Monitoring Urban Deprived Areas with Remote Sensing and Machine Learning in Case of Disaster Recovery

Rapid urbanization and increasing population in cities with a large portion of them settled in deprived neighborhoods, mostly defined as slum areas, have escalated inequality and vulnerability to natural disasters. As a result, monitoring such areas is essential to provide information and support decision-makers and urban planners, especially in case of disaster recovery. Here, we developed an approach to monitor the urban deprived areas over a four-year period after super Typhoon Haiyan, which struck Tacloban city, in the Philippines, in 2013, using high-resolution satellite images and machine learning methods. A Support Vector Machine classification method supported by a local binary patterns feature extraction model was initially performed to detect slum areas in the pre-disaster, just after/event, and post-disaster images. Afterward, a dense conditional random fields model was employed to produce the final slum areas maps. The developed method detected slum areas with accuracies over 83%. We produced the damage and recovery maps based on change analysis over the detected slum areas. The results revealed that most of the slum areas were reconstructed 4 years after Typhoon Haiyan, and thus, the city returned to the pre-existing vulnerability level.

[1]  Sooyoul Kim,et al.  Local amplification of storm surge by Super Typhoon Haiyan in Leyte Gulf , 2014, Geophysical research letters.

[2]  Abdulhakim M. Abdi,et al.  Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data , 2019, GIScience & Remote Sensing.

[3]  Alfred Stein,et al.  Detection of Informal Settlements from VHR Images Using Convolutional Neural Networks , 2017, Remote. Sens..

[4]  E. Tayag,et al.  An assessment of disaster-related mortality post-Haiyan in Tacloban City. , 2015, Western Pacific surveillance and response journal : WPSAR.

[5]  R. B. Potts.  Some generalized order-disorder transformations , 1952, Mathematical Proceedings of the Cambridge Philosophical Society.

[6]  Emma Izquierdo-Verdiguier,et al.  Evaluating the Performance of a Random Forest Kernel for Land Cover Classification , 2017, Remote. Sens..

[7]  Hannes Taubenböck,et al.  Slum mapping in polarimetric SAR data using spatial features , 2017 .

[8]  Dilkushi A. de Alwis Pitts,et al.  Enhanced change detection index for disaster response, recovery assessment and monitoring of buildings and critical facilities - A case study for Muzzaffarabad, Pakistan , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[9]  Vladlen Koltun,et al.  Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials , 2011, NIPS.

[10]  Dongmei Chen,et al.  Change detection from remotely sensed images: From pixel-based to object-based approaches , 2013 .

[11]  F. Yamazaki,et al.  Post-Disaster Urban Recovery Monitoring in Pisco After the 2007 Peru Earthquake Using Satellite Image , 2014 .

[12]  Daniel Arribas-Bel,et al.  Remote sensing-based measurement of Living Environment Deprivation: Improving classical approaches with machine learning , 2017, PloS one.

[13]  M. Kuffer,et al.  Urban morphology of unplanned settlements: the use of spatial metrics in VHR remotely sensed images , 2011 .

[14]  Norman Kerle,et al.  Post-Disaster Recovery Monitoring with Google Earth Engine , 2020 .

[15]  Monika Kuffer,et al.  Identifying a Slums' Degree of Deprivation from VHR Images Using Convolutional Neural Networks , 2019, Remote. Sens..

[16]  Norman Kerle,et al.  Remote Sensing-Based Proxies for Urban Disaster Risk Management and Resilience: A Review , 2018, Remote Sensing.

[17]  George Vosselman,et al.  Identification of Structurally Damaged Areas in Airborne Oblique Images Using a Visual-Bag-of-Words Approach , 2016, Remote. Sens..

[18]  Anil M. Cheriyadat,et al.  Image Based Characterization of Formal and Informal Neighborhoods in an Urban Landscape , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[19]  Alfred Stein,et al.  Urban slum detection using texture and spatial metrics derived from satellite imagery , 2016 .

[20]  Catherine Linard,et al.  Need for an Integrated Deprived Area “Slum” Mapping System (IDEAMAPS) in Low- and Middle-Income Countries (LMICs) , 2020, Social Sciences.

[21]  Edoardo Pasolli,et al.  Post-Disaster Building Database Updating Using Automated Deep Learning: An Integration of Pre-Disaster OpenStreetMap and Multi-Temporal Satellite Data , 2019, Remote. Sens..

[22]  Alejandro Betancourt,et al.  Exploring the Potential of Machine Learning for Automatic Slum Identification from VHR Imagery , 2017, Remote. Sens..

[23]  Ranga Raju Vatsavai,et al.  Machine Learning Approaches for Slum Detection Using Very High Resolution Satellite Images , 2018, 2018 IEEE International Conference on Data Mining Workshops (ICDMW).

[24]  J. Chamie,et al.  World Urbanization Prospects: The 2003 Revision , 2004 .

[25]  J. Qi,et al.  Remote Sensing for Grassland Management in the Arid Southwest , 2006 .

[26]  Hannes Taubenböck,et al.  Urbanization in India - Spatiotemporal analysis using remote sensing data , 2009, Comput. Environ. Urban Syst..

[27]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[28]  Norman Kerle,et al.  Post-disaster recovery assessment using multi-temporal satellite images with a deep learning approach , 2019 .

[29]  Monika Kuffer,et al.  Post-Disaster Recovery Assessment with Machine Learning-Derived Land Cover and Land Use Information , 2019, Remote. Sens..

