NAIP Multiband Remote Sensing Images in Python
This is a small project to calculate the NDVI in Python. For this I used the EarthPy data subset naip-fire-crop. This dataset contains NAIP data for the Cold Springs Fire study area in Colorado. NAIP stands for National Agriculture Imagery Program, they collect aerial imagery during the agricultural growing season in the continental US. NAIP imagery is often taken using only the red, green, and blue bands, but some include the infrared band as well.
Link to the JupyterNotebook: https://github.com/Leonieen/Projects/blob/main/NDVIPython/NDVI.ipynb
With EarthPy the data is imported and then the individual bands can be plotted.
Python
Keywords:
AearthPy
NAIP
JupyterNotebook
Remote Sensing
NDVI
Composites can now be created from the images of the different bands again.
By applying a stretch, contrast and clarity can be improved. To do this, there is also again a function in EarthPy.
To calculate the NDVI I use the EarthPy function normalized_diff from earthpy.spatial.
Calculating NDVI in Python with Landsat 8 Images
NDVI is calculated by comparing the reflectance of visible red and near-infrared light by vegetation. Here is another way the NDVI can be calculated using Python, Rasterio using Landsat-8 imagery. I will use the band 4 (red) and band 5 (NIR) to calculate the NDVI. Finally, the results are visualized using Matplotlib.
Link to the JupyterNotebook: https://github.com/Leonieen/Projects/blob/main/NDVIPython/NDVI_Landsat.ipynb
Python
Keywords:
NDVI
JupyterNotebook
Landsat8
Plotting Band 4 (Red) and Band 5 (NIR)
Plotting Band 5 (NIR) using different colormaps
Plotting Band 4 (Red) and Band 5 (NIR) with colorscale
Calculating NDVI (left) and Comparing NDVI July 2022 and July 2019 (right)