Giant 3D map shows almost every building in the world

Dec 12, 2025

A giant 3D map shows almost every building in the world

A database of 2.75 billion buildings could help scientists to monitor urban planning, climate change, disaster risks and even corruption.

By Mohana Basu, in Nature

An aerial building model of structures in Singapore with heights highlighted in different shades of blue. — Three-dimensional maps, such as this one of a district in Singapore, could help researchers to keep track of urban planning, disaster risk assessment and climate change.Credit: Zhu *et al./ESSD*

Scientists have produced the most detailed 3D map of almost all buildings in the world. The map, called GlobalBuildingAtlas, combines satellite imagery and machine learning to generate 3D models for 97% of buildings on Earth.

The data set, published in the open-access journal Earth System Science Data on 1 December¹, covers 2.75 billion buildings, each mapped with footprints and heights at a spatial resolution of 3 metres by 3 metres.

The 3D map opens new possibilities for disaster risk assessment, climate modelling and urban planning, according to study co-author Xiaoxiang Zhu, an Earth observation data scientist at the Technical University of Munich in Germany. It could also help to improve how researchers monitor United Nations (UN) Sustainable Development Goals for cities and communities, Zhu adds.

Billions of buildings

Conventionally, creating detailed 3D maps at a global scale has been difficult, say Zhu, because it usually requires either laser scanning or high‑resolution stereo imagery. The team’s solution was to combine deep learning with laser-scanning techniques to predict building heights. The tool was trained on reference data obtained using light detection and ranging (LiDAR) from 168 cities, mostly in Europe, North America and Oceania.

The researchers created the 3D maps from approximately 800,000 satellite scenes captured in 2019, using the deep-learning tool to predict building heights, volumes and areas.

The study found that Asia accounts for nearly half of all mapped buildings in the world — approximately 1.22 billion structures. Asia also dominates the total building volume at 1.27 trillion cubic metres, reflecting rapid urbanization and dense metropolitan clusters in China, India and southeast Asia.

Africa has the second largest number of buildings, at 540 million, but their combined volume is only 117 billion cubic metres, underscoring the prevalence of small, low-rise structures.

City-scale analyses illustrate how building volume correlates with population density and economic development. In Europe, Finland has six times more building volume per capita than does Greece. The study also highlighted that Niger’s per-capita building volume is 27 times below the world average.

These patterns suggest that conventional 2D measures of urban growth, such as built-up areas, might obscure crucial differences between infrastructure and living conditions.

An aerial model of structures in Changsha, China, overlayed on a map of the city. Heights of buildings are highlighted in different shades of blue. — An aerial model of structures in the Chinese city of Changsha.Credit: Zhu *et al./ESSD*, (Basemap ©CARTO and ©OpenStreetMap contributors)

Disaster risk assessment

Dorina Pojani, an urban planning researcher at the University of Queensland in Brisbane, Australia, says that the data set would be extremely valuable for her research, because she has previously relied on static, 2D data.

“Since this can be regularly updated it will be very valuable over the next five to ten years, as the data set will reveal how urban areas develop over time,” Pojani says.

She says that the data set presents fresh opportunities to study corruption, allowing researchers to “link buildings or projects to specific developers, firms or politically connected actors, and ask whether certain networks of people are disproportionately represented in high-value or strategically located projects”.

Pojani says her previous research has linked informal settlements with election outcomes². Political parties often ignore “such settlements when there is an election coming up”, she adds. With a more dynamic data set, Pojani says her work could involve more high-quality evidence.

Liton Kamruzzaman, a transport and urban planner at Monash University in Melbourne, Australia, says that the data set has a lot of potential to help track urbanization around the world.

“There are many parts in the world that do not have any information about how their cities and buildings are growing. This data set is great for everyone irrespective of where they are living,” he adds.

doi: https://doi.org/10.1038/d41586-025-04036-x

References

Zhu, X. X., Chen, S., Zhang, F., Shi, Y. & Wang, Y. Earth Syst. Sci. Data, 17, 6647–6668 (2025).

Article Google Scholar
Merkaj, E., Imami, D., Pojani, D. & Lami, E. Polit. Geogr. 113, 103155 (2024).

