Satellite images are images of the Earth that are collected by the imaging satellites which are operated by the government and businesses all around the world. In this article, I’m going to introduce you to a data science tutorial on Satellite Imagery Analysis with Python.
Satellite Imagery Analysis
In this article, I will walk you through a satellite imagery analysis task over the Sundarbans forest in India. The Google map below shows the Sundarbans region. We will perform satellite imagery analysis on this region so you should know what it is before we get started with the task.
The Sundarbans are one of the largest mangrove areas in the delta formed by the confluence of the Ganges, Brahmaputra and Meghna rivers in the Bay of Bengal. The Sundarbans Forest stretches approximately 10,000 km sq across India and Bangladesh, 40% of which is found in India and is home to many rare and globally threatened wildlife.
Satellite Imagery Analysis with Python
In this task, I will be using a very small part of the Sundarbans region for the task of analyzing satellite imagery with Python. I’ll be using a small portion of the Sundarbans satellite data that is acquired using the Sentinel-2 satellite.
The dataset I am using is in the form of 954×298 pixels, with 12 bands with a spectral resolution varying from 10 to 60 meters. Now let’s import the necessary Python libraries and dataset to begin the task of analyzing satellite images with Python:
As I stated in the above section that the dataset contains 12 bands now let’s visualize them to see what we are going to work with:
This dataset has several numbers of bands that contain data ranging from visible to infrared. It is therefore difficult to visualize the data for humans. Creating an RGB composite image facilitates an effective understanding of the data:
Now let’s visualize the histogram of the dataset which will help us to understand the distribution of the values of the bands:
Analyzing the Vegetation Index:
Now as a task of analyzing images I will analyze the vegetation of the Sundarbans region:
When you have negative values it is probably water. On the other hand, if you have an NDVI value close to +1, it may be dense green leaves. But when the NDVI is close to zero, there are no green leaves and it might even be an urbanized area.
You can get all the code used in this data science tutorial on the task of Satellite Imagery Analysis with Python.
I hope you liked this article on the task of Satellite Imagery Analysis with Python. Feel free to ask your valuable questions in the comments section below.