https://github.com/nirmalyabag20/crop-yield-prediction-using-machine-learning

This project uses machine learning to predict crop yields based on factors like region, crop type, rainfall, temperature, and pesticide use. By analyzing a dataset of over 28,000 records, the models provide accurate yield forecasts, helping optimize farming decisions and resource management, ultimately contributing to sustainable agriculture.
https://github.com/nirmalyabag20/crop-yield-prediction-using-machine-learning

jupyter-notebook matplotlib numpy pandas python scikit-learn seaborn

Last synced: 16 days ago
JSON representation

This project uses machine learning to predict crop yields based on factors like region, crop type, rainfall, temperature, and pesticide use. By analyzing a dataset of over 28,000 records, the models provide accurate yield forecasts, helping optimize farming decisions and resource management, ultimately contributing to sustainable agriculture.

• Host: GitHub
• URL: https://github.com/nirmalyabag20/crop-yield-prediction-using-machine-learning
• Owner: nirmalyabag20
• Created: 2024-09-06T14:34:27.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-09-06T15:00:30.000Z (4 months ago)
• Last Synced: 2024-10-31T12:22:25.110Z (2 months ago)
• Topics: jupyter-notebook, matplotlib, numpy, pandas, python, scikit-learn, seaborn
• Language: Jupyter Notebook
• Homepage:
• Size: 554 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Crop Yield Prediction~

______________________

Project Overview~ 

  This project predicts crop yields based on various factors such as area, crop type, year, average rainfall, pesticide use, and average temperature. Accurate yield predictions can guide agricultural planning, optimize resource management, and support     sustainable farming practices.

Dataset Overview~

  The dataset used contains 28,242 records with the following features:

  1.	Area: The geographical region where crops are grown.

    

  2.	Item: The type of crop (e.g., wheat, rice).

     

  3.	Year: The year of crop yield data.

     

  4.	hg/ha_yield: Crop yield in hectograms per hectare.

     

  5.	Average Rainfall (mm per year): The average annual rainfall in millimeters for the area.

      

  6.	Pesticides (tonnes): The amount of pesticides used per area in tonnes.

      

  7.	Average Temperature (°C): The average annual temperature in the region.

    

Key Features~

  •	Data Analysis: Explored relationships between rainfall, temperature, pesticide usage, and crop yield.

  

  •	Feature Engineering: Created additional variables from the dataset to improve prediction accuracy.

  

  •	Machine Learning Models: Tested algorithms including Linear Regression, Random Forest, and Gradient Boosting.

  

  •	Data Visualization: Visualized the influence of climatic factors and pesticide usage on crop yield.

Results~

  •	Achieved 93% prediction accuracy using the Decision Tree Regressor, which demonstrated the best performance.

  

  •	Notable factors influencing yield: rainfall, temperature, and pesticide use.