Buildings and Cities

''This page is about the intersection of urban planning and machine learning in the context of climate change mitigation and adaptation. For an overview of buildings and cities as a whole, please see the Wikipedia page on this topic.'' Buildings offer some of the lowest-hanging fruit when it comes to reducing GHG emissions. While the energy consumed in buildings is responsible for a quarter of global energy-related emissions, a combination of easy-to-implement fixes and state-of-the-art strategies could reduce emissions for existing buildings by up to 90%. It is possible today for buildings to consume almost no energy. Many of these energy efficiency measures actually result in overall cost savings and simultaneously yield other benefits, such as cleaner air for occupants. This potential can be achieved while maintaining the services that buildings provide – and even while extending them to more people, as climate change will necessitate. For example, with the changing climate, more people will need access to air conditioning in regions where deadly heat waves will become common.

Two major challenges are heterogeneity and inertia. Buildings vary according to age, construction, usage, and ownership, so optimal strategies vary widely depending on the context. For instance, buildings with access to cheap, low-carbon electricity may have less need for expensive features such as intelligent light bulbs. Buildings also have very long lifespans; thus, it is necessary both to create new, energy-efficient buildings, and to retrofit old buildings to be as efficient as possible. Urban planning and public policy can play a major role in reducing emissions by providing infrastructure, financial incentives, or energy standards for buildings.

Machine learning provides critical tools for supporting both building managers and policy makers in their efforts to reduce GHG emissions. At the level of building management, ML can help select strategies that are tailored to individual buildings, and can also contribute to implementing those strategies via smart control systems. At the level of urban planning, ML can be used to gather and make sense of data to inform policy makers. In addition, ML can help cities as a whole to transition to low-carbon futures.

Optimizing buildings

 * Forecasting energy loads:
 * Device usage patterns analysis:
 * Controlling HVAC and lighting systems:
 * Fault detection and predictive maintenance in building systems:
 * Demand response and energy social games:
 * AI-guided building design and planning:

(under construction)

Urban planning

 * Mapping built-up and energy infrastructure: Decarbonizing the building and urban transportation sectors requires accurate mapping of the existing infrastructure but there are large data gaps. ML can help generate such data from remote sensing and existing maps.
 * Macro-scale energy demand and GHG emissions assessment in cities: While some electricity system operators release publicly-available data on energy use and the emissions associated with fossil fuel generators, this data is not available in many cases. ML can help map greenhouse gas emissions using remote sensing and/or on-the-ground data.
 * Identifying building retrofit needs: For reducing energy use for thermal comfort in buildings, many buildings need to be retrofitted to increase their thermal performance. ML can help pinpoint which buildings and which specific parts of buildings would yield the best performance gains.
 * Low-carbon urban form, from neighborhoods to large agglomerations: Urban form, the physical form of cities, has important implications of energy use and GHG emissions, for example sprawled cities can induce mobility demand. ML can help analyze energy use implications of different urban forms, simulate urban development pathways and (re-)designing neighborhoods by finding patterns in urban form data.

The future of cities

 * Efficient sensing: The proliferation of sensors poses the question of how to minimize the energy use related to capturing, sending and storing the data. ML can help recognize what is the most information, possibly on the edge, make sensing more efficient.
 * Causal inference of policy interventions: The effect of policy interventions are often uncertain, and it is important to evaluate them to evaluate their effectiveness. Causal inference methods in ML can help observe the effects of policies from observational data.
 * Assessing urban climate: Cities have an influence on their local climate -- which they tend to make hotter -- which has important implications for climate change mitigation and adaptation. ML can help investigate climatic processes in cities at high-resolution and how they related to the built infrastructure.
 * Enabling nature-based solutions in cities: Nature-based solutions, for example planting trees, can provide multiple benefit including sequestrating carbon and providing cooling. ML can help assess what is the current vegetation in cities and pinpoint opportunities for planting trees.
 * Predictive maintenance of public infrastructure: Public infrastructure, for example street lighting, can include a large amount of individual components that are difficult to monitor. ML can help predict which components are more likely to be dysfunctional to ease maintenance operations.

Urban transportation
Urban transportation is of high relevance to mitigating climate change in cities, as mobility within cities represents a large share of the total final energy use in the transportation sector (40% in 2010 ). Transportation topics are treated as a separate section of the wiki, where areas of particular relevance include:


 * Understanding mobility patterns
 * Enabling low-carbon shared mobility
 * Electric vehicle charging infrastructure
 * Fostering urban cycling
 * Supporting public transportation network expansion

Relevant IPCC chapters

 * Chapter 9: "Buildings" in the IPCC Fifth Assessment Report (2014) : An overview of issues related to the mitigation of greenhouse gas emissions (GHG) from the buildings sector.
 * Chapter 12: "Human Settlements, Infrastructure and Spatial Planning" in the IPCC Fifth Assessment Report (2014) : An overview of issues related to the mitigation of greenhouse gas emissions (GHG) from urban areas.

