Syndicate content

Nicaragua

What can satellite imagery tell us about secondary cities? (Part 2/2)

Sarah Elizabeth Antos's picture
In the previous blog, we discussed how remote sensing techniques could be used to map and inform policymaking in secondary cities, with a practical application in 10 Central American cities. In this post, we dive deeper into the caveats and considerations when replicating these data and methods in their cities.

Can we rely only on satellite? How accurate are these results?

It is standard practice in classification studies (particularly academic ones) to assess accuracy from behind a computer. Analysts traditionally pick a random selection of points and visually inspect the classified output with the raw imagery. However, these maps are meant to be left in the hands of local governments, and not published in academic journals.

So, it’s important to learn how well the resulting maps reflect the reality on the ground.

Having used the algorithm to classify land cover in 10 secondary cities in Central America, we were determined to learn if the buildings identified by the algorithm were in fact ‘industrial’ or ‘residential’. So the team packed their bags for San Isidro, Costa Rica and Santa Ana, El Salvador.

Upon arrival, each city was divided up into 100x100 meter blocks. Focusing primarily on the built-up environment, roughly 50 of those blocks were picked for validation. The image below shows the city of San Isidro with a 2km buffer circling around its central business district. The black boxes represent the validation sites the team visited.
 
Land Cover validation: A sample of 100m blocks that were picked to visit in San Isidro, Costa Rica. At each site, the semi-automated land cover classification map was compared to what the team observed on the ground using laptops and the Waypoint mobile app (available for Android and iOS).

What can satellite imagery tell us about secondary cities? (Part 1/2)

Sarah Elizabeth Antos's picture

The buzz around satellite imagery over the past few years has grown increasingly loud. Google Earth, drones, and microsatellites have grabbed headlines and slashed price tags. Urban planners are increasingly turning to remotely sensed data to better understand their city.

But just because we now have access to a wealth of high resolution images of a city does not mean we suddenly have insight into how that city functions.

The question remains: How can we efficiently transform big data into valuable products that help urban planners?

In an effort a few years ago to map slums, the World Bank adopted an algorithm to create land cover classification layers in large African cities using very high resolution imagery (50cm). Building on the results and lessons learned, the team saw an opportunity in applying these methods to secondary cities in Latin America & the Caribbean (LAC), where data availability challenges were deep and urbanization pressures large. Several Latin American countries including Argentina, Bolivia, Costa Rica, El Salvador, Guatemala, Honduras, Nicaragua, and Panama were faced with questions about the internal structure of secondary cities and had no data on hand to answer such questions.

A limited budget and a tight timeline pushed the team to assess the possibility of using lower resolution images compared to those that had been used for large African cities. Hence, the team embarked in the project to better understand the spatial layout of secondary cities by purchasing 1.5 meter SPOT6/7 imagery and using a semi-automated classification approach to determine what types of land cover could be successfully detected.

Originally developed by Graesser et al 2012 this approach trains (open source) algorithm to leverage both the spectral and texture elements of an image to identify such things as industrial parks, tightly packed small rooftops, vegetation, bare soil etc.

What do the maps look like? The figure below shows the results of a classification in Chinandega, Nicaragua. On the left hand side is the raw imagery and the resulting land cover map (i.e. classified layer) on the right. The land highlighted by purple shows the commercial and industrial buildings, while neighborhoods composed of smaller, possibly lower quality houses are shown in red, and neighborhoods with slightly larger more organized houses have been colored yellow. Lastly, vegetation is shown as green; bare soil, beige; and roads, gray.

Want to explore our maps? Download our data here. Click here for an interactive land cover map of La Ceiba.

Resilience for the most vulnerable: Managing disasters to better protect the world’s poorest

Stéphane Hallegatte's picture

In his “The People of the Abyss,” novelist Jack London describes in grim detail a devastating storm that rocked London in the early 20th century. Residents suffered terribly—some losing as much as £10,000, a ruinous sum in 1902—but none lost more than the city’s poorest.
 
