Introduction

A repository containing the code for prediction of yield for 45 potato farms in Saudi Arabia using Normalized Difference Vegetation Index (NDVI) values gathered from the Sentinel - 2 satellite imagery data. The Sentinel - 2 imagery data was taken from Google Earth Engine.

Process

1. After getting the coordinates and the yield data from the research paper mentioned below, the coordinates were cleaned and converted to a DMS format using basic Excel techniques.

2. Next, the coordinates were imported to a QGIS to create shape files.

3. The shape files were then uploaded to the Google Earth Engine code editor, and NDVI values for the date range of '2016-02-02' to '2016-02-28'.

4. Finally a regression model with an R-Squared score of 0.07 was created using Data Analysis Toolpak.

Further Process

1. The analysis and modelling doesn't end here. More rigorous modelling techniques will be implemented in Python to improve the Yield prediction.

2. More variables such as the precipitation and temperature will be soon added to the model for more accurate predictions.

Citations

This analysis has been performed on the data collected in this research paper: Al-Gaadi, K. A., Hassaballa, A. A., Tola, E., Kayad, A. G., Madugundu, R., Alblewi, B., & Assiri, F. (2016). Prediction of Potato Crop Yield Using Precision Agriculture Techniques. PLOS ONE, 11(9), e0162219. https://doi.org/10.1371/journal.pone.0162219