Mapping of Krau wildlife reserve (KWR) using satellite-based remote sensing and machine-learning techniques

Shaharum, Nur Syafira Nisa (2017) Mapping of Krau wildlife reserve (KWR) using satellite-based remote sensing and machine-learning techniques. [Project Paper] (Submitted)

Text FK 2017 85.pdf Download (62MB)

Abstract

Human-dominated ecosystems are speeding up the loss of habitat populations and species, thus, monitoring and managing the Earth's heritage of biodiversity is really a challenge in natural resource management. Mapping protected area (PA) is essential to understand the disturbance that can affect the biodiversity and conservation management. Land use/ land cover (LU/LC) maps can be used as a tool for decision making by policy makers to ensure sustainable development and understanding the effect of human activities within and around the PA. However, in Malaysia, updated maps of PA are limited and this is a problem for effective management of PA. The objective of this study was to produce an updated LU/LC map for a PA known as Krau Wildlife Reserve (KWR) and its surrounding using remote sensing and related geospatial technologies. Three supervised classification algorithms were used and compared. Multi-date images from Landsat 8 were utilized and Spectral Angle Mapper (SAM), Support Vector Machine (SVM) and Artificial Neural Network (ANN) classifiers were applied and evaluated. The approaches of pan-sharpening and cloud patching were used to enhance the accuracy of LU/LC classification. The images were classified into five classes as dense forest, less dense forest/agriculture, built-up, bare soil and water. Results for the overall accuracy for SAM, ANN and SVM were 85.42%, 97.40% and 97.35% for 30m spatial resolution and 81.96%, 98.22% and 97 .40% for 15m spatial resolution respectively. Thus, the ANN pan-sharpened map produced the highest overall accuracy and the map was utilized to extract more information related to disturbance and encroachment within and around the protected area. It was identified that human socio-economic activities play a major role in altering the environmental conditions of the KWR.

Item Type:	Project Paper
Subjects:	T Technology > TA Engineering (General). Civil engineering (General)
Faculty:	Faculty of Engineering
Depositing User:	Ms Siti Mariam Giman
Date Deposited:	26 Nov 2025 03:22
Last Modified:	26 Nov 2025 03:22
URI:	http://psaspb.upm.edu.my/id/eprint/2624

Actions (login required)

View Item