Floodplain Mapping through Support Vector Machine and Optical/Infrared Images from Landsat 8 OLI/TIRS Sensors: Case Study from Varanasi

Floods are among the most destructive natural disasters causing huge loss to life and property. Any flood management strategy requires floodplain mapping through discrimination of the flood prone areas. The city of Varanasi or Benaras is believed to be the oldest continuously inhabited city of the world. This study aims to develop tools for mapping and discrimination of floodplain of river Ganga at Varanasi. During 2014 floods, the flooded areas were extracted through Normalized Difference Water Index (NDWI) and by Modified NDWI (MNDWI) using the NIR and SWIR bands separately from that of the Landsat 8 satellite imagery. The inundated areas were then identified through Support Vector Machines (SVMs) classification. The results reveal that the MNDWI images provide a better result for flood discrimination than the NDWI images. Ground based measurements for floodplain distance varied between 11 ± 5 m at Janki ghat (bank) and 80 ± 5 m at Asi ghat. The validation between measured and SVMs derived values indicate a strong positive correlation of 0.88 and a low value of Root Mean Square Error (RMSE) of 12.62. The t-test is suggestive of no significant difference between the observed and SVMs values at 95% confidence level, indicating a satisfactory performance of the SVMs for floodplain mapping using Landsat 8 imagery. Therefore, the methodology proposed in this study provides a novel and robust way for floodplain mapping and has potential applications in disaster management and mitigation in the flood affected regions.

[1]  Der-Chiang Li,et al.  A class possibility based kernel to increase classification accuracy for small data sets using support vector machines , 2010, Expert Syst. Appl..

[2]  Dawei Han,et al.  Data Fusion Techniques for Improving Soil Moisture Deficit Using SMOS Satellite and WRF-NOAH Land Surface Model , 2013, Water Resources Management.

[3]  R. P. Singh,et al.  Banāras (Vārāṇasī) : cosmic order, sacred city, Hindu traditions : festschrift to Prof. R.L. Singh , 1993 .

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

[5]  Mustafa Neamah Jebur,et al.  Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS , 2014 .

[6]  Dawei Han,et al.  Artificial intelligence techniques for clutter identification with polarimetric radar signatures , 2012 .

[7]  Xixi Lu,et al.  Application of Remote Sensing in Flood Management with Special Reference to Monsoon Asia: A Review , 2004 .

[8]  P. D. Bhavsar.  Review of remote sensing applications in hydrology and water resources management in India , 1984 .

[9]  M. Zalewski,et al.  Sustainable floodplain management for flood prevention and water quality improvement , 2015, Natural Hazards.

[10]  Y. Ouma,et al.  A water index for rapid mapping of shoreline changes of five East African Rift Valley lakes: an empirical analysis using Landsat TM and ETM+ data , 2006 .

[11]  Hanqiu Xu.  Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery , 2006 .

[12]  Navraj Hanspal,et al.  Artificial Neural Network to Determine Dynamic Effect in Capillary Pressure Relationship for Two-Phase Flow in Porous Media with Micro-Heterogeneities , 2015, Environmental Processes.

[13]  B. Krishna,et al.  Monthly Rainfall Prediction Using Wavelet Neural Network Analysis , 2013, Water Resources Management.

[14]  P. Hobson,et al.  A global map of the functionality of terrestrial ecosystems , 2012 .

[15]  Taskin Kavzoglu,et al.  A kernel functions analysis for support vector machines for land cover classification , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[16]  Alexander Siegmund,et al.  Automatic land cover analysis for Tenerife by supervised classification using remotely sensed data , 2003 .

[17]  Dawei Han,et al.  Machine Learning Techniques for Downscaling SMOS Satellite Soil Moisture Using MODIS Land Surface Temperature for Hydrological Application , 2013, Water Resources Management.

[18]  Dawei Han,et al.  Selection of classification techniques for land use - land cover change investigation , 2012 .

[19]  W. Mitsch,et al.  Ecological engineering of floodplains , 2008 .

[20]  M. Zalewski.  Ecohydrology, biotechnology and engineering for cost efficiency in reaching the sustainability of biogeosphere , 2014 .

