Land cover classification in the tropics, solving the problem of cloud covered areas using topographic parameters

Abstract Optical remote sensing data has been extensively used since early seventies for mapping and monitoring land cover. But, cloud cover has always been hindering the optimal use of the data, especially in the tropical and temperate regions. Because of cloud cover, researchers are forced to use only cloud free images or generate a composite using data from different dates to fill in the cloud and cloud-shadow areas. It is not a problem if the filling image is from the same season and from the same year. If there is large time gap between the acquisition date of image with the clouds and that of the filling image it will have an effect on classification accuracy. In this paper, we describe an approach in land cover classification of areas covered by cloud and cloud shadows. We use the synergy of optical image classification, processing of SAR data taking advantage of its ability of penetrating clouds, and decision rules using terrain parameters. We hypothesize that surface roughness of different land cover types derived from processing of SAR data and in combination with other topographic parameters (slope and elevation) can be applied to classify areas covered by clouds and cloud-shadows. The method was applied in a case study in Mts. Wayang-Windu and Patuha areas, near Bandung in West Java, Indonesia. Landsat 8 OLI-TIRS, Sentinel-1 A C band and SRTM DEM data of the study area were obtained. Initial classification of the optical data was carried out using training samples and fuzzy classification. Class labelling was done by applying fuzzy c-means algorithm. The Sentinel-1 A C band data was processed to get surface roughness. Decision boundaries for surface roughness, terrain slope and elevation were generated for each land cover type, which were implemented in the classification of the areas covered by cloud and cloud shadows. The result shows that it is possible to solve the problem of cloud cover using terrain parameters.

[1]  Fabio Del Frate,et al.  Optical and SAR sensor synergies for forest and land cover mapping in a tropical site in West Africa , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[2]  Neil Flood,et al.  Cloud and cloud shadow screening across Queensland, Australia: An automated method for Landsat TM/ETM+ time series , 2013 .

[3]  Dhruba Pikha Shrestha,et al.  Modelling erosion on a daily basis, an adaptation of the MMF approach , 2018, Int. J. Appl. Earth Obs. Geoinformation.

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

[5]  E. Nezry,et al.  Structure detection and statistical adaptive speckle filtering in SAR images , 1993 .

[6]  Eric A. Lehmann,et al.  SAR and optical remote sensing: Assessment of complementarity and interoperability in the context of a large-scale operational forest monitoring system , 2015 .

[7]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[8]  Quan Wang,et al.  A cloud shadow detection method combined with cloud height iteration and spectral analysis for Landsat 8 OLI data , 2018 .

[9]  M. Shepard,et al.  Lava flow surface roughness and depolarized radar scattering , 1996 .

[10]  Dhruba Pikha Shrestha,et al.  Land use classification in mountainous areas : integration of image processing, digital elevation data and field knowledge : application to Nepal , 2001 .

[11]  André Twele,et al.  Regional land cover mapping in the humid tropics using combined optical and SAR satellite data—a case study from Central Sulawesi, Indonesia , 2009 .

[12]  Alex B. McBratney,et al.  Spacial prediction and mapping of continuous soil classes , 1992 .

[13]  Katsuaki Koike,et al.  Applying Bayesian Decision Classification to Pi-SAR Polarimetric Data for Detailed Extraction of the Geomorphologic and Structural Features of an Active Volcano , 2012, IEEE Geoscience and Remote Sensing Letters.

[14]  Kustiyo,et al.  NEW AUTOMATED CLOUD AND CLOUD-SHADOW DETECTION USING LANDSAT IMAGERY , 2014 .

[15]  Chengquan Huang,et al.  Automated masking of cloud and cloud shadow for forest change analysis using Landsat images , 2010 .

[16]  G. Asner,et al.  Cloud cover in Landsat observations of the Brazilian Amazon , 2001 .

[17]  Arif Susanto,et al.  Characterizing Surface Manifestation of Geothermal System under Torrid Zone using Synthetic Aperture Radar(SAR) Data , 2015 .

[18]  B. Law,et al.  Forest Attributes from Radar Interferometric Structure and Its Fusion with Optical Remote Sensing , 2004 .

[19]  Dhruba Pikha Shrestha,et al.  Application of airborne gamma-ray imagery to assist soil survey: A case study from Thailand , 2017 .

[20]  Don-Lin Yang,et al.  An efficient Fuzzy C-Means clustering algorithm , 2001, Proceedings 2001 IEEE International Conference on Data Mining.

[21]  Ketut Wikantika,et al.  Modified Campbell-Shepard Model to Retrieve Surface Roughness in Paddy Fields Using Radarsat-2 Data and Field Measurements , 2018 .

[22]  Kenneth Grogan,et al.  A Review of the Application of Optical and Radar Remote Sensing Data Fusion to Land Use Mapping and Monitoring , 2016, Remote. Sens..

[23]  Josaphat Tetuko Sri Sumantyo,et al.  Identifying Surface Materials on an Active Volcano by Deriving Dielectric Permittivity From Polarimetric SAR Data , 2015, IEEE Geoscience and Remote Sensing Letters.

[24]  C. Woodcock,et al.  Continuous change detection and classification of land cover using all available Landsat data , 2014 .

[25]  Hongsheng Zhang,et al.  Improving the impervious surface estimation with combined use of optical and SAR remote sensing images , 2014 .

[26]  Jie Chen,et al.  GA-SVM Algorithm for Improving Land-Cover Classification Using SAR and Optical Remote Sensing Data , 2017, IEEE Geoscience and Remote Sensing Letters.

[27]  M Saranya.  Cloud Removal from Satellite Images Using Information Cloning , 2014 .

[28]  Anthony Vodacek,et al.  Tracking Land Use/Land Cover Dynamics in Cloud Prone Areas Using Moderate Resolution Satellite Data: A Case Study in Central Africa , 2015, Remote. Sens..

[29]  Fangju Wang,et al.  Fuzzy supervised classification of remote sensing images , 1990 .

[30]  Eric Pottier,et al.  A review of target decomposition theorems in radar polarimetry , 1996, IEEE Trans. Geosci. Remote. Sens..

[31]  Giles M. Foody,et al.  Approaches for the production and evaluation of fuzzy land cover classifications from remotely-sensed data , 1996 .

[32]  M. Joseph Hughes,et al.  Automated Detection of Cloud and Cloud Shadow in Single-Date Landsat Imagery Using Neural Networks and Spatial Post-Processing , 2014, Remote. Sens..

[33]  Marguerite Madden,et al.  Closest Spectral Fit for Removing Clouds and Cloud Shadows , 2009 .

[34]  Yifang Ban,et al.  Fusion of Quickbird MS and RADARSAT SAR data for urban land-cover mapping: object-based and knowledge-based approach , 2010 .

[35]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[36]  Carlos Cabo,et al.  Estimation of surface roughness and stone cover in burnt soils using SAR images , 2008 .

[37]  Zhe Zhu,et al.  Object-based cloud and cloud shadow detection in Landsat imagery , 2012 .

[38]  M. Lake,et al.  Geographical Information Systems in Archaeology , 2006 .