Identifying degrees of deprivation from space using deep learning and morphological spatial analysis of deprived urban areas
Identifying degrees of deprivation from space using deep learning and morphological spatial analysis of deprived urban areas
复制标题
DOI：
10.1016/j.compenvurbsys.2022.101820
复制
发表时间：
2022-05-07
影响因子：
6.8
通讯作者：
Kuffer, Monika
中科院分区：
文献类型：
--
作者：
Abascal, Angela;Rodriguez-Carreno, Ignacio;Kuffer, Monika
低收入和中等收入国家的许多城市正面临着建成区无计划的快速增长，而缺乏关于这些贫困城市地区的详细信息。在住房条件和城市空间方面存在着明显的差异，这些差异与城市贫困有关。然而，中低收入国家的DUAs通常没有用于解决城市贫困问题的适当地理空间信息，这构成了一个紧迫的知识差距。本研究的目的是应用深度学习技术和形态分析来识别DUAs中的剥夺程度。为此，我们首先使用参与式社区众包方法生成建筑足迹的参考数据集。其次，我们采用了基于U-Net架构的深度学习模型，用于卫星图像的语义分割（WorldView 3），以生成建筑物足迹。最后，我们计算多层次的形态特征，从建筑物的足迹，以确定DUAs内的剥夺变化。我们的研究结果表明，深度学习技术在预测DUA中的建筑足迹方面表现令人满意，准确度为F1得分= 0.84，Jaccard指数= 0.73。由此产生的建筑物覆盖区（预测建筑物）是有用的形态度量的计算在网格单元水平，因为，在高密度区域，建筑物不能单独检测，但在团块。形态学特征捕捉DUAs内的剥夺的物理差异。使用四个指标来定义DUA中的形态，即，其中两项涉及建筑物的形式（建筑物的大小和内部的不规则性），另外两项涉及开放空间的形式（邻近性和方向性）。剥夺的程度可以通过分析从预测的建筑物中提取的形态特征来评估，从而产生三个类别：高，中，低剥夺。这项研究的成果有助于改进编制关于城市DUAs（通常称为“贫民窟”）的最新和分类形态空间数据的方法，这些数据对于了解贫困的物理层面至关重要，从而相应地规划有针对性的干预措施。
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.