSpeak is useful for collecting, visualizing, and analyzing live IoT data streams.

4. Application Layer

This is the user-facing dashboard. It shows moisture percentage, temperature, humidity, pump status, alerts, charts, and historical logs.

Circuit Diagram Explanation

In a basic ESP32 smart agriculture project:

• Soil moisture sensor analog output connects to an ESP32 analog pin.
• DHT11/DHT22 data pin connects to a digital GPIO pin.
• Relay input connects to a GPIO pin.
• Water pump connects through the relay, not directly to ESP32.
• External power supply is used for the pump.
• ESP32 sends readings to Firebase, MySQL API, or ThingSpeak through Wi-Fi.

Important: The pump should not be powered directly from the microcontroller. Use a relay module and separate supply to protect the board.

Suggested image alt text:
IoT based smart agriculture system circuit diagram using ESP32 soil moisture sensor relay and water pump

Working Flow / Algorithm

1. Start the system.
2. Connect ESP32 to Wi-Fi.
3. Read soil moisture, temperature, humidity, and water level.
4. Convert raw sensor values into readable units.
5. Compare soil moisture with threshold.
6. If moisture is below 35%, turn pump ON.
7. If moisture reaches 60%, turn pump OFF.
8. Upload readings and pump status to the database.
9. Display live data on dashboard.
10. Generate alerts for abnormal conditions.

This makes the project more than a sensor display. It becomes a soil moisture based irrigation system with decision-making.

Source Code Flow

A strong smart agriculture system project with source code should be organized clearly.

File / Folder	Purpose
/hardware/esp32_code.ino	Sensor reading and pump control
/backend/api/	Receives data from ESP32
/database/schema.sql	Tables for users, sensors, readings, alerts
/frontend/dashboard/	Web dashboard UI
/admin/	Admin login, user management, thresholds
/reports/	Test cases, screenshots, project report assets

Basic source code logic:

Read sensor values
Check moisture threshold
Control pump through relay
Send data to cloud/database
Fetch latest data on dashboard
Show charts and alerts

Database Design

Table Name	Important Fields	Purpose
users	user_id, name, email, password, role	Login and access control
sensor_readings	id, moisture, temperature, humidity, water_level, created_at	Stores field data
irrigation_logs	id, pump_status, moisture_value, action_time	Tracks pump activity
alerts	id, alert_type, message, status, created_at	Stores warning messages
crops	crop_id, crop_name, ideal_moisture, ideal_temp	Optional crop advisory

Dashboard Features

A professional dashboard should include:

• Live soil moisture percentage.
• Temperature and humidity cards.
• Pump ON/OFF status.
• Manual pump override.
• Daily moisture trend chart.
• Alert panel.
• Admin threshold settings.
• Exportable report logs.

This improves user engagement and also helps during project viva because faculty can clearly see input, processing, output, and automation.

Implementation Guide

Step 1: Define Scope

Start with soil moisture monitoring and automatic irrigation. Add advanced features only after the basic version works.

Step 2: Test Sensors Individually

Check soil moisture, DHT11/DHT22, and water-level sensor separately before connecting all components.

Step 3: Calibrate Soil Moisture

Record dry soil and wet soil values. Convert them into percentage values. Without calibration, sensor readings may be inaccurate.

Step 4: Add Pump Control

Use a relay module. Set safe moisture thresholds such as:

Condition	Action
Moisture below 35%	Pump ON
Moisture between 35–60%	Monitor
Moisture above 60%	Pump OFF
Water tank low	Pump OFF + alert

Step 5: Connect Database

Use Firebase, ThingSpeak, or MySQL API to store data. Store readings with timestamps for report generation.

Step 6: Build Web Dashboard

Create user and admin login. Show cards, charts, logs, and alerts.

Step 7: Add Report and PPT Material

Prepare abstract, problem statement, system architecture, flowchart, modules, database design, test cases, output screens, limitations, and future scope.

