From Above

Welcome to Team From Above's repository of work done during the JournalismAI 2021 Collab Challenge in the Americas 🌎.

Background

For this year's challenge, participants from various newsrooms across the Americas came together to work with the Knight Lab team at Northwestern University exploring how we might use AI technologies to innovate newsgathering and investigative reporting techniques.

Team members

• Gibran Mena (DataCritica)
• Shreya Vaidyanathan (Bloomberg News)
• David Ingold (Bloomberg News)
• Flor Coehlo (LaNacion)
• María Teresa Ronderos (CLIP)

Our Goal

• A picture can say a thousand words and we are keen to explore using satellite images for storytelling. It's a tool that is unique, complex but out of the reach for many journalists and our team is motivated to explore the usage of Satellite Imagery and applied AI as a tool for reporting. Our primary focus has been to look at the climate crisis through this lens to see what can be reported through the observation of our planet via satellite imagery. We’ve focused on the investigative story idea of detecting deforestation and illegal cattle ranching in the protected forests of four South American countries (Mexico, Colombia, Brazil & Argentina).

• Our goal is to produce a comprehensive and approachable “Guide for satellite image based investigation with AI” that details the various components, technical requirements, difficulties and showcases the potential for future reporting. In conjunction, we will also share takeaways and learnings from our approach for using this technique for the investigation of detecting illegal cattle ranching in Mexico, Colombia, Brazil and Argentina.

Contents

The repository contains material that we have collected.

Notebooks:

1. Satellite data processing
2. Satellite and label data merging
3. Training and evaluation data splitting
4. Model training
5. Model evaluation