Coastline Change Modelling Induced by Climate Change Using Geospatial Techniques in Togo (West Africa)

• 作者: Appollonia Okhimambe Jean Paul Rudant Jerry Asaana Kouami Kokou Pouwèréou Nimon Yawo Konko
• 来源期刊: 遥感技术进展(英文)
• 学科: 地球科学
• 关键词: Coastal Erosion Landsat Images NDWI Remote Sensing Sentinel Images SHORELINE SVM
• 年，卷（期）: ygjsjzyw,（2）
• 页码范围: 85-100
• 页数: 16页
• 分类号: P73

摘要

Climate change is a major concern of humanity. One of the consequences of climate change is global warming causing melting glaciers, rising sea levels and shoreline regression. In Togo, the regression of shoreline leads to coastal erosion with significant damage on socio-economic infrastructures and hu</span><span style="font-family:Verdana;">man habitats. This research, basing on geospatial techniques, focuses on coastal </span><span style="font-family:Verdana;">erosion monitoring from 1988 to 2018 in Togo. It is interested in the extrac</span><span style="font-family:Verdana;">tion of shoreline and in the analysis of change. Various satellite images index</span></span><span style="font-family:Verdana;">es</span><span style="font-family:""> </span><span style="font-family:""><span style="font-family:Verdana;">have been developed for shoreline extraction but the major scientific problem concerns the precision of the different classification algorithms methods used for the extraction of the shoreline from these water index. This study used NDWI index from multisource satellite images. It assesses the performance of </span><span style="font-family:Verdana;">Otsu threshold segmentation, Iso Cluster Unsupervised Classification and Supp</span><span style="font-family:Verdana;">ort Vector Machine (SVM) Supervised Classification methods for the</span><span style="font-family:Verdana;"> extraction of the shoreline on NDWI index. The topographic morphology such </span><span style="font-family:Verdana;">as linear and non-linear coastal surfaces have been considered. The estimation</span><span style="font-family:Verdana;"> of the rates of change of the shoreline was performed using the statistical linear regression method (LRR). The results revealed that the SVM Supervised </span><span style="font-family:Verdana;">Classification method showed good performance on linear and non-linear coastal </span><span style="font-family:Verdana;">surface than the other methods. For the kinematics of the shoreline, the southwest of the To