IDEAS home Printed from https://ideas.repec.org/a/bla/rgscpp/v14y2022i4p891-913.html
   My bibliography  Save this article

Predicting intra‐urban well‐being from space with nonlinear machine learning

Author

Listed:
  • Piotr Wójcik
  • Krystian Andruszek

Abstract

There is a growing need to analyze welfare at an intra‐urban level because cities often evince stark divisions. It is therefore important to identify inequalities within them. However, data are hardly available – or very expensive. The purpose of this article is to test whether nonlinear machine learning algorithms provide more accurate predictions of intra‐city well‐being than linear models. In addition, we aim to check if freely available and easily accessible data from Open Street Map offer an alternative to high‐resolution daytime satellite images from Google Maps in accurately predicting well‐being on a local level. Inspired by the Local Human Development Index, we construct a well‐being index based on three dimensions: health, education, and welfare. Potential predictors of well‐being include indicators related to the urbanization rate, access to natural amenities, the transportation system, and access to public transport. Four nonlinear machine learning algorithms (support vector regression with polynomial and radial kernel, random forest, and xgboost) are compared with the linear LASSO approach for the 18 districts of Warsaw, Poland. In addition, we apply innovative tools of explainable artificial intelligence (XAI) to identify the most important predictors of well‐being (measuring model‐agnostic feature importance) and to disclose the shape of relationships between well‐being and its most important predictors. We conclude that the application of nonlinear machine learning algorithms to modeling well‐being not only allows us to reach higher predictive accuracy, but also to better identify and explain the impact of its predictors. Cada vez es más necesario analizar el bienestar a nivel intraurbano, ya que las ciudades muestran a menudo divisiones muy marcadas. Por lo tanto, es importante identificar las desigualdades en su seno. Sin embargo, apenas hay datos disponibles, o son muy caros. El objetivo de este artículo es comprobar si los algoritmos de aprendizaje automático no lineal proporcionan predicciones más precisas del bienestar intraurbano que los modelos lineales. Además, se quiso comprobar si los datos gratuitos de libre acceso de Open Street Map ofrecen una alternativa a las imágenes de satélite diurnas de alta resolución de Google Maps a la hora de predecir con precisión el bienestar a nivel local. Tomando el Índice de Desarrollo Humano Local como inspiración, se construyó un índice de bienestar basado en tres dimensiones: salud, educación y bienestar. Entre los posibles predictores del bienestar se encuentran los indicadores relacionados con la tasa de urbanización, el acceso a los servicios de recreo naturales, el sistema de transporte y el acceso al transporte público. Se compararon cuatro algoritmos de aprendizaje automático no lineales (regresión de vectores de apoyo con núcleo polinómico y radial, random forest y xgboost) con el enfoque lineal LASSO para los 18 distritos de Varsovia (Polonia). Además, se aplicaron herramientas innovadoras de inteligencia artificial explicable (conocidas como XAI) para identificar los predictores más importantes del bienestar (midiendo la importancia de las características de forma agnóstica respecto al modelo) y para revelar la forma de las relaciones entre el bienestar y sus predictores más importantes. Se concluyó que la aplicación de algoritmos de aprendizaje automático no lineal a los modelos del bienestar no sólo permite alcanzar una mayor precisión predictiva, sino también identificar y explicar mejor el impacto de sus predictores. 都市は完全な分断を示すことが多いため、都市内レベルで福祉(welfare)を分析する必要性が高まっている。したがって、都市内における不平等を特定することが重要である。しかし、データはほとんど得られていないか、非常に高価である。本稿では、非線形の機械学習アルゴリズムが線形モデルよりも都市内のwell‐beingを正確に予測するかどうかを検定する。さらに、自由に利用可能で容易にアクセスできるOpen Street Mapのデータが、地域レベルでの健康状態を正確に予測する上で、グーグル・マップの高解像度の衛星画像の代替となるものかどうかを検討する。そこで、Local Human Development Indexをヒントに、健康、教育、福祉の3つの項目によるwell‐being指数を構築した。Well‐beingの予測因子の候補として、都市化率、自然アメニティへのアクセス、交通輸送システム、公共交通機関へのアクセスに関する指標などがある。ポーランドのワルシャワの18地区において、4つの非線形の機械学習アルゴリズム(多項式および動径基底関数カーネルによるサポートベクター回帰、ランダムフォレスト、およびXGBoost)を線形Lasso回帰と比較した。また、説明可能な人工知能 (explainable artificial intelligence:XAI)の革新的ツールを適用して、well‐beingの最も重要な予測因子(モデル非依存性の特徴量の測定)を特定し、well‐beingとその最も重要な予測因子との関連の形を明らかにする。結論として、well‐beingのモデル化に、非線形の機械学習アルゴリズムを使用することにより、より高い予測精度が得られるだけでなく、その予測因子の影響をより正確に特定し、説明することが可能になる。

