TerraInsight: Inclusive Agricultural Planning and Sustainable Land Management

This project aims to leverage geospatial data from satellite imagery to analyze land qualities, and also data from weather reports to predict crop yields. By utilizing machine learning models and geospatial analysis techniques, the project provides insights into crop performance and suggests suitable crops for specific regions based on historical data and current environmental conditions.

Features:

Geospatial Analysis:

Utilizes satellite data to analyze land characteristics, weather patterns, and other factors affecting crop growth.

Crop Yield Prediction:

Uses machine learning models to predict crop yields based on historical data and current environmental conditions.

Crop Recommendation:

Suggests suitable crops for agriculture based on the analysis of geospatial data and predicted crop yields.

Installations:

1.Clone the repository:

https://github.com/salazangar/ICIQ-FECh32Ch.git

2.Install dependancies:

pip install -r installments

Contributors:

• Sidharth Manikandan(@salazangar)
• Sai Krishna(@Saikicj)
• Tejal Daivajna(@tejaldaivajna)

Dataset

use this drive link for the required datasets.

Acknowledmends

• Thanks to USGS for the Sentinel-2 satellite data
• Thanks to WRF for the weather data
• Thanks to USDA for the crop yield data

References

• Geospatial assessment for crop physiological and management improvements with examples using the simple simulation model - Thomas R. Sinclair, Afshin Soltani, Helene Marrou, Michel Ghanem, Vincent Vadez
• OPTIMIZATION OF LAND USE SUITABILITY FOR AGRICULTURE USING INTEGRATED GEOSPATIAL MODEL AND GENETIC ALGORITHMS - S. B. Mansor, S. Pormanafi, A. R. B. Mahmud, and S. Pirasteh