Academic perspectives

 * Advances Toward a Net-Zero Global Building Sector, Ürge-Vorsatz et al. (2020) : An authoritative review of the existing academic and professional literature towards decarbonizing the building sector globally.
 * Six research priorities for cities and climate change, Bai, X., et al. (2018) : Leading urban sustainability researchers call for long-term, cross-disciplinary studies to reduce carbon emissions and urban risks from global warming.
 * Sustainability in an urbanizing planet, by Seto, K C., et al. (2017) : This introduction to a special issue in PNAS enumerates key common themes, knowledge gaps and research priorities towards sustainability in an urbanizing planet.
 * Carbon lock-in: types, causes, and policy implications, by Seto, K,C., et al. (2016) : This is an authoritative review of carbon lock-ins, the phenomenon of inertia in carbon emissions, for example due to long-lived infrastructure, and which a key issue for climate change mitigation in cities.
 * The urban south and the predicament of global sustainability, by Nagendra, H,, et al.(2018) : This piece highlights the challenges to achieve sustainability in cities from the Global South. The authors call for a renewed research focus, and targeted efforts to correct structural biases in the knowledge production system.
 * Internet of Things: Energy boon or bane?, by Hittinger, E,, and Jaramillo, P. (2019) : This short piece discussed direct and indirect impacts on energy systems of Internet of Things technologies.

Perspectives in popular media

 * The air conditioning trap: how cold air is heating the world : This 'long read' from the Guardian introduces the issue of indoors cooling in a warming world, and interlinkages between climate change mitigation and adaptation.

Online Courses and Course Materials

 * Management of Urban Infrastructures, by EPFL, on Coursera. Learn how to develop management practices that effectively integrate the processes of urban planning with urban infrastructures planning and management for sustainable and resilient cities. Course available here.
 * Planning for Climate Change in African Cities, by a consortium, on Coursera: Learn the foundations for understanding African cities’ exposure and sensitivity to climate change, and how cities can manage these impacts in the face of growing uncertainty. The course has a focus on adaptation but is also relevant to understand African cities in the context of climate change mitigation. Course available here.
 * Co-Creating Sustainable Cities, by TU Delft and Wageningen University, on edX: Learn how citizens can be co-creators of sustainable cities when they engage in city politics or in the design of the urban environment and its technologies and infrastructure. Course available here.
 * Renewable Energy and Green Building Entrepreneurship, by Duke University, on Coursera: Learn about the tools, trends, and tips from the field of entrepreneurship as a career path for making a difference and generating wealth in the renewable energy and green building sectors. Course available here.
 * Set of courses on Sustainable Buildings Systems, by TU Delft, on edX: Learn about different ways to reduce energy use in buildings without compromising occupant comfort, in a series of courses from a leading Dutch university. Courses available on Energy Demand in Buildings, Efficient HVAC Systems, Energy Supply Systems for Buildings and more on the edX website.

Major conferences
Building Simulation

Building Simulation and Optimization

BuildSys: ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

Building Performance Analysis Simbuild Conference

Major journals
Energy and Buildings

Applied Energy

Building and Environment

Journal of Building Performance Simulation

Building Simulation

Renewable and Sustainable Energy Reviews

Energy

Energies

Automation in Construction

Indoor Air

Major societies and organizations
The Global Covenant of Mayors for Climate & Energy

The Global Alliance for Buildings and Construction (GlobalABC)

The Global City Teams Challenge (GCTC)

International Building Performance Simulation Association

The American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE)

The American Society of Mechanical Engineers (ASME)

Data
TODO format

Building energy use

 * New York City municipal buildings for buildings over 10,000 square feet, identifying each building’s energy intensity, and available GHG emissions for the calendar years 2010-2014.
 * The Commercial Buildings Energy Consumption Survey (CBECS) is a national sample survey that collects information on the stock of U.S. commercial buildings, their energy-related building characteristics, and their energy consumption and expenditures.

City metabolism
The "metabolism" of a city includes the electricity used, waste generated, and GHG emitted.


 * Metabolism data for 150 cities
 * The China Emission Accounts & Datasets provides energy, emission and socio-economic accounting inventories for China
 * First attempts of global databases on cities emissions and relevant ancillary metrics
 * The Carbon Disclosure Project provides a global platform for cities to measure and disclose environmental data; a variety of datasets are available

Urban Land Use, Infrastructure Data

 * OpenStreetMap is a cooperative alternative to Google Maps where all the data is open access.
 * NYU’s Atlas of Urban Expansion contains historical data on 200 cities worldwide.
 * Open 3D models are available for a few cities.
 * The Urban Atlas of the European Union agency Copernicus includes information on urban land use types.
 * The TABULA project combines data on building types across all of Europe.