MULTI-DATE SENTINEL1 SAR IMAGE TEXTURES DISCRIMINATE PERENNIAL AGROFORESTS IN A TROPICAL FOREST-SAVANNAH TRANSITION LANDSCAPE

Abstract. Synthetic Aperture Radar (SAR) provides consistent information on target land features; especially in tropical conditions that restrain penetration of optical imaging sensors. Because radar response signal is influenced by geometric and di-electrical properties of surface features’, the different land cover may appear similar in radar images. For discriminating perennial cocoa agroforestry land cover, we compare a multi-spectral optical image from RapidEye, acquired in the dry season, and multi-seasonal C-band SAR of Sentinel 1: A final set of 10 (out of 50) images that represent six dry and four wet seasons from 2015 to 2017. We ran eight RF models for different input band combinations; multi-spectral reflectance, vegetation indices, co-(VV) and cross-(VH) polarised SAR intensity and Grey Level Co-occurrence Matrix (GLCM) texture measures. Following a pixel-based image analysis, we evaluated accuracy metrics and uncertainty Shannon entropy. The model comprising co- and cross-polarised texture bands had the highest accuracy of 88.07 % (95 % CI: 85.52–90.31) and kappa of 85.37; and the low class uncertainty for perennial agroforests and transition forests. The optical image had low classification uncertainty for the entire image; but, it performed better in discriminating non-vegetated areas. The measured uncertainty provides reliable validation for comparing class discrimination from different image resolution. The GLCM texture measures that are crucial in delineating vegetation cover differed for the season and polarization of SAR image. Given the high accuracies of mapping, our approach has value for landscape monitoring; and, an improved valuation of agroforestry contribution to REDD+ strategies in the Congo basin sub-region.

[1]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[2]  Cheng Wang,et al.  Utility of multitemporal lidar for forest and carbon monitoring: Tree growth, biomass dynamics, and carbon flux , 2018 .

[3]  Hannes Feilhauer,et al.  Estimating Vegetation Cover from High-Resolution Satellite Data to Assess Grassland Degradation in the Georgian Caucasus , 2016 .

[4]  E. Næsset,et al.  Forest biomass change estimated from height change in interferometric SAR height models , 2014, Carbon Balance and Management.

[5]  Christian Thiel,et al.  Mapping CORINE Land Cover from Sentinel-1A SAR and SRTM Digital Elevation Model Data using Random Forests , 2015, Remote. Sens..

[6]  Robert M. Hawlick.  Statistical and Structural Approaches to Texture , 1979 .

[7]  Olena Dubovyk,et al.  A rule-based approach for crop identification using multi-temporal and multi-sensor phenological metrics , 2018 .

[8]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[9]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[10]  Olena Dubovyk,et al.  Mapping Mangroves Extents on the Red Sea Coastline in Egypt using Polarimetric SAR and High Resolution Optical Remote Sensing Data , 2018 .

[11]  R. Ryan,et al.  Remote Sensing Time Series Product Tool , 2006 .

[12]  S. Weise,et al.  Structure and composition of cocoa agroforests in the humid forest zone of Southern Cameroon , 2017, Agroforestry Systems.

[13]  A. Skidmore,et al.  Narrow band vegetation indices overcome the saturation problem in biomass estimation , 2004 .

[14]  N. Silleos,et al.  Vegetation Indices: Advances Made in Biomass Estimation and Vegetation Monitoring in the Last 30 Years , 2006 .

[15]  J. Shotton,et al.  Decision Forests for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning , 2011 .

[16]  Mryka Hall-Beyer,et al.  Practical guidelines for choosing GLCM textures to use in landscape classification tasks over a range of moderate spatial scales , 2017 .

[17]  Luis Alonso,et al.  Evaluation of Sentinel-2 Red-Edge Bands for Empirical Estimation of Green LAI and Chlorophyll Content , 2011, Sensors.

[18]  L. Norgrove,et al.  Carbon stocks in shaded Theobroma cacao farms and adjacent secondary forests of similar age in Cameroon , 2013 .

[19]  A. Viña,et al.  Comparison of different vegetation indices for the remote assessment of green leaf area index of crops , 2011 .

[20]  D. Unwin.  Geographical information systems and the problem of 'error and uncertainty' , 1995 .

[21]  Bernard De Baets,et al.  Random Forests as a tool for estimating uncertainty at pixel-level in SAR image classification , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[22]  Giorgos Mountrakis,et al.  Effect of classifier selection, reference sample size, reference class distribution and scene heterogeneity in per-pixel classification accuracy using 26 Landsat sites , 2018 .