Semi-supervised 'soft' extraction of urban types associated with deprivation

Date

2024-09-05

Authors

Vanhuysse, Sabine
Wang, Jon
Georganos, Stefanos
Kuffer, Monika
Wolff, Eléonore

Director

Publisher

IEEE
Acceso abierto / Sarbide irekia
Contribución a congreso / Biltzarrerako ekarpena
Versión aceptada / Onetsi den bertsioa

Project identifier

Impacto
OpenAlexGoogle Scholar
cited by count

Abstract

Mapping deprived urban areas in low- and middle-income countries is essential for policy development. While urban deprivation is a complex concept encompassing multiple dimensions, we propose an approach to capture its physical traits reflected in urban morphology, aiming for scalability. Our method makes use of affordable Earth Observation imagery and existing open geospatial datasets, and eliminates the need for manual labeling. It involves feature extraction, unsupervised learning, and pseudo-label based semi-supervised learning, resulting in 'soft' urban deprivation maps that avoid flagging areas as 'slums'. The study demonstrated its effectiveness in identifying the urban types associated with deprived areas at the scale of a large sub-Saharan African city.

Description

Keywords

Semi-supervised learning, Scalability, Morphometrics, Slums, Urban poverty

Department

Ingeniería / Ingeniaritza

Faculty/School

Degree

Doctorate program

item.page.cita

Vanhuysse, S., Abascal, A., Wang, J., Georganos, S., Kuffer, M., Wolff, E. (2024) Semi-supervised 'soft' extraction of urban types associated with deprivation. In 2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (pp. 1581-1584). IEEE. 979-8-3503-6033-2

item.page.rights

© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Los documentos de Academica-e están protegidos por derechos de autor con todos los derechos reservados, a no ser que se indique lo contrario.