Towards operational SAR-based flood mapping using neuro-fuzzy texture-based approaches

Abstract Synthetic Aperture Radar (SAR) data are currently the most reliable resource for flood monitoring, though still subject to various uncertainties, which can be objectively represented with probabilistic flood maps. Moreover, the growing number of SAR satellites has increased the likelihood of observing a flood event from space through at least a single SAR image, but generalized methods for flood classification independent of sensor characteristics need to be developed, to fully utilize these images for disaster management. Consequently, a neuro-fuzzy flood mapping technique is proposed for texture-enhanced single SAR images. Accordingly, any SAR image is first processed to generate second-order statistical textures, which are subsequently optimized using a dimensionality reduction technique. The flood and non-flood classes are then modelled within a fuzzy inference system using Gaussian curves. Parameterization is achieved by training a neural network on the image through user-defined polygons. The results of the optimized texture-based neuro-fuzzy classification were compared against the performance of the SAR image alone and that of SAR enhanced with randomly selected texture features. This approach was tested for a COSMO-SkyMed SAR image at two validation sites, for which high resolution aerial photographs were available. An overall accuracy assessment using reliability diagrams demonstrated a reduction of 54.2% in the Weighted Root Mean Squared Error (WRMSE) values compared to the stand-alone use of SAR. WRMSE values estimated for the proposed method varied from 0.027 to 0.196. A fuzzy validation exercise was also proposed to account for the uncertainty in manual flood identification from aerial photography, resulting in fuzzy spatial similarity values ranging from 0.67 to 0.92, with higher values representing better performance. Results suggest that the proposed approach has demonstrated potential to improve operational SAR-based flood mapping.

[1]  Hilde Vernieuwe,et al.  ROC‐based calibration of flood inundation models , 2014 .

[2]  Frank S. Marzano,et al.  Discrimination of Water Surfaces, Heavy Rainfall, and Wet Snow Using COSMO-SkyMed Observations of Severe Weather Events , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[3]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[4]  G. Schumann,et al.  The direct use of radar satellites for event-specific flood risk mapping , 2010 .

[5]  Alberto Refice,et al.  SAR and InSAR for flood monitoring: Examples with COSMO/SkyMed data , 2013, 2013 IEEE International Geoscience and Remote Sensing Symposium - IGARSS.

[6]  David Gillieson,et al.  Relationship of local incidence angle with satellite radar backscatter for different surface conditions , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[7]  Luis Ángel Ruiz Fernández,et al.  Definition of a comprehensive set of texture semivariogram features and their evaluation for object-oriented image classification , 2010, Comput. Geosci..

[8]  Marco Chini,et al.  A Hierarchical Split-Based Approach for Parametric Thresholding of SAR Images: Flood Inundation as a Test Case , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Matthew S. Horritt,et al.  A methodology for the validation of uncertain flood inundation models , 2006 .

[10]  Fernando Pellon de Miranda,et al.  The semivariogram in comparison to the co-occurrence matrix for classification of image texture , 1998, IEEE Trans. Geosci. Remote. Sens..

[11]  Valentijn R. N. Pauwels,et al.  Remote Sensing-Derived Water Extent and Level to Constrain Hydraulic Flood Forecasting Models: Opportunities and Challenges , 2016, Surveys in Geophysics.

[12]  H. Redkey,et al.  A new approach. , 1967, Rehabilitation record.

[13]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[14]  Peter M. Atkinson,et al.  The integration of spectral and textural information using neural networks for land cover mapping in the Mediterranean , 2000 .

[15]  P. Bates,et al.  Progress in integration of remote sensing–derived flood extent and stage data and hydraulic models , 2009 .

[16]  Li Xiao-juan,et al.  Texture Analysis and its Application for Single-Band SAR Thematic Information Extraction , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[17]  Paul D. Bates,et al.  A Change Detection Approach to Flood Mapping in Urban Areas Using TerraSAR-X , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Dong-Chen He,et al.  Texture features based on texture spectrum , 1991, Pattern Recognit..

