Normalized Difference Vegetation Index — You Don’t Always Need Deep Learning for Satellite Imagery

Published
Mar 21, 2021
Rate this post
(6 votes)
Heatmap of NDVI values per district

While looking for an ML solution to understand the relationship between climate change and forced displacement in Somalia, Deep Learning turned out to be non-resource-efficient. Instead, we used satellite imagery indices to understand image bands and the different combinations to get the information and data we needed for our project.

By Vishal R

Deep Learning algorithms are designed to mimic the working of our human brain. We know our brain is a powerful computer. So, an algorithm that mimics such a computer must need a lot of processing power. This is one of the many disadvantages of Deep Learning.

 

A large amount of data

Possibility of overfitting

Overfitting. Source: Wikipedia

Overfitting. Source: Wikipedia

 

Hyperparameter tuning

The Problem We Faced

Normalized Difference Indexes

Satellite Imagery vegetation Index calculation

Satellite Imagery vegetation Index calculation

Satellite Imagery water Index calculation

Satellite Imagery water Index calculation

 

Satellite Imagery built-up Index calculation

Satellite Imagery built-up Index calculation

Heatmap of NDVI values per district - Source: Omdena

Heatmap of NDVI values per district – Source: Omdena

 

I believe community learning programs like this are the way to go for anyone with any level of skill.

More of our work

Explore

Omdena

Building AI Solutions for Real-World Problems

Omdena Projects
Omdena Projects

Develop Your Career and Make a Real-World Impact.

Read more

Omdena Lore
OmdenaLore

The World’s largest AI4Good Python library for real-world projects.

Read more

Omdena School
Omdena School

Real-world data science and machine learning courses.

Read more

NGOs Events

Subscribe to get our Case Studies, Projects, and Real-World AI

  • Subscribe today to receive updates on the latest news!
  • We will send you periodic updates.
  • And many more information: Events, Courses,…
  • We respect your privacy.

JOIN IN

Leave a Comment
1 Comment
  1. Tanya

    We started to study in detail the issue of the normalized water difference index when we were faced with the task of creating efficient software for agriculture. Its main application today is the detection and monitoring of slight changes in the water content of water bodies.
    Using this index gives almost 99% reliable information about the water content of plants. Therefore, it is a very good indicator for determining plant water stress. The Normalized Difference Water Index (NDWI) is a satellite-derived near-infrared (NIR) and short-wave infrared (SWIR) index.

    Reply
Submit a Comment

Your email address will not be published.