Why global environmental negotiations keep failing

Dec 12, 2025

Why global environmental negotiations keep failing – and what we can do about it

President Andre Correa do Lago during closing plenary meeting of the 30th UN climate summit (Cop30).
Photo by Ueslei Marcelino/Cop30, CC BY-NC-ND

Catalina Turcu, UCL

In the past year alone, four major environmental negotiations have collapsed.

Global talks on a treaty to cut plastic pollution fell apart. Governments did not agree on the timeline and scope for the seventh assessment report of the Intergovernmental Panel on Climate Change (IPCC). Talks on the International Maritime Organization’s net-zero framework failed to reach consensus. And the summary for policymakers for the UN Environment Programme’s flagship report on the state of the environment was not approved.

These failures signal a deeper breakdown in how the world tackles environmental crises such as climate change, biodiversity loss, pollution and waste and land degradation.

There are cracks in the system. International negotiations are built on principles of representation and consensus, meant to ensure fairness and inclusivity. In theory, every country has a voice, and decisions reflect collective agreement. In practice, however, these principles often paralyse or delay progress.

Consensus can allow a few countries to block collective action, even when most members are in favour, while calls for representation are sometimes used to delay decisions in the name of democracy – ironically, sometimes by states where democratic principles are in question.

Take the global plastics treaty negotiations. Talks have hit a deadlock between countries seeking limits on plastic production and oil-producing countries pushing to focus only on waste and recycling. Similarly, the IPCC process is grappling with unprecedented disputes over timelines and plans for removing carbon from oceans and rivers.

Then there’s the politicisation of science. Every paragraph of a policy summary – distilling key scientific findings for governments – is negotiated line by line. This process often dilutes or deletes science to fit national agendas, with the recent UN climate summit (Cop30) declaration removing any mention of fossil fuels. The result: assessments that take years to produce and summaries mired in political wrangling, eroding trust in science, and delaying the urgent action they are meant to drive.

Who really decides? Formally, it is the member states – that’s nations and entities like the EU. On paper, every country has an equal voice. In reality, power dynamics tell a different story.

Some nations dominate the floor with large, well-prepared teams, armed with technical experts and seasoned negotiators. They arrive with detailed positions, ready to shape the agenda. Others, often from smaller or less-well-resourced states, struggle to be heard. Their delegations are thin, sometimes just one or two people juggling multiple sessions.

Gender gaps persist, too. Despite decades of commitments to equality, men still speak far more often than women in many negotiations – up to four times more in some sessions of the recently collapsed Global Environment Outlook, the UN’s flagship report on the state of the global environment that connects climate change, nature loss and pollution to unsustainable consumption.

Negotiations to agree on possible ways to tackle the issues fell apart when some governments failed to agree with scientific conclusions outlined in the report. This is not just about optics, and it affects whose perspectives shape global environmental policy. When voices are missing, so are ideas and priorities.

Scientists, meanwhile, sit at the back of the room. Their role is largely reactive – allowed to clarify technical points only when specifically asked by member states. Their expertise, which should anchor decisions in evidence, is often sidelined by political bargaining. The result? Policies that sometimes drift away from what science says is necessary to protect ecosystems and communities.

The new fault lines

Rising nationalism and geopolitical tensions make cooperation harder. Environmental action is increasingly framed as a sovereignty issue, with domestic interests trumping global solutions. Climate pledges are weighed against economic competitiveness, biodiversity targets through trade-offs and resource control. Trust erodes, negotiations drag on, and the planet pays the price.

This reality shows in the slow progress of major agreements. Multilateralism, once the only path forward, now splinters into shifting blocs. Some countries stall decisions to protect short-term gains; others walk away entirely, creating a void – and an opportunity for others to step in.

Improving this means rethinking the system from the ground up. That involves challenging the consensus stranglehold. The requirement for consensus often paralyses negotiations. Allowing coalitions of ambitious countries to move ahead when consensus fails could break deadlocks and create momentum. So-called “coalitions of the willing” (such as the fossil fuel phase-out coalition announced at Cop30) can set higher standards and inspire others to follow.

Giving science a stronger voice, while allowing political input, ensures that decisions remain grounded in facts without ignoring legitimate national concerns.
Current models treat scientific input as secondary to political negotiation. Hybrid approval systems can protect evidence without ignoring legitimate national concerns.

Modernising the process can speed up negotiations. Moving away from paper-heavy, language-dependent systems towards digital tools and AI-assisted drafting could accelerate text negotiations, reduce translation or language delays and make participation easier for smaller delegations.

