Temporal assessment on land use land cover of Somalia after the effect of the civil war using remote sensing

8th IGRSM International Conference and Exhibition on Geospatial & Remote Sensing

地球科学;计算机科学

Abdulle, Abdinur^1 ; Tan, Adhwa Amir^1 ; Pradhan, Biswajeet^1 ; Abdullahi, Saleh^1

Department of Civil Engineering, Faculty of Engineering, University Putra Malaysia, Serdang, Selangor

43400 UPM, Malaysia^1

关键词: Kappa coefficient;    Land use and cover change;    Land use/ land covers;    Mahalanobis classifiers;    Overall accuracies;    Supervised classification;    Temporal assessment;    Undeveloped areas;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/37/1/012063/pdf
DOI  :  10.1088/1755-1315/37/1/012063

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

The aim of this study is to analyse land use and cover changes for the studied area during 1992-2015 and particularly evaluate the effect of civil war on these changes. Three Landsat images were used; Landsat 4 (1992), Landsat 7 (2000) and Landsat 8 (2015). Assessment of changes has been applied through three supervised classification algorithms, support vector machine, minimum classifier, and mahalanobis classifier. The result shows that SVM is providing highest overall accuracy of 98.5% for the years 2000 and 2015 with kappa coefficient of 0.9803 in year 2015. The change detection result show that the higher changes is between year 1992-2000 where vegetation land cover has dropped down to 11.1% and undeveloped area has increased to 11.4%. Whereas for year 2000-2015, higher changes belongs to build up area by 3.30% while undeveloped area and vegetation land cover keep decreasing by 2.64% and 1.93% respectively.