| 1. |
- Abascal, Angela, et al.
(författare)
-
AI perceives like a local : predicting citizen deprivation perception using satellite imagery
- 2024
-
Ingår i: npj Urban Sustainability. - : Springer Nature. - 2661-8001. ; 4:1
-
Tidskriftsartikel (refereegranskat)abstract
- Deprived urban areas, commonly referred to as ‘slums,’ are the consequence of unprecedented urbanisation. Previous studies have highlighted the potential of Artificial Intelligence (AI) and Earth Observation (EO) in capturing physical aspects of urban deprivation. However, little research has explored AI’s ability to predict how locals perceive deprivation. This research aims to develop a method to predict citizens’ perception of deprivation using satellite imagery, citizen science, and AI. A deprivation perception score was computed from slum-citizens’ votes. Then, AI was used to model this score, and results indicate that it can effectively predict perception, with deep learning outperforming conventional machine learning. By leveraging AI and EO, policymakers can comprehend the underlying patterns of urban deprivation, enabling targeted interventions based on citizens’ needs. As over a quarter of the global urban population resides in slums, this tool can help prioritise citizens’ requirements, providing evidence for implementing urban upgrading policies aligned with SDG-11.
|
|
| 2. |
- 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.
|
|
| 3. |
- Abascal, Angela, et al.
(författare)
-
Making Urban Slum Population Visible : Citizens and Satellites to Reinforce Slum Censuses
- 2024
-
Ingår i: Urban Inequalities from Space. - : Springer. - 9783031491856 - 9783031491832 ; , s. 287-302
-
Bokkapitel (refereegranskat)abstract
- In response to the “Leave No One Behind” principle (the central promise of the 2030 Agenda for Sustainable Development), reliable estimate of the total number of citizens living in slums is urgently needed but not available for some of the most vulnerable communities. Not having a reliable estimate of the number of poor urban dwellers limits evidence-based decision-making for proper resource allocation in the fight against urban inequalities. From a geographical perspective, urban population distribution maps in many low- and middle-income cities are most often derived from outdated or unreliable census data disaggregated by coarse administrative units. Moreover, slum populations are presented as aggregated within bigger administrative areas, leading to a large diffuse in the estimates. Existing global and open population databases provide homogeneously disaggregated information (i.e. in a spatial grid), but they mostly rely on census data to generate their estimates, so they do not provide additional information on the slum population. While a few studies have focused on bottom-up geospatial models for slum population mapping using survey data, geospatial covariates, and earth observation imagery, there is still a significant gap in methodological approaches for producing precise estimates within slums. To address this issue, we designed a pilot experiment to explore new avenues. We conducted this study in the slums of Nairobi, where we collected in situ data together with slum dwellers using a novel data collection protocol. Our results show that the combination of satellite imagery with in situ data collected by citizen science paves the way for generalisable, gridded estimates of slum populations. Furthermore, we find that the urban physiognomy of slums and population distribution patterns are related, which allows for highlighting the diversity of such patterns using earth observation within and between slums of the same city.
|
|
| 4. |
- Ferrara, Vincenza, et al.
(författare)
-
Scaffolding geospatial epistemic discomfort : a pedagogical framework for cross-disciplinary landscape research
- 2024
-
Ingår i: Journal of geography in higher education. - 0309-8265 .- 1466-1845. ; , s. 1-11
-
Tidskriftsartikel (refereegranskat)abstract
- Current environmental crises call for an integrated knowledge of landscapes and their ecosystems in a broader sense. This article presents a pedagogical framework for cross-disciplinary landscape research at postgraduate level. The framework is grounded in the use of geospatial epistemic discomfort as a creative force to develop and enhance inquiry skills able to cross and merge disciplinary boundaries. Developed within the Erasmus+ KA2 project “CROSSLAND”, the pedagogical framework is based on the scaffolding of epistemic discomfort through four key didactic elements: 1) cross-disciplinary group work and open-ended assignment, 2) in-field inquiry as pre-training on space-time, 3) replacement of traditional lectures by student-led seminars, 4) GIS labs centred on the exploration of cross-disciplinary portfolios of geospatial approaches and methods given as worked-out examples. Main results from the evaluation of the framework implementation in a Summer School show how learning cross-disciplinarity happened thanks to a scaffolding that allowed, first and foremost, the socialisation of different conceptualisations of space. While students felt at ease with geospatial epistemic discomfort, we can conclude that spatial cognitive processes are powerful in improving abilities beyond the spatial domain.
|
|
| 5. |
- Ferrara, Vincenza, et al.
(författare)
-
Scaffolding geospatial epistemic discomfort : a pedagogical framework for cross-disciplinary landscape research
- 2024
-
Ingår i: Journal of geography in higher education. - : Routledge. - 0309-8265 .- 1466-1845.
