Digital Detection of Acacia Mangium Trees via Remote Sensing for Controlling the Invasive Population of Biodiversity Threats: Case Study in Brunei

Abstract

The growth of invasive Acacia Mangium has presented a new biodiversity threat to Brunei, which is situated on the biologically diverse island of Borneo. Hazards to the native flora due to Acacia's fast invasion and threats to forest fires have resulted in increased risks of burnable oil. In line with Brunei's National Climate Change Policy, which is reflected in Brunei Vision 2035, it is crucial to conserve Brunei's extensive forest cover by proactive management of the Acacia population in the country's tropical rainforests. Therefore, In line with Brunei's National Climate Change Policy, which is reflected in the Brunei vision, active management of the Acacia population in Brunei's rainforests is considered crucial as it can determine and scope out the country's extensive forest cover. In order to identify the species of Acacia tree and the coverage, this study uses UAV-based, high-resolution RGB photos that have been analysed by machine learning software. The images captured are tested and analysed using a convolutional neural network (CNN) model which is trained to detect the Acacia tree species highlighting regions that indicated a maximum accuracy of 84% based on the manually annotated datasets.