CROP PRIDICATION USING AI with IOT along with varous data
1. JIS College of Engineering
Project Title/IDEA: CROP PREDICTION USING AI
Team Member's Name :
KUMAR SAURAV
UJJWAL KUMAR DUBEY
LUCKY RAJ
AAYUSHMAN GUPTA
ANURAG RAJ
Mentor's Name:
Mayanglambam Aarbindro Singh
2. JIS College of Engineering
Challenges in Agriculture:
1. Unpredictable weather impacting crop planning.
2. Pest outbreaks causing significant crop damage.
3. Inefficient resource utilization, leading to higher costs.
What is the Solution????
Crop Prediction
What is Crop Prediction?
Crop prediction is the process of forecasting the type, yield, or health of crops
using data-driven approaches.
It assists farmers, agricultural experts, and policymakers in making informed
decisions.
3. JIS College of Engineering
Key Objectives
• Data Collection: Use IoT sensors to collect real-time data on soil moisture,
temperature, humidity, and weather conditions.
• AI Model Development: Build a machine learning model to predict the
best crop based on historical and real-time data.
• User Interface: Develop a simple mobile or web-based interface for
farmers to access predictions.
• Field Testing: Test the system in real-world conditions with small-scale
farmers.
• Training: Provide training to farmers on how to use the system effectively.
4. JIS College of Engineering
Target Audience:
- Small and Marginal Farmers
Expected Outcomes
• Improved Crop Yield: Farmers will be able to select the best crop for their soil
and weather conditions, leading to higher yields.
• Cost Savings: Efficient use of resources (water, fertilizers) will reduce costs for
farmers.
• Scalability: The system can be scaled to cover larger areas and more crops in
the future.
• Farmer Empowerment: Small-scale farmers will have access to advanced AI
tools, enabling them to compete with larger agricultural enterprises.
5. JIS College of Engineering
Idea Description :
Core Idea: A cost-effective AI-powered prototype for crop prediction.
What It Solves:
Helps small-scale farmers decide the best crop using real-time data.
The prototype acts as a foundation for scaling up.
Challenges Addressed:
- Cost Barrier: Using low-cost sensors and open-source software.
- Accessibility: SMS-based alerts for farmers without smartphones.
6. JIS College of Engineering
Technical Details
1. IoT Sensors
• Soil Moisture Sensor: Measures the water content in the soil.
• Temperature Sensor: Monitors the ambient temperature.
• Humidity Sensor: Tracks the humidity levels in the air.
• Weather Station: Collects data on rainfall, wind speed, and other weather
parameters.
2. Data Collection
• Data will be collected in real-time from the sensors and stored in a cloud-based
database (e.g., AWS, Google Cloud).
• Historical data on crops, soil types, and weather patterns will also be used to
train the AI model.
7. JIS College of Engineering
Technical Details
3. AI Model Development
• Data Preprocessing: Clean and normalize the data to remove outliers and missing values.
• Model Selection: Use machine learning algorithms such as Random Forest, Support Vector
Machines (SVM), or Neural Networks for crop prediction.
• Model Training: Train the model using historical data and validate it using cross-validation
techniques.
• Real-Time Prediction: The trained model will predict the best crop based on real-time
sensor data.
4. User Interface
• A simple mobile or web-based interface will be developed for farmers to input their location
and receive crop predictions.
• The interface will display the predicted crop, along with recommendations for planting and
resource management.
8. JIS College of Engineering
Technical Details Data Collection
Processing
SUPPORT VECTOR
MACHIINE (SVM)
K-NEAREST NEIGHBORS
DESCISION TREE RANDAM
FOREST ANN NA/VE BAYES
LSTM
TRAINING
FEATURE
EXTRACTION
ML/DL MODULES
TESTING AND
EVALUATION
DECISION(BASED
ON BEST ML
MODEL)
NEW CROP
DATA
PREDICTION AND
NEIGHBOUR
10. JIS College of Engineering
Budget:
Item Cost (INR) Description
IoT Sensors ₹30,000 Soil moisture, temperature, humidity, and weather sensors.
Software Development ₹20,000 AI model development, mobile/web app development, and database setup.
Testing & Field Trials ₹10,000 Field testing in real-world conditions, including travel and logistics.
Training for Farmers ₹5,000 Training sessions for farmers on how to use the system.
Miscellaneous ₹10,000 Contingency funds for unforeseen expenses.
Total ₹75,000