Natural disasters are devastating to all affected; however, not everyone experiences them the same way. A dollar in losses does not mean to a rich person what it does a poor person, who may live at subsistence level or lack the means to rebound and rebuild after disaster strikes. Be it a drought or flood, the poor are always hit harder than their wealthier counterparts.
 
This disparity was closely examined in the Global Facility for Disaster Reduction and Recovery (GFDRR) report, Unbreakable: Building the Resilience of the Poor in the Face of Natural Disasters. Unbreakable recommended a range of policies to help countries reduce poverty and build resilience, providing cutting-edge analysis on how disaster risk management (DRM) and well-designed development can alleviate poverty and risk in 117 countries. 

Do changes in land use caused by Payments for Environmental Services last?

Stefano Pagiola's picture



Not long after I joined the World Bank, I worked on a team assessing the extent and severity of land degradation in El Salvador. As part of this work, I went to visit the site of a soil conservation project that had been implemented a few years earlier and was considered extremely successful. Indeed, the project’s implementation report was full of numbers on linear kilometers of terraces built, and other indicators of success. Once we reached the project site, however, we looked in vain for any sign of a terrace. The terraces had once been there (there were photographs to prove it), but a few years later they no longer were.

That results may not last once a project ends is a constant concern. The extent to which it is actually a problem is hard to assess, however, as there rarely is any monitoring after a project closes.

Eradicating household air pollution will pay for itself

Ernesto Sanchez-Triana's picture

© Isabelle Schäfer/World Bank

Globally 2.9 million people died from household air pollution in 2015, caused by cooking over foul, smoky fires from solid fuels such as wood, charcoal, coal, animal dung, and agricultural crop residues. Well over 99% of these deaths were in developing countries, making household air pollution one of their leading health risk factors.

Many women across the world spend their days and evenings cooking with these fuels. They know the fumes are sickening, which is why some cook in a separate outhouse or send the children to play while they cook. Sadly, these small actions cannot fully protect the young. As for the women themselves, they suffer incredible morbidity and mortality from household air pollution.

The Central Matter: An artistic analysis of Central America's Nini subculture

Rafael de Hoyos's picture


On her daily walk down the muddy road that connects her home with school, Beatriz would sing a cumbia and dream of becoming a professional dancer. However, she would soon find out that her aspirations were short lived. At the age of 14, Beatriz got pregnant and never went back to school. In the six years following her pregnancy, she struggled with an unstable and low-paid job, cleaning rich houses in Guatemala City. By the age of 20, without minimum skills and a secure job, Beatriz had little control over her life and a murky picture of her future loomed. 

Partnering to measure impacts of private sector projects on job creation

Alvaro Gonzalez's picture
Worker in Ghana
For the poor and vulnerable of the world, jobs are key to ending poverty and driving development. But not all jobs are equally transformational.  
Photo: Jonathan Ernst / World Bank

Jobs are what we earn, what we do, and sometimes even who we are. For the poor and vulnerable of the world, jobs are key to ending poverty and driving development. But not all jobs are equally transformational. Good jobs add value to society, taking into account the benefits they have on the people who hold them, and the potential spillover effects on others. For example, inclusive jobs, such as those that employ women, can change the way families spend money and invest in the education and health of children.  

A Lifetime Approach To Preventing Violence In Latin America

Jorge Familiar's picture
A prevention program against crime and violence in Zacatecoluca, El Salvador, supports sporting activities for the children from this municipality. Photo: Victoria Ojea/World Bank

2016: A unique opportunity to get it right on forests and climate change

Ellysar Baroudy's picture
Moniz Phu Khao Khouay, Vientiane Province
Forest monitoring efforts in Phu Khao Khouay, Vientiane Province, Laos PDR. Photo credit: Hannah McDonald

If ever there was a year to make significant progress on forest conservation and climate change, it was 2016. Coming on the heels of the historic COP21 Paris Agreement, 2016 was a year to demonstrate the commitment the World Bank Group has to support countries as they take forward their nationally determined contributions to address our global climate change challenge. It’s gratifying to look back on 2016 and feel that we contributed to harnessing this momentum and sense of urgency; especially in showing how sustainable land use, including sustainable forest management, is critical to achieving the ambitious targets set out in the Paris Agreement.


Pages