For example, a Cairo-based startup called “Swvl” is disrupting commuting in the In the Middle East and North Africa region by mapping out commuters’ travel directions and enabling app-based, affordable bus rides that can compete with on-demand ride-hailing.
Information and Communication Technologies
Machine learning algorithms are excellent at answering “yes” or “no” questions. For example, they can scan huge datasets and correctly tell us: Does this credit card transaction look fraudulent? Is there a cat in this photo?
But it’s not only the simple questions – they can also tackle nuanced and complex questions.
Today, machine learning algorithms can detect over 100 types of cancerous tumors more reliably than a trained human eye. Given this impressive accuracy, we started to wonder: what could machine learning tell us about where people live? In cities that are expanding at breathtaking rates and are at risk from natural disasters, could it warn us that a family’s wall might collapse during an earthquake or rooftop blow away during a hurricane?
More than 1,000 years.
That’s how long recent estimates suggest it would take in some developing countries to legally register all land – due to the limited number of land surveyors in country and the use of outdated, cumbersome, costly, and overly regulated surveying and registration procedures.
But I am convinced that the target of registering all land can be achieved – faster and cheaper. This is an urgent need in Africa where less than 10% of all land is surveyed and registered, as this impacts securing land tenure rights for both women and men – a move that can have a greater effect on household income, food security, and equity.
Perhaps one of our answers can be found in rural Tanzania where I recently witnessed the use of a mobile surveying and registration application. In several villages, USAID and the government of Tanzania are piloting the use of the Mobile Application to Secure Tenure (MAST), one of several (open-source) applications available on the market. DFID, SIDA, and DANIDA are supporting a similar project.
There is a unique space where you can encounter everyone from developers of self-driving cars in Silicon Valley to city planners in Niamey to humanitarian workers in Kathmandu Valley: the global OpenStreetMap (OSM) community. It comprises a geographically and experientially diverse network of people who contribute to OSM, a free and editable map of the world that is often called the “Wikipedia of maps.”
What is perhaps most special about this community is its level playing field. Anyone passionate about collaborative mapping can have a voice from anywhere in the world. In the past few years, there has been a meteoric rise of locally organized mapping communities in developing countries working to improve the map in service of sustainable development activities.
The next opportunity to see the OSM community in action will be the November 14th mapathon hosted by the Global Facility for Disaster Reduction and Recovery (GFDRR)’s Open Data for Resilience Initiative (OpenDRI). Mapathons bring together volunteers to improve the maps of some of the world’s most vulnerable areas, not only easing the way for emergency responders when disaster strikes, but also helping cities and communities plan and build more resiliently for the future.
When Dara Dotz, an industrial designer, travelled to Haiti after the devastating earthquake in 2010, she saw firsthand the supply chain challenges people were facing that had life threatening consequences – most vividly, a nurse having to use her medical gloves to tie off the umbilical cords of newborn babies, because she didn’t have access to an umbilical clamp. Deploying a 3D printer, Dara was able to design a locally manufactured, inexpensive plastic clamp that could be used in the local hospitals for newborns.
From there, Dara co-founded Field Ready, an NGO that is part of the “maker movement,” which pilots new technologies to rapidly manufacture components of essential supplies in the field. Using 3D printing and a range of software, Field Ready works with volunteers to make lifesaving medical components like IV bag hooks, oxygen splitters, and umbilical cord clamps, an approach that has often proven to be both quicker and cheaper than waiting for shipments to arrive.
This is one example of local innovation and design in disaster situations. Communities and governments need to think creatively and find new ways to build resilience, and some of the latest developments in science and technology can provide promising solutions.
Over the past few decades, there has been an exponential increase in the amount of information and data that is open and available – whether from satellites and drones collecting data from above, or from crowdsourced information and social media from citizens on the ground. When analyzed holistically, this data can provide valuable insight for understanding the risks and establishing a common operating picture.
Natural disasters made 2017 a very expensive year.
At $330 billion, last year’s global losses from disasters set a record. These economic losses were primarily a result of meteorological events, such as floods and hurricanes, which are increasing in frequency and intensity due to climate change. An increasing number of people are also exposed to tectonic risks, such as earthquakes and landslides, due to rapid urbanization.