Beyond funding and technical aid, small delegations can be empowered through real-time intelligence, dedicated staff, mentorship and early access to information. Gender and regional balance can be ensured through measures like speaking-time quotas and consistent, process-long leadership roles.

The collapse of these talks is a warning. Our governance systems were built for another era, yet environmental crises today are more complex and more interconnected than ever. The machinery meant to solve them is buckling under outdated rules and rising pressure.

Without bold reform, multilateral environmentalism risks irrelevance. Failure to reach global agreements will invite fragmented, unilateral fixes – patchwork solutions far too weak to prevent ecological breakdown. The question is not whether reform is needed, but whether we act before it’s too late.

The stakes are high. Every delay means more emissions, more extinctions and more communities exposed to environmental impacts. The world cannot afford negotiations that stall while ecosystems collapse. We need systems that are agile, inclusive, evidence-based and fit for the 21st century.

Don’t have time to read about climate change as much as you’d like?

Get a weekly roundup in your inbox instead. Every Wednesday, The Conversation’s environment editor writes Imagine, a short email that goes a little deeper into just one climate issue. Join the 47,000+ readers who’ve subscribed so far.

Catalina Turcu, Professor of Sustainable Built Environment, UCL

This article is republished from The Conversation under a Creative Commons license. Read the original article.

**

How AI is transforming the future of the built environment

Dec 11, 2025

Image : Rethinking The Future

How AI is transforming the future of the built environment

December 10, 2025

Vector Polygon dot connect line shaped AI. Concept for machine learning and artificial intelligence. — ©undefined undefined | iStock, via Trimble

Artificial Intelligence has been part of our technological landscape for years, but its capabilities are rapidly advancing. The construction industry, in particular, is witnessing unprecedented changes driven by AI, with technology being used in ways unimaginable just a year ago. Benedict Wallbank, partnerships and digital construction strategy manager at Trimble, discusses further

Many of us already use AI assistants to some degree, such as ChatGPT. In fact, many are of the belief that we are at the start of a revolution that will profoundly reshape human society. For the construction industry, this transformation brings both immense opportunities and critical questions.

The vast bulk of AI applied in the construction industry today is “narrow AI”, which is trained to perform a single task, often better and faster than a human can. This is the main type of AI that is currently in use, powering everything from chatbots to workflow automation.

However, a more transformative change is on the horizon: AI with autonomous, agent-like behaviour that can plan, make decisions and execute complex tasks with less human input.

The next wave: Agentic AI and new business models

Greater change is on the way in the form of Artificial General Intelligence (AGI), also known as Agentic AI. Unlike narrow AI, AGI can apply previous learnings and skills to accomplish new tasks in a different context, without needing to be retrained by humans. This allows it to learn and potentially perform virtually any intellectual task a human can.

This evolution will have profound economic implications. According to Jari Heino, vice president & GM, BIM & Engineering at Trimble in Finland, our entire business model may be affected: “AI agents will eventually work somewhat independently, which opens up a whole new world. Which of our tasks can – and should – AI take over?”

The interest in AI within the construction sector is significant, with many seeking to understand its practical value. The true potential of AI lies not in replacing humans, but in eliminating the tasks that humans shouldn’t be doing in the first place.

Redirecting human potential

By automating repetitive, cognitively mundane and even dangerous work, AI frees up human resources to tackle more pressing and skilled challenges, allowing us to confront the labour shortage crisis head on.

In many ways, the time spent on repetitive tasks that could be easily automated represents wasted human potential. Instead, AI can redirect our skilled workforce towards the more pressing challenges and complex jobs, rather than consuming it with routine.

The result isn’t just about improving productivity and efficiency levels – it represents a fundamental shift in what construction professionals can accomplish.

Unlocking trapped data

Perhaps one of the industry’s most persistent challenges is fragmented data. A plethora of proprietary formats means that information can get trapped and value is lost at every project handover. While standards are important, forcing everyone to work the same way is not always a practical solution. Instead, AI can help to organise data behind the scenes, allowing teams to maintain flexible work practices while achieving data harmony.

