Computational Social Science from Space
Topic: The IC2S2 community studies how online social media and web data can be used to understand different aspects of society and human behavior. While these online data sources are valuable for sensing and quantifying the ‘social fabric’, they are not made for sensing the physical world. This tutorial will provide attendees with another data source with which to complement their analysis: satellite imagery. As the Earth Observation (EO) community is turning to use social media data, we aim to encourage a reciprocal interdisciplinary approach, too. At the same time, satellite-based remote sensing creates new needs for setting community standards around the responsible use of such data, something the IC2S2 community is well-positioned to contribute to. In this tutorial, we will give a short overview of existing work in the social sciences that uses EO to study social phenomena, encouraging discussion from the audience. Additionally, we will offer a hands-on introduction to using Google Earth Engine to demonstrate the effects of redlining, the practice of racially segregated housing policies, visible from space and still impacting communities today.
Agenda:
Date: July 17, 2023
1.30pm - 3pm: Part I, give a high-level overview of what type of satellite imagery is (mostly openly) available. This will then lead to a showcase of case studies which already use satellite imagery to study human behavior and interaction. The emphasis of this part is on showing ‘what is possible’. There will also be a short networking element towards the end to help connect participants, and initiate idea building.
3.30pm - 5pm: Part II, walk through a number of notebooks hosted on Google Colab using the Earth Engine (GEE) Python API, to show the ‘how to do it’ element. We will demonstrate the use of various pre-existing datasets on GEE, such as NDVI/NDWI indicies, pollution and temperature data, as well as raw satellite data and how to extract from them certain indicies (e.g., NDVI indices from Sentinel-2 images).
Resources:
Some of the hands-on elements will be using Google Earth Engine, Google Colab and Google Drive. Signing up (for free) for these services will be required to follow along. We will share a Google Drive folder with the participants before the start, with preliminary project structure including Colab notebooks, and redlining data.
N.B. To ensure a seamless experience in our tutorial, please make sure to register at Google Earth Engine beforehand. Here is how:
1) Visit https://signup.earthengine.google.com/
2) Sign-up with your Google account
3) After signing up, please note that it might take between 1-2 days to get the approval.
To avoid any delays and ensure your readiness, we recommend completing this step promptly. Enjoy exploring with us!
TUTORIAL MATERIALS
Practical Tutorial Project (download me and place into your Google Drive)
Instructors:
Sanja Šćepanović (Nokia Bell Labs)
Sanja Šćepanović is a research scientist at the AI Lab of Nokia Bell Labs in Cambridge, UK, and a Beyond Fellow at AI4EO Lab at TUM/DLR, Munich, Germany. She researches health and well-being at the intersection of Computational Social Science and Earth Observation. Personal website, Google Scholar, LinkedIn, Twitter.
Ingmar Weber (Saarland University)
Ingmar is an Alexander von Humboldt Professor and Chair for Societal Computing at Saarland University. His interdisciplinary research looks at how digital data and computational methods can be applied to address research questions from demography, the development sector, or from other domains. Personal website, Google Scholar, LinkedIn, Twitter.
Acknowledgements:
We thank Zainab Akhtar at the Qatar Computing Research Institute for providing pointers and general information on the use of Google Earth Engine for the collection and analysis of satellite imagery.