-
Tidskriftsartikel (refereegranskat)abstract
- Current environmental crises call for an integrated knowledge of landscapes and their ecosystems in a broader sense. This article presents a pedagogical framework for cross-disciplinary landscape research at postgraduate level. The framework is grounded in the use of geospatial epistemic discomfort as a creative force to develop and enhance inquiry skills able to cross and merge disciplinary boundaries. Developed within the Erasmus+ KA2 project “CROSSLAND”, the pedagogical framework is based on the scaffolding of epistemic discomfort through four key didactic elements: 1) cross-disciplinary group work and open-ended assignment, 2) in-field inquiry as pre-training on space-time, 3) replacement of traditional lectures by student-led seminars, 4) GIS labs centred on the exploration of cross-disciplinary portfolios of geospatial approaches and methods given as worked-out examples. Main results from the evaluation of the framework implementation in a Summer School show how learning cross-disciplinarity happened thanks to a scaffolding that allowed, first and foremost, the socialisation of different conceptualisations of space. While students felt at ease with geospatial epistemic discomfort, we can conclude that spatial cognitive processes are powerful in improving abilities beyond the spatial domain.
|
|
| 6. |
|
|
| 7. |
- 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.
|
|
| 8. |
- Georganos, Stefanos, et al.
(författare)
-
A Forest of Forests : A Spatially Weighted and Computationally Efficient Formulation of Geographical Random Forests
- 2022
-
Ingår i: ISPRS International Journal of Geo-Information. - : MDPI AG. - 2220-9964. ; 11:9, s. 471-
-
Tidskriftsartikel (refereegranskat)abstract
- The aim of this paper is to present developments of an advanced geospatial analytics algorithm that improves the prediction power of a random forest regression model while addressing the issue of spatial dependence commonly found in geographical data. We applied the methodology to a simple model of mean household income in the European Union regions to allow easy understanding and reproducibility of the analysis. The results are encouraging and suggest an improvement in the prediction power compared to previous techniques. The algorithm has been implemented in R and is available in the updated version of the SpatialML package in the CRAN repository.
|
|
| 9. |
- Georganos, Stefanos, et al.
(författare)
-
Examining the NDVI-rainfall relationship in the semi-arid Sahel using geographically weighted regression
- 2017
-
Ingår i: Journal of Arid Environments. - : Elsevier BV. - 0140-1963. ; , s. 64-74
-
Tidskriftsartikel (refereegranskat)abstract
- The Sahel of Africa is an eco-sensitive zone with complex relations emerging between vegetation productivity and rainfall. These relationships are spatially non-stationary, non-linear, scale dependant and often fail to be successfully modelled by conventional regression models. In response, we apply a local modelling technique, Geographically Weighted Regression (GWR), which allows for relationships to vary in space. We applied the GWR using climatic data (Normalized Vegetation Difference Index and rainfall) on an annual basis during the growing seasons (June–September) for 2002–2012. The operating scale of the Sahelian NDVI–rainfall relationship was found to stabilize around 160 km. With the selection of an appropriate scale, the spatial pattern of the NDVI-rainfall relationship was significantly better explained by the GWR than the traditional Ordinary Least Squares (OLS) regression. GWR performed better in terms of predictive power, accuracy and reduced residual autocorrelation. Moreover, GWR formed spatial clusters with local regression coefficients significantly higher or lower than those that the global OLS model resulted in, highlighting local variations. Areas near wetlands and irrigated lands displayed weak correlations while humid areas such as the Sudanian region at southern Sahel produced higher and more significant correlations. Finally, the spatial relationship of rainfall and NDVI displayed temporal variations as there were significant differences in the spatial trends throughout the study period.
|
|
| 10. |
- Georganos, Stefanos, et al.
(författare)
-
Introduction
- 2024
-
Ingår i: Urban Inequalities from Space. - : Springer. - 9783031491856 - 9783031491832 ; , s. 1-9
-
Bokkapitel (refereegranskat)abstract
- This chapter discusses the challenges faced by low-and middle-income countries (LMICs) in dealing with rapid transformation processes, including increasing inequalities, overconsumption of natural resources, high urbanisation rates, massive environmental degradation, and the growing impacts of climate change. The Majority World, where most of the world’s population resides, is the epicentre of the ongoing urban transformation, but it lacks accurate, high-resolution, and timely data to support mitigation and adaptation processes. The article highlights the potential of Earth Observation (EO) data to address data gaps and tackle urban and environmental challenges in LMICs. The article discusses the advances in using AI and EO-based algorithms to measure and characterize urban and environmental inequalities, including climate change and environmental challenges, infrastructure inequalities, and mapping the morphology and dynamics of cities, sub-urban and peri-urban areas with EO. We emphasize the innovative use of existing datasets to provide locally relevant information to users and how EO can create societal impacts.
|
|