Benedict Wallbank, who is also a non executive director at NIMA (formerly the UK BIM Alliance), elaborates on this potential: “I’ve been obsessed with the challenges of data interoperability and how we efficiently get to quality, whole-life asset data. At NIMA, so many of our current discussions are on how AI will help us achieve that goal. My personal view is that Agentic AI will provide much of the solution. Do we still need classification and standards? Yes – but AI offers the potential ability to identify and map data that is currently trapped within documents, drawings, models, scans and reality capture.”

Industry-native AI in action

While the world has seen great strides in general purpose AI, attention is turning to industry-native solutions that speak the language of construction. These specialised tools are focused on solving practical problems, understanding context and integrating with existing workflows.

Within Trimble, AI adoption is already widespread, from using it to speed up code writing to enhancing software solutions, all with the focus of streamlining design, modelling and field workflows.

AI enables users to modify 3D models with text prompts, automate geometry creation and classify models efficiently. It performs automated document classification, checks compliance in BIM models, analyses change orders, identifies road defects and runs energy simulations.

In the field, AI can monitor site safety by identifying PPE compliance and hazard zones, as well as comparing scans with models in order to detect deviations. AI aids in finding content, creating materials and detailing designs, providing comprehensive support for various needs.

Navigating the future with trust and responsibility

As AI becomes more autonomous, questions of trust, accountability and regulation are critical. Global approaches to regulation vary. The UK has set out five key principles to be policed sector by sector, while the EU is taking a centralised approach, establishing a shared supervision and enforcement regime.

The US has opted for a lighter touch, leaving regulation to existing laws and individual states to encourage innovation.

The more we hand over tasks to autonomous systems, the more important it becomes to define when a human needs to be involved. Like all things, AI is not infallible. We build systems around the reality of human fallibility, and yet we expect near-infallibility from automated systems.

Regardless, it’s clear that the AI genie has escaped its bottle and is in the process of reshaping the industry. The firms that thrive won’t be those that race to implement every new innovation but those that ask deeper questions of it: which human capabilities should we amplify? How do we preserve the irreplaceable judgment that comes from years of experience in the field?

The organisations that navigate this transition with strategic clarity, understanding that AI serves the builder rather than replacing the craft, will forge the sustainable path forward.

Ben Wallbank

Digital Construction and Partnerships Manager

Trimble

+44 0800 048 8152

vp_uksales@trimble.com

*

Learn more about Trimble, here: www.trimble.com/construction.

*

How artificial intelligence is helping urban planners

Dec 6, 2025

Andrea Yu

Special to The Globe and Mail

Published December 4, 2025

.

Planners and researchers are turning to artificial intelligence to better understand how people move, live and work – while keeping human judgment at the heart of city building.GETTY IMAGES

.

From housing demand to traffic congestion, city planners have long relied on imperfect models to predict how people move and live. Now, artificial intelligence promises to make those forecasts more accurate.

Mohamad Khalil, a transportation engineering researcher who is currently a postdoctoral fellow at the University of Alberta, has been interested in machine learning long before it was trendy.

“I actually started working with machine learning in 2014,” he says. “To me, at the time, it seemed very appealing and very futuristic and an important next step to [urban planning] modelling.” Mr. Khalil says that most urban planning models, which were developed 50 or 60 years ago, are overly simplistic.

“It assumes that humans are 100-per-cent rational and will choose the best option for their own sake,” he says. “For example, you will choose the best route to go to work based on travel time. However, this is not 100-per-cent true. Sometimes, for some reason, you might choose another route.” In comparison, machine learning models are able to use countless data points collected from devices such as mobile phones and vehicle GPS systems to create more complex models, faster and with greater accuracy.

“Machine learning excels with complicated behaviour,” he says.

Mr. Khalil, who conducted his PhD thesis in transportation engineering at the University of British Columbia, built a “modelling suite” – a collection of tools that help simulate and visualize different land-use scenarios using AI to make better predictions that factor in changes across urban, transportation and demographic systems.

“If we’re implementing a policy, how is that policy going to affect a city?” Mr. Khalil says. “If 20 per cent of people are working online compared to 100-per-cent remote, maybe we’ll see less traffic on our roads, maybe people need bigger homes if both partners are working from home and maybe they don’t need two vehicles.”

He envisions his research and modelling tools being adopted by city planners and decision-makers.

“We present to them the different scenarios that could happen,” he says. In turn, planners can make decisions and recommendations to elected officials about infrastructure development such as zoning, building new transit lines and housing.

