Change analysis on historical shorelines extracted from medium resolution satellite images: a case study on the southern coast of Peninsular Malaysia

9th IGRSM International Conference and Exhibition on Geospatial & Remote Sensing

地球科学;计算机科学

Manaf, Syaifulnizam Abd^1 ; Mustapha, Norwati^1 ; Sulaiman, Md Nasir^1 ; Husin, Nor Azura^1 ; Abdul Hamid, Mohd Radzi^2

Intelligent Computing Research Group, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, UPM Serdang, Selangor

44300, Malaysia^1

Coastal Management and Oceanography Research Centre, National Hydraulic Research Institute of Malaysia, Seri Kembangan, Selangor, Malaysia^2

关键词: Anthropogenic activity;    Boundary information;    Boundary limits;    Change analysis;    Medium-resolution satellite images;    Post-processing stages;    Satellite images;    Supervised machine learning;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/169/1/012101/pdf
DOI  :  10.1088/1755-1315/169/1/012101

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

Information on changes of coastal zones such as erosions and accretions can be monitored by identifying conditions of shorelines. Shorelines provide the boundary information of land and water, which can be performed by using satellite images rather than by using traditional ground survey, which is known as laborious and expensive. In this study, the historical satellite images of Landsat sensors were gathered from year 1977 to 2017. Additionally, one image of SPOT-5 was also included to get more data for analysis. For each satellite image acquired, supervised machine learning techniques were used to classify the image into land and water classes. Then, the shoreline GIS vector were extracted after locating boundaries of both classes and applying post-processing stages on the classified images. The historical shorelines extracted were used to do further change analysis using End Point Rate method to examine the differences between the older shorelines and the newer shorelines. At this stage, two baselines were created for inner and outer baselines to control the analysis boundary limit. Then, transects of the historical shorelines were created for every 50 m interval. The rate of change statistics represent a cumulative summary of the processes affected during the observation duration. The research findings observed that the southern region of Peninsular Malaysia which known as Tanjung Piai was affected mostly by erosion while the western coast was affected by accretion. The erosion regions were affected by the living population along the coastal areas while the accretion was caused by land reclamation against erosion or built-up area expansion. This study was conducted to observe the most affected areas in the southern Peninsular Malaysia for more than 30 years' duration, potentially due to sea level rises besides natural processes and anthropogenic activities.