Viewing green space from above
HUGSI stands for Husqvarna Urban Green Space Index — a digital innovation initiative developed by Husqvarna in collaboration with Overstory. The ambition is to help safeguard and improve maintenance of green spaces in urban areas. By applying computer vision and deep learning techniques on satellite images, HUGSI unveils insights about the size, proportion, distribution, and health of green space in urban areas.
How it works
satellite

Satellite data acquisition

Satellite image data is acquired from Copernicus project supported by European Commission and European Space Agency (ESA)

dashes
satellite

Data processing

Computer vision and machine learning techniques are applied to turn satellite image data into a range of urban green space metrics

satellite

Calculating the index

The overall greenness scores are calculated and are used to rank select cities.

Year

Size

Format

2020

8 MB

PDF

2019

3 MB

PDF

The HUGSI Report

In the HUGSI-report we have complied an essence of HUGSI 2021 that you can read and share with others. Included are articles and insights from this edition of the index as well as global and regional green space data. We hope you will enjoy it and get a lot of value out of it.

satellite

Webinars and videos

Watch all HUGSI related videos and webinars on demand. This is where we gather all our video content with an exclusive access available for you as a subscriber to our newsletter. Hopefully you can learn something new and get inspired into making the world a bit greener

Green space matters

Urbanization is happening at an unprecedented pace. Cities are increasingly focused on sustainable development. With proven environmental and recreational value, the development and management of urban green space is becoming a focus area for cities across the globe. It takes political guidance, citizen participation and cross-sector collaboration to turn the vision for urban green space into reality.

That’s why we created HUGSI – to raise the awareness about the value of urban green space among citizens, support city officials and politicians to make data informed decisions and facilitate the collaboration across industries and organizations to together make “smart and sustainable city” a reality.

satellite
Achievement badges

Achievements

New to HUGSI 2020 is that we want to further highlight and acknowledge global and regional achievements based on our KPI’s. All cities that have a top score for any KPI on global or regional level will be awarded with an achievements badge. So take a look at your favorite cities and see if they carry a badge or not.

Frequently Asked Questions

How should I use the index?

We don’t intend to set any restrictions on how the index should be used. You’re welcome to spread the word and be creative in how you use it.

Ideally, we expect to see the index being used to raise awareness of urban green space in various occasions. For example, you might cite HUGSI as a source of reference in a social media post or an in-person discussion with your colleagues.

Potentially you may use the index and KPI data to:

  • Understand the state and development of a city
  • Compare and benchmark cities
  • Be happy about and celebrate good results and high score!
  • Drive for change and development of green space if you are not happy with current scoring.
  • Safeguard the green space in your city by HUGSI monitoring the development for you.
  • Relate our data to other indexes or research on environmental and living conditions of urban areas.

Remember that we focus on urban vegetation and the greenness of urban areas only. We do not measure other important factors such as biodiversity, air quality and such.


The index is based on range of factors such as the percentage of urban area covered by vegetation, health of vegetation, and how well the green space is distributed across the urban area. To provide as accurate results as possible the different parameters have been extracted for different types of vegetation separately. Combining values from different categories requires a standardization process before weighing them together. For each type of vegetation we use its different factors to produce as product distribution which is furthermore transformed into a normal distribution. Using the cumulative distribution function of the normal distribution we obtain a cumulative probability score ranging from 0 to 1. After obtaining the cumulative probability scores for the different types of vegetation they are weighted together and re-scaled into the range 0 to 100 providing the final score.

The multiplicative nature of the computations ensures that cities with high values for multiple factors rank higher than cities with very high value for one factor but low for the others.

The rationale of including vegetation health and distribution is to better reflect the environmental and recreational values of urban green space. We believe evenly distributed green space across urban area is more accessible by citizens and thus higher recreational value than that concentrated at only a few spots. Besides, healthier vegetation has higher environmental value due to more carbon dioxide absorption and higher oxygen emission. The index puts twice the weight on trees compared to grass to recognize the higher impact they have on the environment - see reference below.

Contact us if you're interested in more details about the statistical and analytical methods utilized in HUGSI.


The first round of 98 cities in the initial launch 2020 was selected based on C40 member cities, including temporarily inactive cities with the addition of non C40 members; Gothenburg, Sweden and Marseille, France.

57 new cities were selected for 2020 to fill gaps and white space in Europe, North America and India.

In 2021 cities part of the 'Green City Challenge' in Netherlands were added. To know more, please click here


We’re open to evaluating and updating the list of cities when relevant. If you have an additional city of interest, let us know!

In particular, if you work with city government or municipality and want to request an analysis of your city, get in touch!


To calculate the index we use primarily the Sentinel 2 satellite image dataset. This data is captured by satellites operated by European Space Agency (ESA) and made publicly available by The European Commission's Copernicus programme in collaboration with ESA. Additional satellite image data, such as high-resolution satellite imagery from Airbus and Maxar, are used to complement and validate the results.


Deep learning techniques are utilized to process the satellite image data and extract relevant metrics from the raw images.

As a subset of machine learning, deep learning leverages deep neural networks to effectively learn from unstructured data (such as satellite images) and reveal patterns, characteristics and insights


City boundaries in HUGSI are defined based on OSM Boundaries dataset provided by Open Street Map.

Population data from Global Human Settlement Layer (GHS-POP) is used to adjust the area to analyze within OSM city boundaries. We only take into consideration urban areas where citizens actually reside.

GHS-POP divides a city into grids of 250 by 250 meters and measures average density of population in each grid. Our approach excludes tiles with less than 1000 people per square mile (24 people per 250m by 250m) and includes islands (smaller areas disconnected from the main body of a city) with more than 5000 people residing are included.

Then, we add a 300m buffer around the filtered boundaries to include surrounding areas. This resulting area is regarded as the urban area for a city which is used followed in all further calculations.

This method produce three important output:

  1. Urban area to use in the analysis of a city
  2. Actual area of the city in m² that the analysis cover
  3. Estimated population for the measured area

Read more about OSM Boundaries data: https://osm-boundaries.com/Map

Read more about Global Human Settlement Layer: https://ghsl.jrc.ec.europa.eu/ghs_pop2019.php


HUGSI uses a machine learning model to based on height differentiate trees from other vegetation including bush. The model is trained on visually labeled dataset in which vegetation over 1m height are classified as trees.


The results are produced through our thorough and open methodology

HUGSI focus on globally scalable analytics and can be used to derive current state, development and changes for a city, cities, region and globally. The results are not optimized to produce detailed and highly accurate readings for a particular city.

The results provided are validated by data scientists and domain experts and believed to be very accurate. A thorough approach of testing and validation is employed in data processing with deep learning to ensure deep understanding of the performance and continuous optimization of the algorithms.

Legal disclaimer: All results are assumptions based on our open methodology and the AI-models used.www.hugsi.green/terms-of-use


We’re open to share the metrics for a city or area of your interest upon request. Drop us a message and we’re happy to discuss.


You’re encouraged to get in touch with us and discuss the details and insights of your interest. We’re continuously extracting new insights and will be happy to support you in making use of HUGSI.