By considering multiple scenarios, which can be produced quickly and accurately, urban planners can take a more creative and flexible approach to their work by experimenting with different parameters and possibilities.

That ability to test real-world scenarios before making costly infrastructure decisions is already taking hold in Canadian cities.

Ryan Smith, divisional director of planning and development services for the City of Kelowna in the southern interior of British Columbia, has been using predictive modelling to make more informed decisions and recommendations for nearly a decade, although he says the technology has improved recently to analyze larger data sets.

“We’re flying less blind now,” he says. Kelowna has been an early adopter of such technologies. One example is an AI-enabled predictive modelling tool Mr. Smith uses to see what neighbourhoods are likely to be redeveloped soon. These are typically areas with older homes and buildings that might be demolished soon and rebuilt with additional housing density.

“We know what year a house was built, whether or not the owner lives in the house, the improvement value on the property and how much the building is worth,” he says. “We can create a probability of redevelopment with that data and make smarter infrastructure decisions.”

That might look like curb, gutter, sidewalk and street tree improvements, replacing and upsizing sewer and watermains or improving electrical infrastructure in neighbourhoods that are likely to see a higher rate of redevelopment and therefore an increase in residents. These tools allow planners like Mr. Smith to “get ahead” of risks, such as ensuring neighbourhoods have sufficient infrastructure to support more residents.

But while some planners see clear benefits to integrating AI into city planning, others caution against letting the technology steer too much of the process.

Pamela Robinson, a professor at Toronto Metropolitan University’s School of Urban and Regional Planning, cautions against becoming too reliant on it.

“I would argue that AI could be an input into research and decision support, but it shouldn’t be making the decisions,” Ms. Robinson says. “Planners need to stay in charge and be the humans in the loop around the sound professional advice they offer.”

Ms. Robinson sees the potential for AI to improve city building in several different ways, from expediting the approvals process for issuing building permits to platforms for public engagement and consultation and design decisions, such as what types of cladding on a building have lower greenhouse gas emissions. However, she encourages urban planners, decision makers and elected officials to use these technologies with care.

“I think planners are appropriately curious and cautious, and I think that’s a good thing,” she says. “The planners that we’ve worked with want to deliver good outcomes for their residents and they’re committed to their work and the communities where they’re planners. There’s a lot of hype around these tools. It’s early days and I think this kind of curiosity and caution will serve Canadian cities well.”

*

Experience in Energy Transition and Sustainable Development

Dec 3, 2025

.

The Boao Forum for Asia (BFA) Riyadh Conference, co-hosted recently by global company in diversified chemicals SABIC in Riyadh, Saudi Arabia, brought fresh perspectives and valuable experience from the Middle East region, which is witnessing dramatic changes in its economic and social structure.

At a roundtable talks on “Energy Transition and Sustainable Development” within the framework of the BFA Riyadh Conference, Mr. Abdulrahman Al-Fageeh, CEO and Executive Board Member of SABIC, Board Member of BFA, emphasized the importance of energy transition in the context of sustainable development.

e said that to achieve this goal, economy is one of the main factors of sustainable development. According to Mr. Al-Fageeh, the economy can be built on two main sources: manufacturing and services. Both of these sectors need to rely on four pillars to develop: cost competitiveness, technology and innovation, regulation and infrastructure.

Of which, cost competitiveness is an important factor to promote growth and development. However, over the past decade, many developed regions such as Europe have witnessed a significant increase in energy prices and stocks, reducing economic competitiveness.

Mr. Al-Fageeh affirmed technology and innovation is especially important in the chemical industry. Investing in technology and innovation is not only a cost but also a strategic investment for the future. However, many companies still see this as a financial burden rather than an opportunity for growth.

Regulation is the third pillar, with many regulations being issued that can cause uncertainty and slow down economic growth.

Finally, infrastructure, mainly invested by governments and semi-governmental organizations, needs to be developed to support the economy.

Mr. Abdulrahman Al-Fageeh, CEO and Executive Board Member of SABIC, Board Member of BFA

The environment is the second factor that needs to be focused on in sustainable development. “A clean and healthy environment is a goal that all of us, from individuals to businesses and governments, need to strive for,” said Mr. Al-Fageeh. “Reducing, even eliminating, toxic emissions to the air, land and water is a big challenge. In particular, carbon footprint reduction and decarbonization have become important strategic goals for manufacturing and service industries. SABIC has pioneered the development of technology to capture and purify CO2 for use in the production of beverages and industrial products.”

