Fusion of Sentinel-1A and Sentinel-2A data for land cover mapping: a case study in the lower Magdalena region, Colombia

Abstract

Land cover-land use (LCLU) classification tasks can take advantage of the fusion of radar and optical remote sensing data, leading generally to increase mapping accuracy. Here we propose a methodological approach to fuse information from the new European Space Agency Sentinel-1 and Sentinel-2 imagery for accurate land cover mapping of a portion of the Lower Magdalena region, Colombia. Data pre-processing was carried out using the European Space Agency's Sentinel Application Platform and the SEN2COR toolboxes. LCLU classification was performed following an object-based and spectral classification approach, exploiting also vegetation indices. A comparison of classification performance using three commonly used classification algorithms was performed. The radar and visible-near infrared integrated dataset classified with a Support Vector Machine algorithm produce the most accurate LCLU map, showing an overall classification accuracy of 88.75%, and a Kappa coefficient of 0.86. The proposed mapping approach has the main advantages of combining the all-weather capability of the radar sensor, spectrally rich information in the visible-near infrared spectrum, with the short revisit period of both satellites. The mapping results represent an important step toward future tasks of aboveground biomass and carbon estimation in the region. ARTICLE HISTORY

Rice Acreage Estimation Using Sentinel-1A Dual Polarised SAR Data in Udham Singh Nagar (Uttarakhand)

“…So, for calculating the radar derived texture, a module was used which was given in the SNAP, grey-level cooccurring matrix (GLCM) module (texture variance and texture contrast) for both VV and VH polarization, parameterized with a 5 × 5 window size and 32 probabilistic quantization levels which results in four different texture images of the Sentinel-1A data (Clerici et al, 2017). And, these six different texture images were then layer stacked into a 6-layers image:…”

A CNN-Based Fusion Method for Feature Extraction from Sentinel Data

“…Turning to multi-sensor SAR-optical fusion for the purpose of vegetation monitoring, a number of contributions can be found in the literature [4,11,16,21,45]. In [11], ALOS POLSAR and Landsat time-series were combined at the feature level for forest mapping and monitoring.…”

“…It represents also the most challenging case because of the several sources of mismatch (temporal, geometrical, spectral, radiometric) among the involved data. As for other categories, a number of typical remote sensing problems can fit this paradigm, such as classification [10,16,[35][36][37], coregistration [15], change detection [38] and feature estimation [4,[39][40][41]. -mixed: the above cases may also occur jointly, generating mixed situations.…”

“…The NDVI obtained from the Landsat source was combined with different SAR polarization subsets for feeding ad hoc artificial networks. A similar feature-level approach, based on Sentinel data, was followed in [16] for the purpose of land cover mapping. To this end, the texture maps extracted from the SAR image were combined with several indices drawn from the optical bands.…”

“…According to the taxonomy given in [5] data fusion methods, i.e., processing dealing with data and information from multiple sources to achieve improved information for decision making can be grouped into three main categories: -pixel-level: the pixel values of the sources to be fused are jointly processed [6][7][8][9]; -feature-level: features like lines, regions, keypoints, maps, and so on, are first extracted independently from each source image and subsequently combined to produce higher-level cross-source features, which may represent the desired output or be further processed [10][11][12][13][14][15][16][17]; -decision-level: the high-level information extracted independently from each source is combined to provide the final outcome, for example using fuzzy logic [18,19], decision trees [20], Bayesian inference [21], Dempster-Shafer theory [22], and so forth.…”