Testing Table

Test Case	Input Condition	Expected Output
Dry soil test	Moisture below 35%	Pump turns ON
Wet soil test	Moisture above 60%	Pump turns OFF
High temperature	Temperature above set limit	Alert generated
Low tank level	Water level low	Pump disabled
Sensor failure	No sensor reading	Error alert
Dashboard test	New reading uploaded	UI updates correctly

Advantages

• Reduces manual field monitoring.
• Saves water through threshold-based irrigation.
• Gives real-time visibility through dashboard.
• Supports remote monitoring.
• Can be extended with AI/ML modules.
• Useful for academic demo and real-world farming use cases.

Limitations

• Low-cost sensors need calibration.
• Internet failure may delay cloud updates.
• Soil readings vary by soil type.
• The demo version may not represent full farm-scale deployment.
• Pump and relay wiring must be handled safely.

Advanced Features to Make the Project Stand Out

To make the project more impressive, add:

• Weather API based irrigation decision.
• Crop recommendation using soil and climate data.
• Pest detection using image processing.
• MQTT-based communication.
• WhatsApp/SMS/email alerts.
• Mobile app dashboard.
• Solar-powered sensor node.
• LoRa-based long-range field communication.

AI agriculture is also becoming more relevant. India’s National Pest Surveillance System supports 66 crops and over 432 pest types, showing how AI and digital tools are being used for agricultural advisories at scale.

Smart Agriculture Viva Questions

1. Why did you choose ESP32 for this project?

ESP32 has built-in Wi-Fi, supports IoT communication, and can read multiple sensors, making it suitable for real-time agriculture monitoring.

2. What is the role of the soil moisture sensor?

It measures the water content in soil and helps the system decide whether irrigation is required.

3. Why is a relay module used?

A relay allows the low-voltage microcontroller to safely control a higher-power water pump.

4. Can this project work without machine learning?

Yes. A rule-based IoT system with threshold-based irrigation is enough for a functional final-year project.

5. How can machine learning be added?

ML can be used for crop recommendation, disease prediction, pest detection, or irrigation prediction.

FAQ

What is a Smart Agriculture System?

A Smart Agriculture System uses IoT sensors, automation, dashboards, and data analysis to monitor field conditions and improve farming decisions.

Is smart agriculture a good final-year project?

Yes. It is practical, socially useful, and technically strong because it combines hardware, software, database, dashboard, and automation.

Which sensors are used in smart agriculture?

Common sensors include soil moisture sensor, DHT11/DHT22, water-level sensor, rain sensor, pH sensor, NPK sensor, and light sensor.

Which is better for this project: Arduino or ESP32?

ESP32 is better for IoT dashboards because it has built-in Wi-Fi. Arduino is easier for beginners but usually needs an extra communication module.

Can I get source code for a smart agriculture system project?

Yes. A complete project should include controller code, backend/API code, dashboard files, database schema, and setup instructions.

What should be included in the project report?

Include abstract, introduction, objectives, existing system, proposed system, architecture, modules, hardware/software requirements, implementation, testing, screenshots, conclusion, and future scope.

Can smart agriculture use Python?

Yes. Python can be used for Flask dashboards, APIs, data analysis, crop prediction, and machine learning modules.

What should I include in a smart agriculture PPT?

Include problem statement, objectives, block diagram, components, modules, working flow, screenshots, testing results, advantages, limitations, future scope, and conclusion.

Conclusion

A Smart Agriculture System is a high-value final-year project because it connects IoT, automation, sensors, databases, dashboards, and optional AI/ML with a real agricultural problem. The best version starts with soil moisture monitoring and automatic irrigation, then adds cloud storage, charts, alerts, report logs, and crop advisory features.

For students who need a ready project, FileMakr can position this article with a clear CTA: Get the Smart Agriculture System project with source code, report, PPT, setup support, and live demo.