A green AI-revolution for Smart Cities

GeoAI gives an overview over the quality of green areas in cities

Published on: 22/01/2021
Last update: 08/05/2021
News

Green City Watch has since 2018 offered Open Source code and collaboration with cities in order to map their green areas and calulate the quality on three different parametres. This process is based on GeoAI combining methods from GIS, artificial intelligence, and data mining.

 

Green areas in cities have an enormous impact on the citizens’ quality of life. But even Smart and Intelligent Cities might have difficulties implementing green areas in their policies for city development.

This is where Green City Watch’ open source GeoAI technology can help. The technology maps green areas and their quality – not just quantity – on three parameters: Social, Ecology, and Economy. The dashboard makes it possible to turn up and down on these parameters according to a specific need from a city (see a picture of the dashboard)

These three parameters are important to evaluate the quality of parks and other public green areas. Green areas without asphalt or concrete are part of preventing in city floods by absorbing more rainwater while contributing to creating better air quality for the inhabitants. In cities, green areas are used for play and relaxation, which influences our mental health. Finally, parks allow for local cafés and small restaurants which contributes to the local economy.

 

A green AI-revolution

Green City Watch’s mission is: 'To revolutionize the way we value nature, bring transparency to local government, and regenerate our cities.'

Their Open Source code is based on geospatial technology. This is a Machine Learning technology. GeoAI combines methods from GIS, artificial intelligence, and data mining. GeoAI is:

  • Using computer vision for remote sensing, image classification, and object detection,
  • Using super-resolution networks to increase visual clarity and allow higher zoom levels of existing imagery,
  • Using natural language processing to extract geospatial information from unstructured text in documents and images,
  • Applying deep learning to large 3d geospatial datasets, such as point clouds and 3D meshes.

Co-funder Nadina Galle explained their technology like this (in an article from 2019):

We use multispectral imagery, produced by satellite sensors that measure reflected energy within several specific sections (also called bands) of the electromagnetic spectrum.

Green City Watch utilize Maxar’s 30 cm resolution satellite imagary and GBDX Catalog service for automatically filter the best possible image and thereby automatizing their workflow .

 

Sustainable and Smart Cities

The solution by Green City Watch supports Sustainable Development Goal number 11, which aims at creating green public spaces in cities in collaboration with its citizens.

Since 2018 Green City Watch has created a larger portfolio for themselves. They have mapped green areas in Sydney, Amsterdam, Jakata, and 27 other cities worldwide.

 

 

Final take-aways

  • An Open Source geoAI project with a long portefolio is of great value for the city which aim to become a Smart City and/or follow the Sutainable Development Goals.
  • Green City Watch uses geoAI to evaluate the sustainability of a city/area based on three paramatres: Social, Ecology, and Economy.
  • Their open source code is based on geospatial technology. This is a Machine Learning technology. GeoAI combines methods from GIS, artificial intelligence, and data mining.