| 1. |
- Abascal, Angela, et al.
(författare)
-
Identifying degrees of deprivation from space using deep learning and morphological spatial analysis of deprived urban areas
- 2022
-
Ingår i: Computers, Environment and Urban Systems. - : Elsevier BV. - 0198-9715 .- 1873-7587. ; 95
-
Tidskriftsartikel (refereegranskat)abstract
- Many cities in low- and medium-income countries (LMICs) are facing rapid unplanned growth of built-up areas, while detailed information on these deprived urban areas (DUAs) is lacking. There exist visible differences in housing conditions and urban spaces, and these differences are linked to urban deprivation. However, the appropriate geospatial information for unravelling urban deprivation is typically not available for DUAs in LMICs, constituting an urgent knowledge gap. The objective of this study is to apply deep learning techniques and morphological analysis to identify degrees of deprivation in DUAs. To this end, we first generate a reference dataset of building footprints using a participatory community-based crowd-sourcing approach. Secondly, we adapt a deep learning model based on the U-Net architecture for the semantic segmentation of satellite imagery (WorldView 3) to generate building footprints. Lastly, we compute multi-level morphological features from building footprints for identifying the deprivation variation within DUAs. Our results show that deep learning techniques perform satisfactorily for predicting building footprints in DUAs, yielding an accuracy of F1 score = 0.84 and Jaccard Index = 0.73. The resulting building footprints (predicted buildings) are useful for the computation of morphology metrics at the grid cell level, as, in high-density areas, buildings cannot be detected individually but in clumps. Morphological features capture physical differences of deprivation within DUAs. Four indicators are used to define the morphology in DUAs, i.e., two related to building form (building size and inner irregularity) and two covering the form of open spaces (proximity and directionality). The degree of deprivation can be evaluated from the analysis of morphological features extracted from the predicted buildings, resulting in three categories: high, medium, and low deprivation. The outcome of this study contributes to the advancement of methods for producing up-to-date and disaggregated morphological spatial data on urban DUAs (often referred to as 'slums') which are essential for understanding the physical dimensions of deprivation, and hence planning targeted interventions accordingly.
|
|
| 2. |
- Georganos, Stefanos, et al.
(författare)
-
A census from heaven : Unraveling the potential of deep learning and Earth Observation for intra-urban population mapping in data scarce environments
- 2022
-
Ingår i: International Journal of Applied Earth Observation and Geoinformation. - : Elsevier BV. - 1569-8432 .- 1872-826X. ; 114
-
Tidskriftsartikel (refereegranskat)abstract
- Urban population distribution maps are vital elements for monitoring the Sustainable Development Goals, appropriately allocating resources such as vaccination campaigns, and facilitating evidence-based decision making. Typically, population distribution maps are derived from census data from the region of interest. Nevertheless, in several low-and middle-income countries, census information may be unreliable, outdated or unsuitable for spatial analysis at the intra-urban level, which poses severe limitations in the development of urban population maps of adequate quality. To address these shortcomings, we deploy a novel framework utilizing multisource Earth Observation (EO) information such as Sentinel-2 and very-high-resolution Pleiades imagery, openly available building footprint datasets, and deep learning (DL) architectures, providing end -to-end solutions to the production of high quality intra-urban population distribution maps in data scarce contexts. Using several case studies in Sub-Saharan Africa, namely Dakar (Senegal), Nairobi (Kenya) and Dar es Salaam (Tanzania), our results emphasize that the combination of DL and EO data is very potent and can successfully capture relationships between the retrieved image features and population counts at fine spatial resolutions (100 meter). Moreover, for the first time, we used state-of-the-art domain adaptation methods to predict population distributions in Dar es Salaam and Nairobi (R2 = 0.39, 0.60) that did not require national census or survey data from Kenya or Tanzania, but only a sample of training locations from Dakar. The DL architecture is based on a modified ResNet-18 model with dual-streams to analyze multi-modal data. Our findings have strong implications for the development of a new generation of urban population products that are an output of end-to-end solutions, can be updated frequently and rely completely on open data.
|
|
