In Mexico, approximately 25 percent of the urban population live in informal settlements with varying degrees of depravity. Although this has allowed for the upward mobility of inhabitants, the rapid rise in population and informal neighbourhoods is deepening inequality, raising pollution levels and creating some of the largest slums in the world. 

A group of scientists from Mexico have been working together on a large-scale high-resolution detection of vulnerable settlements to help fight poverty and inequity. The project is one of the 32 selected as part of the GEO - Google Earth Engine Program that provides funding to tackle environmental and social challenges using open Earth data.

We spoke with Project Lead, Elio Atenogenes Villaseñor Garcia from the National Institute of Statistics and Geography, and Joaquin Salas, from the National Polytechnic Institute, to learn more about the project and how their team is using GEE to track the growth of vulnerable settlements in Mexico and help design better policies to mitigate inequality. 

What is the challenge that you are tackling?

A critical step in combating poverty is identifying, assessing and tracking the sprawl of affected communities. Traditionally, practitioners have evaluated vulnerability and poverty using nationwide census exercises or ground interviews of samples at random. This burdensome process requires field visits by trained personnel.

Due to their enormous cost, government agencies conduct censuses only sporadically (e.g. every ten years in Mexico). The lack of continuous measurement makes it difficult to track social policies' short-term effects against poverty and inequity. We hope to combat the same issue in a high frequency, low-cost way using EO technology.

How will your project address this challenge? 

In this project, we propose implementing a nationwide system with a purpose to locate vulnerable community sprawls and assess poverty status between census years, using high-resolution, multispectral satellite imagery. We will develop the capabilities to track the differences in gap years and estimate people's wealth status in new and modified settlements.

Crucially, we will supplement our estimates with ground truth data obtained with local surveys. This result will enable us to assess our algorithms' performance and provide relevant feedback to the inference mechanisms. 

This approach will allow for the quick assessment of the degree of vulnerability of new or changing community sprawls, providing quantitative information that interested agencies could use to evaluate the effect of governmental policies and socio-economic factors. Moreover, an updated estimation of a vulnerability index could support decision-making during natural disasters, health crises, climate breaking points, and environmental contingencies. 

How will this impact the global community?

The outcome of this project will be a system with the ability to track vulnerable communities during census gap years, based on deep learning and employing a blend of multispectral and multisensorial satellite imagery and ground surveys.

The reliable, up-to-date and cost-effective information generated by our algorithms will allow policy and decision makers to have more confidence in their decisions and actions. 

Furthermore, thanks to the high frequency capture and data availability that Earth Observation technology provides, policy makers will be able to evaluate the results of their actions faster than previously possible. 

How does GEE help you achieve your project-related goals?

Google Earth Engine's resources have proven to be a valuable asset for our project. We have taken advantage of cloud computing, development resources and satellite datasets. As we scale up our implementation to include all of Mexico, we are taking advantage of GEE apps infrastructure to show our results. 

We have processed more than 2 million of Landsat's image patches. Each of them has been classified according to its vulnerability. Thanks to GEE’s power when it comes to displaying information, we can show the vulnerability distribution at a nationwide scale, while also zooming in and observing it at a residential block level. 

How will the GEO-GEE funding help your project?

Thanks to the GEO-GEE funding, our team has full access to the developmental resources which are essential for building a nationwide application. But these resources are not always enough; the GEO-GEE funding provides our team with valuable technical support and training. 

This support enables us to adopt the technology we need to make this project a success.

Thanks to GEO-GEE funding and training, we now have a team capable of developing and implementing advanced geospatial analytical methods that utilise world leading technology, ensuring we can have maximum social impact.

What does success look like to you?

Success for us is the results obtained by our methodology being used by policy makers. These results should serve to design better policies that help mitigate inequality. Moreover, our analysis will have hopefully improved quantitative models to estimate sociodemographic variables relevant for decision making. 

EO Data Science’s role in the GEO-GEE Program

EO Data Science partnered with Google Earth Engine and the Group on Earth Observations to launch the GEO-GEE Program, which supports GEO member countries to operationalise their science as they strive to tackle the world’s biggest sustainable development challenges. 

In July 2020, 32 projects across 22 countries were selected into the program which offers $3 million USD towards product licenses and $1 million USD in technical support from EO Data Science. This funding and support will help these projects tackle global challenges using open Earth data. Read the announcement and list of winners here

Follow us on TwitterLinkedIn or Facebook to hear about more GEO-GEE winning projects!

Subscribe to the GEO-GEE program newsletter

Keep up-to-date with the latest GEO-GEE program project winners blogs.

 

About the author: Amy Boyes

Amy is the Marketing Assistant at the NGIS Group.

Back To News Stories