Suggested Citation

  • Piotr Wójcik & Krystian Andruszek, 2022. "Predicting intra‐urban well‐being from space with nonlinear machine learning," Regional Science Policy & Practice, Wiley Blackwell, vol. 14(4), pages 891-913, August.
  • Handle: RePEc:bla:rgscpp:v:14:y:2022:i:4:p:891-913
    DOI: 10.1111/rsp3.12478
    as

    Download full text from publisher

    File URL: https://doi.org/10.1111/rsp3.12478
    Download Restriction: no

    File URL: https://libkey.io/10.1111/rsp3.12478?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Lee, Richard J. & Sener, Ipek N., 2016. "Transportation planning and quality of life: Where do they intersect?," Transport Policy, Elsevier, vol. 48(C), pages 146-155.
    2. repec:hal:wpspec:info:hdl:2441/5l6uh8ogmqildh09h4687h53k is not listed on IDEAS
    3. Frank Bickenbach & Eckhardt Bode & Peter Nunnenkamp & Mareike Söder, 2016. "Night lights and regional GDP," Review of World Economics (Weltwirtschaftliches Archiv), Springer;Institut für Weltwirtschaft (Kiel Institute for the World Economy), vol. 152(2), pages 425-447, May.
    4. Charlotta Mellander & José Lobo & Kevin Stolarick & Zara Matheson, 2015. "Night-Time Light Data: A Good Proxy Measure for Economic Activity?," PLOS ONE, Public Library of Science, vol. 10(10), pages 1-18, October.
    5. Ryan Engstrom & Jonathan Hersh & David Newhouse, 2022. "Poverty from Space: Using High Resolution Satellite Imagery for Estimating Economic Well-being," The World Bank Economic Review, World Bank, vol. 36(2), pages 382-412.
    6. Jasiński, Tomasz, 2019. "Modeling electricity consumption using nighttime light images and artificial neural networks," Energy, Elsevier, vol. 179(C), pages 831-842.
    7. Joseph Stiglitz & Amartya Sen & Jean-Paul Fitoussi, 2009. "The measurement of economic performance and social progress revisited: Reflections and Overview," Sciences Po publications 2009-33, Sciences Po.
    8. Chunpei Lin & Guanxi Zhao & Chuanpeng Yu & Yenchun Jim Wu, 2019. "Smart City Development and Residents’ Well-Being," Sustainability, MDPI, vol. 11(3), pages 1-17, January.
    9. Joseph E. Stiglitz & Amartya Sen & Jean-Paul Fitoussi, 2009. "The measurement of economic performance and social progress revisited," Documents de Travail de l'OFCE 2009-33, Observatoire Francais des Conjonctures Economiques (OFCE).
    10. Lincoln R Larson & Viniece Jennings & Scott A Cloutier, 2016. "Public Parks and Wellbeing in Urban Areas of the United States," PLOS ONE, Public Library of Science, vol. 11(4), pages 1-19, April.
    11. Christopher Yeh & Anthony Perez & Anne Driscoll & George Azzari & Zhongyi Tang & David Lobell & Stefano Ermon & Marshall Burke, 2020. "Using publicly available satellite imagery and deep learning to understand economic well-being in Africa," Nature Communications, Nature, vol. 11(1), pages 1-11, December.
    12. repec:hal:spmain:info:hdl:2441/5l6uh8ogmqildh09h4687h53k is not listed on IDEAS
    13. Maxim Pinkovskiy & Xavier Sala-i-Martin, 2016. "Lights, Camera … Income! Illuminating the National Accounts-Household Surveys Debate," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 131(2), pages 579-631.
    14. J. Vernon Henderson & Adam Storeygard & David N. Weil, 2012. "Measuring Economic Growth from Outer Space," American Economic Review, American Economic Association, vol. 102(2), pages 994-1028, April.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Patrick Lehnert & Michael Niederberger & Uschi Backes-Gellner & Eric Bettinger, 2020. "Proxying Economic Activity with Daytime Satellite Imagery: Filling Data Gaps Across Time and Space," Economics of Education Working Paper Series 0165, University of Zurich, Department of Business Administration (IBW), revised Sep 2022.
    2. Krittaya Sangkasem & Nattapong Puttanapong, 2022. "Analysis of spatial inequality using DMSP‐OLS nighttime‐light satellite imageries: A case study of Thailand," Regional Science Policy & Practice, Wiley Blackwell, vol. 14(4), pages 828-849, August.
