Using open data to detect the structure and pattern of informal settlements: an outset to support inclusive SDGs' achievement. Issue 4 (26th November 2021)

• Record Type: Journal Article
• Authors: Assarkhaniki, Zahra; Sabri, Soheil; Rajabifard, Abbas
• Is Part Of: Big earth data. Volume 5:Issue 4(2021)
• Page Start: 497
• Page End: 526
• Publication Date: 2021-11-26
• Subjects: OpenStreetMap (OSM) -- open data -- random forest (RF) -- machine learning -- medium resolution satellite imagery (MR) -- informal settlement detection -- sustainable development goals (SDGs); Earth sciences -- Periodicals; Earth sciences -- Research -- Periodicals; Geographic information systems Periodicals; 550
• DOI: 10.1080/20964471.2021.1948178
• Languages: English
• ISSNs: 2096-4471

Abstract

ABSTRACT: The detection of informal settlements is the first step in planning and upgrading deprived areas in order to leave no one behind in SDGs. Very High-Resolution satellite images (VHR), have been extensively used for this purpose. However, as a cost-prohibitive data source, VHR might not be available to all, particularly nations that are home to many informal settlements. This study examines the application of open and freely available data sources to detect the structure and pattern of informal settlements. Here, in a case study of Jakarta, Indonesia, Medium Resolution satellite imagery (MR) derived from Landsat 8 (2020) was classified to detect these settlements. The classification was done using Random Forest (RF) classifier through two complementary approaches to develop the training set. In the first approach, available survey data sets (Jakarta's informal settlements map for 2015) and visual interpretation using High-Resolution Google Map imagery have been used to build the training set. Throughout the second round of classification, OpenStreetMap (OSM) layers were used as the complementary approach for training. Results from the validation test for the second round revealed better accuracy and precision in classification. The proposed method provides an opportunity to use open data for informal settlements detection, when: 1) more expensive high resolution data sources are not accessible; 2) the area of interest is not larger than a city; and 3) the physical characteristics of the settlements differ significantly from their surrounding formal area. The method presents the application of globally accessible data to help the achievement of resilience and SDGs in informal settlements.