[30]  Benjamin F. Zaitchik,et al.  Land Cover Classification in Complex and Fragmented Agricultural Landscapes of the Ethiopian Highlands , 2016, Remote. Sens..

[31]  Thomas Blaschke,et al.  Monitoring recovery after earthquakes through the integration of remote sensing, GIS, and ground observations: the case of L’Aquila (Italy) , 2016 .

[32]  Mustafa Turker,et al.  Building extraction from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification, Hough transformation and perceptual grouping , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[33]  Alfred Stein,et al.  Urban social vulnerability assessment with physical proxies and spatial metrics derived from air- and spaceborne imagery and GIS data , 2009 .

[34]  Saman Ghaffarian,et al.  Automatic building detection based on Purposive FastICA (PFICA) algorithm using monocular high resolution Google Earth images , 2014 .

[35]  Amir Hossein Alavi,et al.  Machine learning in geosciences and remote sensing , 2016 .

[36]  Fabio Dell'Acqua,et al.  Phisical Vulnerability Proxies from Remotes Sensing: Reviewing, Implementing and Disseminating Selected Techniques , 2015, IEEE Geoscience and Remote Sensing Magazine.

[37]  Xueliang Zhang,et al.  Deep learning in remote sensing applications: A meta-analysis and review , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[38]  Krithi Ramamritham,et al.  Transfer learning approach to map urban slums using high and medium resolution satellite imagery , 2019, Habitat International.

[39]  Pedram Ghamisi,et al.  Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review , 2020, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[40]  Jerry T. Mitchell,et al.  Evaluating post-Katrina recovery in Mississippi using repeat photography. , 2011, Disasters.

[41]  Cuizhen Wang,et al.  Remote Sensing Derived Indices for Tracking Urban Land Surface Change in Case of Earthquake Recovery , 2020, Remote. Sens..

[42]  Stephanie E. Chang,et al.  Urban disaster recovery: a measurement framework and its application to the 1995 Kobe earthquake. , 2010, Disasters.

[43]  Saman Ghaffarian,et al.  Automatic vehicle detection based on automatic histogram-based fuzzy C-means algorithm and perceptual grouping using very high-resolution aerial imagery and road vector data , 2016 .

[44]  P. Agouris,et al.  The study of slums as social and physical constructs: challenges and emerging research opportunities , 2016 .

[45]  Saman Ghaffarian,et al.  Automatic histogram-based fuzzy C-means clustering for remote sensing imagery , 2014 .

[46]  George Vosselman,et al.  Post-Disaster Building Damage Detection from Earth Observation Imagery Using Unsupervised and Transferable Anomaly Detecting Generative Adversarial Networks , 2020, Remote. Sens..

[47]  Monika Kuffer,et al.  Machine Learning-Based Slum Mapping in Support of Slum Upgrading Programs: The Case of Bandung City, Indonesia , 2018, Remote. Sens..

[48]  Mustafa Turker,et al.  Support vector machines classification for finding building patches from IKONOS imagery: the effect of additional bands , 2014 .

[49]  Monika Kuffer,et al.  Image based classification of slums, built-up and non-built-up areas in Kalyan and Bangalore, India , 2018, European Journal of Remote Sensing.

[50]  Francesco Carlo Nex,et al.  UAV-Based Structural Damage Mapping: A Review , 2019, ISPRS Int. J. Geo Inf..

[51]  Shuyuan Yang,et al.  A Survey of Deep Learning-Based Object Detection , 2019, IEEE Access.

[52]  Gui-Song Xia,et al.  Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models , 2018 .

[53]  Jiong Wang,et al.  Deprivation pockets through the lens of convolutional neural networks , 2019, Remote Sensing of Environment.

[54]  Meng Liu,et al.  The use of remotely sensed data and ground survey tools to assess damage and monitor early recovery following the 12.5.2008 Wenchuan earthquake in China , 2012, Bulletin of Earthquake Engineering.

[55]  Norman Kerle,et al.  TOWARDS POST-DISASTER DEBRIS IDENTIFICATION FOR PRECISE DAMAGE AND RECOVERY ASSESSMENTS FROM UAV AND SATELLITE IMAGES , 2019, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[56]  Monika Kuffer,et al.  Slums from Space - 15 Years of Slum Mapping Using Remote Sensing , 2016, Remote. Sens..

[57]  Alfred Stein,et al.  An ontology of slums for image-based classification , 2012, Comput. Environ. Urban Syst..

[58]  Andrew Crooks,et al.  A Critical Review of High and Very High-Resolution Remote Sensing Approaches for Detecting and Mapping Slums: Trends, Challenges and Emerging Opportunities , 2018 .

[59]  Norman Kerle,et al.  Structural Building Damage Detection with Deep Learning: Assessment of a State-of-the-Art CNN in Operational Conditions , 2019, Remote. Sens..

[60]  Xin Pan,et al.  Joint Deep Learning for land cover and land use classification , 2019, Remote Sensing of Environment.

[61]  Katja Banovec Juros.  Sendai Framework Monitor , 2020 .

[62]  Monika Kuffer,et al.  Extraction of Slum Areas From VHR Imagery Using GLCM Variance , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[63]  Divyani Kohli,et al.  Mapping informal settlement indicators using object-oriented analysis in the Middle East , 2018, Int. J. Digit. Earth.

[64]  Norman Kerle,et al.  Evaluating Resilience-Centered Development Interventions with Remote Sensing , 2019, Remote. Sens..