    3. Prakash, Nishith & Rockmore, Marc & Uppal, Yogesh, 2019. "Do criminally accused politicians affect economic outcomes? Evidence from India," Journal of Development Economics, Elsevier, vol. 141(C).
    4. Dickinson, Jeffrey, 2020. "Planes, Trains, and Automobiles: What Drives Human-Made Light?," MPRA Paper 103504, University Library of Munich, Germany.
    5. Abbate Nicolás & Gasparini Leonardo & Gluzmann Pablo Alfredo & Montes Rojas Gabriel & Sznaider Iván & Yatche Tobías, 2023. "Ingreso Estructural Por Área Geográfica: una aplicación para Argentina," Asociación Argentina de Economía Política: Working Papers 4622, Asociación Argentina de Economía Política.
    6. Guanghua Chi & Han Fang & Sourav Chatterjee & Joshua E. Blumenstock, 2022. "Microestimates of wealth for all low- and middle-income countries," Proceedings of the National Academy of Sciences, Proceedings of the National Academy of Sciences, vol. 119(3), pages 2113658119-, January.
    7. José García-Montalvo & Marta Reynal-Querol & Juan Carlos Muñoz Mora, 2021. "Measuring Inequality from Above," Working Papers 1252, Barcelona School of Economics.
    8. Jaqueson K. Galimberti, 2020. "Forecasting GDP Growth from Outer Space," Oxford Bulletin of Economics and Statistics, Department of Economics, University of Oxford, vol. 82(4), pages 697-722, August.
    9. Pape,Utz Johann & Wollburg,Philip Randolph, 2019. "Estimation of Poverty in Somalia Using Innovative Methodologies," Policy Research Working Paper Series 8735, The World Bank.
    10. Nguyen, Cuong & Noy, Ilan, 2018. "Measuring the impact of insurance on urban recovery with light: The 2011 New Zealand earthquake," Working Paper Series 6955, Victoria University of Wellington, School of Economics and Finance.
    11. Imryoung Jeong & Hyunjoo Yang, 2021. "Using maps to predict economic activity," Papers 2112.13850, arXiv.org, revised Apr 2022.
    12. E. Ustaoglu & R. Bovkır & A. C. Aydınoglu, 2021. "Spatial distribution of GDP based on integrated NPS-VIIRS nighttime light and MODIS EVI data: a case study of Turkey," Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, Springer, vol. 23(7), pages 10309-10343, July.
    13. Bluhm, Richard & Krause, Melanie, 2022. "Top lights: Bright cities and their contribution to economic development," Journal of Development Economics, Elsevier, vol. 157(C).
    14. Tanner Regan & Giorgio Chiovelli & Stelios Michalopoulos & Elias Papaioannou, 2023. "Illuminating Africa?," Working Papers 2023-11, The George Washington University, Institute for International Economic Policy.
    15. Boone, Catherine & Simson, Rebecca, 2019. "Regional inequalities in African political economy: theory, conceptualization and measurement, and political effects," Economic History Working Papers 100861, London School of Economics and Political Science, Department of Economic History.
    16. Jung, Woojin, 2023. "Mapping community development aid: Spatial analysis in Myanmar," World Development, Elsevier, vol. 164(C).
    17. Gregor Pfeifer & Fabian Wahl & Martyna Marczak, 2018. "Illuminating the World Cup effect: Night lights evidence from South Africa," Journal of Regional Science, Wiley Blackwell, vol. 58(5), pages 887-920, November.
    18. Jaqueson K Galimberti & Stefan Pichler & Regina Pleninger, 2023. "Measuring Inequality Using Geospatial Data," The World Bank Economic Review, World Bank, vol. 37(4), pages 549-569.
    19. Nguyen, Cuong & Noy, Ilan, 2018. "Measuring the impact of insurance on urban recovery with light: The 2011 New Zealand earthquake," Working Paper Series 20316, Victoria University of Wellington, School of Economics and Finance.
    20. Hannes Mueller & André Groeger & Jonathan Hersh & Andrea Matranga & Joan Serrat, 2021. "Monitoring War Destruction from Space Using Machine Learning," Working Papers 1257, Barcelona School of Economics.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:bla:rgscpp:v:14:y:2022:i:4:p:891-913. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Wiley Content Delivery (email available below). General contact details of provider: http://www.blackwellpublishing.com/journal.asp?ref=1757-7802 .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.