AgroTech AI platform is a comprehensive web-based tool where users can access various machine learning models for making accurate predictions related to agriculture. It offers solutions for crop management, soil health assessment, pest control, and more.
Make sure you star the repository and show your love to us💗
Contributing in open source increases your opportunities to work with different projects and mentors, getting to know various insights and ideas. It is a platform where contributors grow together with a construvtive and a positive attitude. This repository also provides one such platforms where contributers come over and put their ideas and make our website as interactive as much they can!
| Event Logo | Event Name | Event Description |
|---|---|---|
 |
GirlScript Summer of Code 2024 | GirlScript Summer of Code is a three-month-long Open Source Program conducted every summer by GirlScript Foundation. It is an initiative to bring more beginners to Open-Source Software Development. |
AgroTech AI platform is a comprehensive web-based tool where users can access various machine learning models for making accurate predictions related to agriculture. It offers solutions for crop management, soil health assessment, pest control, and more.
It implements machine learning algorithms to implement 3 basic functionalities:
Aims to predict the appropriate fertilizer based on environmental and soil conditions. The dataset contains various features like temperature, humidity, moisture, soil type, crop type, and the levels of nitrogen, potassium, and phosphorus in the soil. The model aims to recommend the correct fertilizer to use, improving crop yield and soil health.
Fertilizer Prediction.csv (Uploaded under notebooks)
A Random Forest Classifier was chosen as the primary model due to its robustness and high accuracy in classification tasks. The dataset was split into training and testing sets in an 80:20 ratio. Key steps:
Categorical variables (Soil Type, Crop Type, and Fertilizer Name) were encoded using LabelEncoder.
A Random Forest model was trained using the training data.
A grid search with cross-validation was applied to find the optimal parameters for the Random Forest model.
Implements a machine learning-based crop recommendation system using various classification algorithms to predict the best crop for farming based on the soil and environmental conditions. The model takes features such as Nitrogen (N), Phosphorus (P), Potassium (K), temperature, humidity, pH, and rainfall as inputs and predicts the most suitable crop for a particular set of conditions.
Crop_recommendation.csv(Uploaded under notebooks)
Four different models were trained on the dataset to predict the crop: The results of each model are as follows:
- Logistic Regression: 96.18%
- Decision Tree Classifier: 97.82%
- Gaussian Naive Bayes: 99.45%
- Random Forest Classifier: 99.45% The final model selected for deployment is the Random Forest Classifier.
Implements machine learning models to classify soil quality based on various features like nitrogen content, pH levels, organic carbon, and other nutrients. The goal of the model is to predict the quality of soil using logistic regression and a Support Vector Machine (SVM) model.
Soil_Quality.csv (Uploaded under notebooks)
-
Logistic Regression Logistic Regression is used to model the soil quality based on the provided features. The dataset is split into training and testing sets, and the logistic regression model is trained on the training data.
-
Support Vector Machine (SVM) A Support Vector Machine with an RBF (Radial Basis Function) kernel is trained as an alternative model. The SVM model aims to find the decision boundary that best separates different soil quality classes.
-
Performance Evaluation The performance of both models is evaluated using accuracy. The accuracy of each model is calculated by comparing the predicted soil quality labels with the actual labels in the test dataset.
Aims to develop a machine learning-based model for predicting crop yields based on various environmental and agricultural factors. The primary objective of this project is to create a model that predicts the total crop yield for a given region using data such as Area and type of crop, Year of cultivation, Average rainfall (in mm per year), Pesticide usage (in tonnes), Average temperature (in °C)
yield_df.csv (Uploaded under notebooks)
Various machine learning regression algorithms are applied, and the performance is evaluated based on metrics like Mean Squared Error (MSE). The results of the models used are as follows:
-
Linear Regression Mean Squared Error : 80852.08620158922 Score 0.09879301553673503
-
K Neighbors Regressor Mean Squared Error : 55183.1146293406 Score 0.5801883304861266
-
Decision Tree Regressor Mean Squared Error : 13211.190235825037 Score 0.9759383181169221
-
Random Forest Regressor Mean Squared Error : 10135.46523142438 Score 0.9858378410451943
-
Gradient Boosting Regressor Mean Squared Error : 34773.822585474634 Score 0.833295640875001
-
XGB Regressor Mean Squared Error : 13451.947664464684 Score 0.975053338957936Linear Regression Mean Squared Error : 80852.08620158922 Score 0.09879301553673503
The Random Forest Regressor was found to have the lowest MSE, making it the most suitable model for crop yield prediction. This model was selected for deployment and future predictions.
- React
- Tailwind
- python - Flask
- Node
- MongoDB
- Express
- Machine Learning
- Deep Learning
Ready to contribute to this fun project? Here's how to set up your development environment:
Make sure you follow our contributing guidlines:- here
- Fork this repository 🍴 and clone it to your local machine:
git clone https://github.com/manikumarreddyu/AgroTech-AI.git
- Install the required Python packages for Flask backend 🐍:
pip install -r requirements.txt
- Start the Flask server ⚡:
python app.py
- Install the dependencies for React frontend 🧩:
npm install
- Run the development server ⚡:
npm run dev
- Open your browser at
http://localhost:3000to see the project running! 🌟
Please note that this project is released with a Code of Conduct. By participating in this project you agree to abide by its terms.
If you would like to contribute to the project then kindly go through Contributing Guidelines to understand everything from setup to necessary instructions.
This project is licensed under the MIT License. See the LICENSE file for more details.
for this project!