But growing disaster losses aren’t inevitable. Policy changes, education, and good disaster risk management practices have been proven to reduce losses – and the foundation of all of them is accurate, reliable information about disaster risks.
called Understanding Risk (UR), which is supported by the Global Facility for Disaster Reduction and Recovery (GFDRR).
This year, the community will convene at the Understanding Risk Forum 2018 May 14–18 in Mexico City. The Forum will highlight best practices, facilitate nontraditional partnerships, and showcase the latest technical knowledge in disaster risk identification.
It’s a critical time for a discussion of disaster risk information. A new GFDRR report, Aftershocks: Remodeling the Past for a Resilient Future, concludes that Aftershocks, which will be discussed at UR2018, explores what we can learn from historic disasters to anticipate similar future events and build resilience ahead of time.
The good news is that the past few years have seen a surge of new ways to get more accurate, more detailed information more quickly, more easily, and in more difficult contexts. We can now use social media to gather increasingly valuable information in the immediate aftermath of an event. Drones are increasingly capturing high-quality images, and machine learning for image recognition is already helping us produce more and better risk data all the time.
These emerging technologies, including artificial intelligence and machine learning, will be one of the major themes of this year’s UR Forum. To find out more about the UR Forum, and how you can get involved, watch the video blog and visit understandrisk.org.
And don’t forget to keep up with all the great ideas coming out of #UR2018 by following along on Twitter: @UnderstandRisk, @GFDRR, and @WBG_Cities.
Imagine you were working in development and poverty reduction in the early 1990s (I was!). Only one website existed in all the world in August 1991 (today there are over 1.5 billion). Mobile phones were expensive, rare, and clunky. Very few would anticipate a situation in which India would have more mobile phones than toilets.
To paraphrase Bill Gates: we tend to overestimate the changes that will happen in the short term and underestimate those in the long term.
[Put together the puzzle pieces to reveal the picture. Scroll down to #9 for hints.]
Hurricanes Harvey, Irma, and Maria that pounded coastal United States and the Caribbean; the severe drought that struck Somalia; forest fires that are ravaging through southern California… Hard to miss were the natural disasters that displaced – even killed – individuals and families.
There were also the “manmade” disasters – conflicts that erupted or lasted in many parts of the world continued to force men, women, and children out of their homes and homelands.
Yet, turning to the bright side,
Just a couple of weeks ago, for example, global and local leaders gathered at the One Planet Summit in Paris to firm up their commitment – and ramp up action – to maximize climate finance for a low-carbon, disaster-resilient future.
At the World Bank, our teams working on social development, urban development, disaster risk management, and land issues have endeavored with countries and cities worldwide throughout the year to achieve a common goal: building inclusive, resilient, and sustainable cities and communities for all.
How did they do? From our “Sustainable Communities” newsletter,
#1: Africa’s Cities: Opening Doors to the World
Released in February 2017, our report on cities in Africa notes that, to grow economically as they are growing in size, Africa’s cities must open their doors and connect to the world. Improving conditions for people and businesses in African cities is the key to accelerating economic growth, adding jobs, and improving city competitiveness. Two more reports released in 2017 also shined a light on inclusive urban growth in East Asia and the Pacific and in Europe and Central Asia respectively.
- natural disasters
- Sustainable Communities
- disaster risk management
- Migration and Remittances
- Labor and Social Protection
- Information and Communication Technologies
- Climate Change
- Urban Development
- Social Development
- The World Region
- East Asia and Pacific
Global positioning systems (GPS), real time traffic maps, accurate weather forecasts, Uber, self-driving cars…
“Geospatial,” or location-based data has existed for hundreds of years – for example, in street and topographical maps. What’s different is how quickly new information is being gathered and the more sophisticated analytics that is being applied to it, thanks to technological advances.
What was once information only found in the domain of government, military, and select private sector, even up to the 1980s and 90s, has come into broad use over the last 20 years.
This summer, some tens of millions of people in the U.S. traveled to see the total solar eclipse, including a co-author of this blog. Not only was the eclipse amazing – but the drive back from Tennessee to Washington, D.C. showed the integration and impact of geospatial information in our daily lives.
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:
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.