Introduction

eo-learn makes extraction of valuable information from satellite imagery easy.

The availability of open Earth observation (EO) data through the Copernicus and Landsat programs represents an unprecedented resource for many EO applications, ranging from ocean and land use and land cover monitoring, disaster control, emergency services and humanitarian relief. Given the large amount of high spatial resolution data at high revisit frequency, techniques able to automatically extract complex patterns in such spatio-temporal data are needed.

eo-learn is a collection of open source Python packages that have been developed to seamlessly access and process spatio-temporal image sequences acquired by any satellite fleet in a timely and automatic manner. eo-learn is easy to use, it’s design modular, and encourages collaboration – sharing and reusing of specific tasks in a typical EO-value-extraction workflows, such as cloud masking, image co-registration, feature extraction, classification, etc. Everyone is free to use any of the available tasks and is encouraged to improve the, develop new ones and share them with the rest of the community.

eo-learn makes extraction of valuable information from satellite imagery as easy as defining a sequence of operations to be performed on satellite imagery. Image below illustrates a processing chain that maps water in satellite imagery by thresholding the Normalised Difference Water Index in user specified region of interest.

eo-learn library acts as a bridge between Earth observation/Remote sensing field and Python ecosystem for data science and machine learning. The library is written in Python and uses NumPy arrays to store and handle remote sensing data. Its aim is to make entry easier for non-experts to the field of remote sensing on one hand and bring the state-of-the-art tools for computer vision, machine learning, and deep learning existing in Python ecosystem to remote sensing experts.

Package Overview

eo-learn package is structured into several modules according to different functionalities. Some modules contain extensions under the extra subfolder. Those modules typically require additional package dependencies which don’t get installed by default, since they are usually very specific to the task.

The modules are:

• core - The main module which implements basic building blocks (EOPatch, EOTask and EOWorkflow) and commonly used functionalities.

• coregistration - Tasks which deal with image co-registration.

• features - A collection of utilities for extracting data properties and feature manipulation.

• geometry - Geometry-related tasks used for transformation and conversion between vector and raster data.

• io - Input/output tasks that deal with obtaining data from Sentinel Hub services or saving and loading data locally.

• mask - Tasks used for masking of data and calculation of cloud/snow/other masks.

• ml-tools - Various tools that can be used before or after the machine learning process.

• visualization - Visualization tools for the core elements of eo-learn.

More Examples

Examples and introductions to the package can be found here. A larger collection of examples is available at the eo-learn-examples repository. While the examples there are not always up-to-date they can be a great source of ideas.

In the past, eo-learn served as a collection of many useful tasks, originating from various contributors or projects. In order to keep eo-learn light and easy to maintain, we have decided to move these specific tasks to eo-learn-examples/extra-tasks, .

Contributions

The list of all eo-learn contributors are listed in the credits file. If you would like to contribute to eo-learn, please check our contribution guidelines.

Blog posts and papers

• Introducing eo-learn (by Devis Peressutti)

• Land Cover Classification with eo-learn: Part 1 - Mastering Satellite Image Data in an Open-Source Python Environment (by Matic Lubej)

• Land Cover Classification with eo-learn: Part 2 - Going from Data to Predictions in the Comfort of Your Laptop (by Matic Lubej)

• Land Cover Classification with eo-learn: Part 3 - Pushing Beyond the Point of “Good Enough” (by Matic Lubej)

• Innovations in satellite measurements for development

• Use eo-learn with AWS SageMaker (by Drew Bollinger)

• Spatio-Temporal Deep Learning: An Application to Land Cover Classification (by Anze Zupanc)

• Tree Cover Prediction with Deep Learning (by Daniel Moraite)

• NoRSC19 Workshop on eo-learn

• Tracking a rapidly changing planet (by Development Seed)

• Land Cover Monitoring System (by Jovan Visnjic and Matej Aleksandrov)

• eo-learn Webinar (by Anze Zupanc)

• Cloud Masks at Your Service

• ML examples for Common Agriculture Policy

  • High-Level Concept

  • Data Handling

  • Outlier detection

  • Identifying built-up areas

  • Similarity Score

  • Bare Soil Marker

  • Mowing Marker

  • Pixel-level Mowing Marker

  • Crop Type Marker

  • Homogeneity Marker

  • Parcel Boundary Detection

  • Land Cover Classification (still to come)

  • Minimum Agriculture Activity (still to come)

  • Combining the Markers into Decisions

  • The Challenge of Small Parcels

  • Traffic Light System

  • Expert Judgement Application

• Scale-up your eo-learn workflow using Batch Processing API (by Maxim Lamare)

Questions and Issues

Feel free to ask questions about the package and its use cases at Sentinel Hub forum or raise an issue on GitHub.

You are welcome to send your feedback to the package authors, EO Research team, through any of Sentinel Hub communication channel.

License

See LICENSE.

Acknowledgements

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreements No. 776115 and No. 101004112.