1
2
3
4
5
6
7
8
9
10
11
12
13
14
|
---
id: ml
title: Machine Learning
sidebar_label: Machine Learning
slug: /highlights/ml
---
H3 is well suited to applying machine learning to geospatial data. Techniques from computer vision, such as [convolution](https://medium.com/@RaghavPrabhu/understanding-of-convolutional-neural-network-cnn-deep-learning-99760835f148#:~:text=Convolution%20is%20the%20first%20layer,and%20a%20filter%20or%20kernel), can be applied to the pixel grid defined by H3.
H3 has functions for finding neighbors (`kRing`) for use in performing convolution, and functions for transforming indexes to a two dimensional IJ coordinate space on which other computer vision algorithms can be run.
## Links
* Jupyter notebook example: [Uber H3 API examples on Urban Analytics in the city of Toulouse (France)](https://github.com/uber/h3-py-notebooks/blob/master/notebooks/urban_analytics.ipynb)
|