[21]  Prashant K. Srivastava,et al.  Flood Hazards Mitigation Analysis Using Remote Sensing and GIS: Correspondence with Town Planning Scheme , 2013, Water Resources Management.

[22]  Conghe Song,et al.  Radiometric correction of multi-temporal Landsat data for characterization of early successional forest patterns in western Oregon , 2006 .

[23]  Xin Huang,et al.  Flood hazard in Hunan province of China: an economic loss analysis , 2008 .

[24]  Damien Raclot,et al.  Remote sensing of water levels on floodplains: a spatial approach guided by hydraulic functioning , 2006 .

[25]  Prashant K. Srivastava,et al.  Appraisal of land use/land cover of mangrove forest ecosystem using support vector machine , 2014, Environmental Earth Sciences.

[26]  Ashbindu Singh,et al.  Review Article Digital change detection techniques using remotely-sensed data , 1989 .

[28]  N. Grimm,et al.  Global Change and the Ecology of Cities , 2008, Science.

[29]  Aradhana Yaduvanshi,et al.  Support vector machines and generalized linear models for quantifying soil dehydrogenase activity in agro-forestry system of mid altitude central Himalaya , 2016, Environmental Earth Sciences.

[30]  Zaw Zaw Latt,et al.  Application of Feedforward Artificial Neural Network in Muskingum Flood Routing: a Black-Box Forecasting Approach for a Natural River System , 2015, Water Resources Management.

[31]  ZhongXiang Zhang,et al.  Development tendency analysis and evaluation of the water ecological carrying capacity in the Siping area of Jilin Province in China based on system dynamics and analytic hierarchy process , 2014 .

[32]  Flow structure in a compound channel with smooth and rough floodplains , 2011 .

[33]  P. Srivastava,et al.  Application of Geo-Spatial Technique for Flood Inundation Mapping of Low Lying Areas , 2014 .

[34]  Robert A. Schowengerdt,et al.  Reconstruction of multispatial, multispectral image data using spatial frequency content , 1980 .

[35]  Christopher B. Field,et al.  Managing the Risks of Extreme Events and Disasters to Advance Climate Change Adaptation: Index , 2012 .

[36]  Deepak Khare,et al.  Flood monitoring using microwave remote sensing in a part of Nuna river basin, Odisha, India , 2015, Natural Hazards.

[37]  Giles M. Foody,et al.  Feature Selection for Classification of Hyperspectral Data by SVM , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[38]  George P. Petropoulos,et al.  Flooding extent cartography with Landsat TM imagery and regularized kernel Fisher's discriminant analysis , 2013, Comput. Geosci..

[39]  Maciej Zalewski,et al.  Ecohydrology and Hydrologic Engineering: Regulation of Hydrology-Biota Interactions for Sustainability , 2015 .

[40]  George P. Petropoulos,et al.  Burnt area delineation from a uni-temporal perspective based on Landsat TM imagery classification using Support Vector Machines , 2011, Int. J. Appl. Earth Obs. Geoinformation.

[41]  K. Shah,et al.  Evolving Human Dimensions and the Need for Continuous Health Assessment of Indian Rivers , 2016 .

[42]  G. Robert Brakenridge,et al.  Floods, floodplains, delta plains — A satellite imaging approach , 2012 .

[43]  B. Wylie,et al.  Analysis of Dynamic Thresholds for the Normalized Difference Water Index , 2009 .

[44]  Guobin Zhu,et al.  Classification using ASTER data and SVM algorithms;: The case study of Beer Sheva, Israel , 2002 .

[45]  Paresh Chandra Deka,et al.  Support vector machine applications in the field of hydrology: A review , 2014, Appl. Soft Comput..

[46]  Paul M. Mather,et al.  Assessment of the effectiveness of support vector machines for hyperspectral data , 2004, Future Gener. Comput. Syst..

[47]  S. K. McFeeters.  The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features , 1996 .

[48]  Pichaid Varoonchotikul,et al.  Flood Forecasting Using Artificial Neural Networks , 2003 .

[49]  Biswajeet Pradhan,et al.  A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS , 2013, Comput. Geosci..

[50]  Luigi Ceccaroni.  Integration of a rule-based expert system, a case-based reasoner and an ontological knowledge-base in the wastewater domain , 2000 .

[51]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.