KrushiAI: SMART CROP RECOMMENDATION

Discover the perfect crops for your land with our AI-powered recommendation system

Intelligent Crop Recommendation

Our crop recommendation model leverages machine learning to analyze key factors such as soil nutrients, weather conditions, and rainfall to provide informed agricultural decisions. By training multiple models, we've honed the accuracy and precision of our recommendations, ensuring that you receive the best advice for your land.

Explore Optimal Crops

Discover the ideal crops for your land by exploring the average conditions required for each crop. Our model takes into account nitrogen, phosphorus, potassium levels, temperature, humidity, pH, and rainfall to suggest the most suitable crops.

Average Conditions for Crops

Crop Nitrogen Phosphorus Potassium Temperature (°C) Humidity (%) pH Rainfall (mm)

How Crop Recommendation Works

1

Data Input

Begin by entering details about your land, such as soil nutrient levels, weather conditions, and historical rainfall data.

2

Model Analysis

Our machine learning model analyzes the data using sophisticated algorithms to determine the most suitable crops for your land.

3

Recommendation

Receive a list of recommended crops along with detailed information about their optimal growing conditions.

KrushiAI: SMART CROP RECOMMENDATION

Discover the perfect crops for your land with our AI-powered recommendation system

Plant Disease Detection

Our mission is to help in identifying plant diseases efficiently. Upload an image of a plant, and our system will analyze it to detect any signs of diseases. Together, let's protect our crops and ensure a healthier harvest!

How Crop Disease Detection Works

Upload Image

Go to the Disease Recognition page and upload an image of a plant with suspected diseases.

Analysis

Our system will process the image using advanced algorithms to identify potential diseases.

Results

View the results and recommendations for further action.

Why Choose Us?

Accuracy

Our system utilizes state-of-the-art machine learning techniques for accurate disease detection.

User-Friendly

Simple and intuitive interface for seamless user experience.

Fast and Efficient

Receive results in seconds, allowing for quick decision-making.

About the Project

This dataset is recreated using offline augmentation from the original dataset. The original dataset can be found on this GitHub repo .

Dataset Content

train (70295 images)
test (33 images)
validation (17572 images)