In addition, water conservation is also an urgent issue. “Water is a gift from nature, and we need to use it more efficiently, reducing consumption in industry,” Mr. Al-Fageeh noted. “Raw material waste is also a major problem, affecting the environment. The obvious solution is recycling. SABIC has developed processes to recycle plastics into pyrolysis oil, which can be reused in production. This approach was adopted by the G20 during the Saudi Arabian presidency in 2020 and should be applied globally.”

Socially, building strong relationships through globalization, cooperation and partnership is essential. Good governance is not only essential for publicly listed companies but also for all organizations and government agencies. Viability is important, everyone deserves to live in a safe environment and have access to basic needs. “We need to ensure that every person, animal and plant on earth has the opportunity to live in a safe and healthy environment. Equity and inclusion are also essential,” Mr. Al-Fageeh added.

Notably, understanding the future generation is an important part of society. The majority of the population is the young generation, especially in Saudi Arabia where more than 60-70 per cent of the population is under 50 years old. We need to understand how they think and work from there. “We must believe that today’s young generation are the leaders of tomorrow,” said Mr. Al-Fageeh.

In Middle East, the SABIC Plastics Application Development Center (SPADC) in Riyadh is among SABIC’s largest application development facilities. Covering an area of around 42,000 sq m, it operates as a Center of Excellence for automotive, packaging, consumer, construction, signage, and compounding, supporting innovation across key sectors, including packaging, electrical & electronics, healthcare & hygiene, building & construction and automotive.

SPADC, which functions from a LEED Gold-certified building, brings together highly skilled scientists and technical teams, besides state-of-art fabrication and testing facilities. Through its advanced infrastructure and strong innovation capabilities, SPADC synergizes with the expanding network of SABIC’s Technology & Innovation centers around the world.

In addition, SPADC provides a level of support to customers, helping them optimize their application solutions. It seeks to foster a collaborative environment for academia and SABIC to come together and provide novel solutions to the world’s pressing problems, like technological and sustainability challenges.

In addition, Home of Innovation is SABIC’s growth initiatives to stimulate localization within the National Industrial Strategy and contribute to the realization of Saudi Vision 2030. By integrating marketing, innovation, and technology, it creates demand, promotes downstream industry development, and offers a platform to showcase SABIC’s global innovations while identifying new market opportunities and developing corresponding solutions.

Illustrations of products developed by SABIC

Home of Innovation, which spans 3,000 sq m, encompasses a Collaboration Center, a High-Performance Demonstration Center, and a Technology Showcase Area, featuring real-world applications of high-performance materials, products, and systems integration through an engaging visitor experience.

The Demonstration Center is the first LEED-Platinum certified residential building in the Middle East. It generates more energy than it consumes and emphasizes the use of innovative materials and technologies to enable the application of renewable energy.

To date, 44 companies from 12 different countries, falling under Saudi Arabia’s National Industrial Strategy, are participating in the program. Since its inauguration in 2016, Home of Innovation has welcomed nearly 11,000 visitors from around the world, spanning diverse industries and backgrounds.

In conclusion, lessons from the Middle East are not only valuable experiences but also strategic directions for other countries on the path to sustainable development. Applying these principles will not only improve the economy, but also protect the environment and build a fair and inclusive society. In the context of globalization and climate change, these efforts are not only necessary but also urgent to ensure a sustainable future for all.

In the context of the world accelerating the process of reducing carbon emissions, Vietnam is entering a period of strong energy transition. Resolution 55-NQ/TW of the Politburo has determined to develop energy “in a fast and sustainable manner, one step ahead”, associated with environmental protection, ensuring national defense and security, and using it economically and effectively. Science and technology are therefore considered strategic spearheads, contributing to shifting the economy from dependence on fossil fuels to a clean, smart and sustainable energy model.

The period 2021 – 2030 is considered a pivotal decade for Vietnam to improve its science and technology capacity and carry out a comprehensive energy transition.

**

Giant 3D map shows almost every building in the world

A giant 3D map shows almost every building in the world

A database of 2.75 billion buildings could help scientists to monitor urban planning, climate change, disaster risks and even corruption.

By Mohana Basu, in Nature

Billions of buildings