Tuesday, December 12, 2017

High-resolution data sets on global man-made impervious surfaces and urban extents

In 2012, we posted about a big research project on global forecasts of urban expansion and its environmental impacts, by Karen C. Seto and her lab at Yale. On a related topic, SEDAC (a NASA data center hosted at CIESIN in Columbia University) has released two new high-resolution data sets that some of you might find useful for your own research:

  1. Global Human Built-up And Settlement Extent for the target year 2010, derived from global 30m Landsat satellite data

  2. Global Man-made Impervious Surface for the target year 2010, derived from global 30m Landsat satellite data

Friday, December 8, 2017

Social inequalities and brute luck







Sunday, December 3, 2017

call for papers: Complexity Science and Public Policy

The journal Complexity has opened a call for papers for a special issue on applications of complexity science for public policy.  Thanks Bernardo Furtado for the pointer and co-editing the special issue

This Special Issue aims at collecting both novel research and reviews on Public Policy Modeling and Applications, showing not only the cross-disciplinary nature of the field but also how rigorous scientific studies have already contributed towards understanding the complexity of social systems and to policy making.

Potential topics include but are not limited to the following:
  • Complex social systems and applications in public policy
  • Complexity methods and analysis for policymakers
  • The effects of governance in complex social systems
  • Management of financial networks, real estate, and financing spillovers
  • Smart cities, mobility, and flows in complex urban environments
  • Dynamic risk management in complex scenarios
  • Analyses that explicitly include political-spatial governance boundaries
  • Design and analysis of complex sociotechnical systems for public services

photo credit: Armando G Alonso

Wednesday, November 29, 2017

Using deep learning and Google Street View to estimate the socioeconomic characteristics of neighborhoods

Timnit Gebru and her colleagues have recently published a very interesting paper in PNAS. The authors developed a method to analyze car images from Google Street View using machine-learning and computer vision methods to determine socioeconomic statistics and political preferences at the zip code level in the US. There is a video of Timnit Gebru presenting the paper here

Gebru, T., Krause, J., Wang, Y., Chen, D., Deng, J., Aiden, E. L., & Fei-Fei, L. (2017). Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States. PNAS 2017 : 1700035114v1-201700035 [arxiv version here]

Abstract:
The United States spends more than $250 million each year on the American Community Survey (ACS), a labor-intensive door-to-door study that measures statistics relating to race, gender, education, occupation, unemployment, and other demographic factors. Although a comprehensive source of data, the lag between demographic changes and their appearance in the ACS can exceed several years. As digital imagery becomes ubiquitous and machine vision techniques improve, automated data analysis may become an increasingly practical supplement to the ACS. Here, we present a method that estimates socioeconomic characteristics of regions spanning 200 US cities by using 50 million images of street scenes gathered with Google Street View cars. Using deep learning-based computer vision techniques, we determined the make, model, and year of all motor vehicles encountered in particular neighborhoods. Data from this census of motor vehicles, which enumerated 22 million automobiles in total (8% of all automobiles in the United States), were used to accurately estimate income, race, education, and voting patterns at the zip code and precinct level. (The average US precinct contains ∼∼1,000 people.) The resulting associations are surprisingly simple and powerful. For instance, if the number of sedans encountered during a drive through a city is higher than the number of pickup trucks, the city is likely to vote for a Democrat during the next presidential election (88% chance); otherwise, it is likely to vote Republican (82%). Our results suggest that automated systems for monitoring demographics may effectively complement labor-intensive approaches, with the potential to measure demographics with fine spatial resolution, in close to real time.


cities used to train a model estimating socioeconomic data from car attributes 



Chart of the Day

Saturday, November 25, 2017

Music for the weekend

Soundtrack for a weekend of coding:


Urban Picture

The Guardian has published today a short but interesting piece on the uncertain future of dockless bike sharing systems in China. I saw this via Tim Schwanen on his Twitter. The 'urban pictures' below come from this piece. The photographs were taken by Chen Zixiang.

Graveyard of dockless bicycles in China



image credit: Chen Zixiang for the Guardian

Tuesday, November 21, 2017

[follow up] Transport legacy of mega-events, equity and the future of public transport in Rio de Janeiro

A couple of weeks ago, I organized the seminar "Transport legacy of mega-events, equity and the future of public transport in Rio de Janeiro", which was held at the Institute for Applied Economic Research (Ipea) in Rio de Janeiro. The seminar generated some interesting discussions on issues of equity, transport planning and uneven urban development in Rio. It also contributed in bringing together academic researchers, organizations from the civil society and policy makers directly involved with the transport and urban planning of Rio in different governmental levels (municipality and metropolitan area).

The seminar was recorded and the videos are now available on Ipea's Youtube channel. Apart from session 2, all presentations were in Portuguese.

  • In this session, three speakers including myself presented some of their recent work assessing the equity impacts of transport legacy of mega-events in Rio de Janeiro.


  • While the presentations in the 1st session focused on the role of governmental policies in delivering just transport policies and investments, the second session emphasized the role of community organization and self-management in promoting more just and inclusive transport systems despite of the government.


  • In the the third session, academics and policy makers heavily involved in the transport planning of Rio municipality and metropolitan area reflected about some of the issues addressed in the previous sessions and the challenged involved in the transport planning of Rio.

The event gathering a good audience (aprox. 70 people) and it received attention from national and local TV channels and newspapers. If you don't have time to watch the entire seminar, these four pieces give a good summary of the discussions:
  1. Rio on Watch: "The Results Are In: Costly Mega-Event Transport Projects Did Not Expand Mobility, Address Inequalities"
  2. Rio on Watch: "Experts Debate the Future of Transport in Rio’s Metropolitan Region"
  3. [Portuguese] G1: "Obras viárias da Copa e Olimpíada contribuíram pouco para melhoria do transporte do Rio, aponta Ipea"
  4. [Portuguese] O Globo: "Obras de mobilidade urbana para Copa e Olimpíada favoreceram mais parcela rica da população do Rio"


Tuesday, November 14, 2017

Future of Informal Transport in Rapidly Growing Cities (seminar)

For those in Oxford, London and surroundings, the Oxford Urbanists collective and the 'Cities that Work' initiative from IGC will be holding a seminar on the "Future of Informal Transport in Rapidly Growing Cities”. The event will feature three of the UK's transportation and development giants: Paul Collier (author of The Bottom Billion), Clemence Cavoli (UCL), and Tim Schwanen (Oxford SoGE). I would definitely go if I had the chance.

The event will be held on Wednesday 15th November, from 17-19 at St. Antony’s College (Panel discussion: 17:00-18:30, Nissan Lecture Theatre. sorry for the late post