Exploring Urban and Natural Dynamics with k-Means Clustering
Explore the docs »
Satellite Data
·
Installation
·
Contact
Table of Contents
The following repository describes a artificial intelligence project with the objective of urban exploration and natural dynamics with k-Means Clustering, developed by students of the Polytechnic University in Madrid (UPM) as part of the course 'Artificial Intelligence'. In this repo it can be found the libraries, results and a collection of the reports produced during the development of this project.
List of major frameworks/libraries used for this project.
In this repo we study how clustering behaves in different urban scenarios from Europe and US. For this urban clustering study we have used Geemap and Google Colab.
New York
Madrid
For the natural dynamics we have focus in Sau and Susqueda reservoirs placed in the northern of Spain (near Girona).
With the help of Sentinel Hub we have obtained a suficient data consisting in four gifs with 50 images each one for the year between 2020 and 2024.
This is the one for 2020:
Some results for the clustering offer different performance depending on the images as shown below. (1) clusters properly the total water area while (2) is not.
The results obtained for the image clustering analysis could be shown in the following figures.
Distributed under the MIT License. See LICENSE.txt for more information.
Jorge Guijarro Tolon - JTlotus - [email protected]
Josep Mª Barberá Civera - jbarciv - [email protected]
Here we list resources we find helpful and would like to give credit to.