[19]  Rodger B. Grayson,et al.  Quantitative comparison of spatial fields for hydrological model assessment––some promising approaches , 2005 .

[20]  Patrick Matgen,et al.  Water Level Estimation and Reduction of Hydraulic Model Calibration Uncertainties Using Satellite SAR Images of Floods , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[21]  F. Ulaby,et al.  Textural Infornation in SAR Images , 1986, IEEE Transactions on Geoscience and Remote Sensing.

[22]  L. Smith.  Satellite remote sensing of river inundation area, stage, and discharge: a review , 1997 .

[23]  Paul D. Bates,et al.  Calibration of channel depth and friction parameters in the LISFLOOD-FP hydraulic model using medium resolution SAR data and identifiability techniques , 2016 .

[24]  Nazzareno Pierdicca,et al.  Monitoring Flood Evolution in Vegetated Areas Using COSMO-SkyMed Data: The Tuscany 2009 Case Study , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[25]  Peter M. Atkinson,et al.  Texture classification of Mediterranean land cover , 2007, Int. J. Appl. Earth Obs. Geoinformation.

[26]  Alberto Refice,et al.  SAR and InSAR for Flood Monitoring: Examples With COSMO-SkyMed Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[27]  L. Guerriero,et al.  Natural Hazards and Earth System Sciences An algorithm for operational flood mapping from Synthetic Aperture Radar ( SAR ) data using fuzzy logic , 2011 .

[28]  Jaan Praks,et al.  Flood Mapping With TerraSAR-X in Forested Regions in Estonia , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[29]  Claudia Künzer,et al.  Flood studies using Synthetic Aperture Radar data , 2015 .

[30]  J. R. Eyre,et al.  Variational Assimilation of Remotely-Sensed Observations of the Atmosphere , 1997 .

[31]  Marco Chini,et al.  A new approach for improving flood model predictions based on the sequential assimilation of SAR-derived flood extent maps , 2014 .

[32]  S. N. Omkar,et al.  Integration of speckle de-noising and image segmentation using Synthetic Aperture Radar image for flood extent extraction , 2013, Journal of Earth System Science.

[33]  X. Lai,et al.  Assimilation of spatially distributed water levels into a shallow-water flood model. Part I: Mathematical method and test case , 2009 .

[34]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[35]  B. Haack,et al.  Multisensor remote sensing data for land use/cover mapping. , 1999 .

[36]  R. De Keyser,et al.  Towards the sequential assimilation of SAR-derived water stages into hydraulic models using the Particle Filter: proof of concept , 2010 .

[37]  Roger White,et al.  Hierarchical fuzzy pattern matching for the regional comparison of land use maps , 2001, Int. J. Geogr. Inf. Sci..

[38]  Barry Haack,et al.  Integrating multisensor data and RADAR texture measures for land cover mapping , 2000 .

[39]  G. Schumann,et al.  Evaluating uncertain flood inundation predictions with uncertain remotely sensed water stages , 2008 .

[40]  P. Bates,et al.  Scheduling satellite-based SAR acquisition for sequential assimilation of water level observations into flood modelling , 2013 .

[41]  Florian Pappenberger,et al.  Grasping the unavoidable subjectivity in calibration of flood inundation models: A vulnerability weighted approach , 2007 .

[42]  Nikolas Prechtel,et al.  An easy to use ArcMap based texture analysis program for extraction of flooded areas from TerraSAR-X satellite image , 2014, Comput. Geosci..

[43]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[44]  Simon Plank,et al.  Sentinel-1-based flood mapping: a fully automated processing chain , 2016 .

[45]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[46]  Huili Gong,et al.  Texture Analysis and its Application for Single-Band SAR Thematic Information Extraction , 2008, IGARSS.

[47]  R. Hostache,et al.  Assimilation of spatially distributed water levels into a shallow-water flood model. Part II: Use of a remote sensing image of Mosel River. , 2010 .

[48]  James R. Carr,et al.  Spectral and textural classification of single and multiple band digital images , 1996 .

[49]  Marc Leblanc,et al.  The use of radar satellite data from multiple incidence angles improves surface water mapping , 2014 .

[50]  Edward H. Adelson,et al.  Texture Classification , 2014, Computer Vision, A Reference Guide.

[51]  Keith Beven,et al.  Fuzzy set approach to calibrating distributed flood inundation models using remote sensing observations , 2006 .

[52]  Paul D. Bates,et al.  Data Utilization in Flood Inundation Modelling , 2010 .

[53]  Imen Hammami,et al.  Flood Extent Mapping from Time-Series SAR Images Based on Texture Analysis and Data Fusion , 2018, Remote. Sens..

[54]  Nazzareno Pierdicca,et al.  Integrating Physical and Topographic Information Into a Fuzzy Scheme to Map Flooded Area by SAR , 2008, Sensors.

[55]  Antonio Iodice,et al.  Unsupervised Rapid Flood Mapping Using Sentinel-1 GRD SAR Images , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[56]  Paul D. Bates,et al.  Automatic selection of flood water levels from high resolution Synthetic Aperture Radar images for assimilation into hydraulic models , 2012 .

[57]  Dmitri Kavetski,et al.  Probabilistic Flood Mapping Using Synthetic Aperture Radar Data , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[58]  P. Atkinson,et al.  Relating SAR image texture to the biomass of regenerating tropical forests , 2005 .

[59]  H. Yésou,et al.  Variational assimilation of remotely sensed flood extents using a 2-D flood model , 2014 .

[60]  Alex Hagen,et al.  Fuzzy set approach to assessing similarity of categorical maps , 2003, Int. J. Geogr. Inf. Sci..

[61]  P. Bates,et al.  A technique for the calibration of hydraulic models using uncertain satellite observations of flood extent , 2009 .

[62]  Nazzareno Pierdicca,et al.  An algorithm for operational flood mapping from Synthetic Aperture Radar (SAR) data using fuzzy logic , 2011 .

[63]  Alberto Refice,et al.  A Bayesian Network for Flood Detection Combining SAR Imagery and Ancillary Data , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[64]  S. A. Long,et al.  Flood extent mapping for Namibia using change detection and thresholding with SAR , 2014 .

[65]  Biswajeet Pradhan,et al.  A New Semiautomated Detection Mapping of Flood Extent From TerraSAR-X Satellite Image Using Rule-Based Classification and Taguchi Optimization Techniques , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[66]  P. Bates,et al.  Timely Low Resolution SAR Imagery To Support Floodplain Modelling: a Case Study Review , 2011 .

[67]  Michael A. Wulder,et al.  Automated derivation of geographic window sizes for use in remote sensing digital image texture analysis , 1996 .

[68]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[69]  G. Lannoy,et al.  Assimilating SAR-derived water level data into a hydraulic model: A case study , 2011 .

[70]  Marco Chini,et al.  Probabilistic mapping of flood-induced backscatter changes in SAR time series , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[71]  Paul D. Bates,et al.  The Utility of Spaceborne Radar to Render Flood Inundation Maps Based on Multialgorithm Ensembles , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[72]  Niko E. C. Verhoest,et al.  Accounting for image uncertainty in SAR-based flood mapping , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[73]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[74]  Alex Hagen-Zanker,et al.  Map comparison methods that simultaneously address overlap and structure , 2006, J. Geogr. Syst..

[75]  Giorgio Boni,et al.  A Prototype System for Flood Monitoring Based on Flood Forecast Combined With COSMO-SkyMed and Sentinel-1 Data , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[76]  Zern Liew.  Easy to use , 2013 .

[77]  Patrick Matgen,et al.  Towards an automated SAR-based flood monitoring system: Lessons learned from two case studies , 2011 .

[78]  Paul D. Bates,et al.  The Use of Radar Imagery in Riverine Flood Inundation Studies , 2012 .

[79]  Mario Chica-Olmo,et al.  Computing geostatistical image texture for remotely sensed data classification , 2000 .

[80]  Inge Uljee,et al.  Further developments of a fuzzy set map comparison approach , 2005, Int. J. Geogr. Inf. Sci..