| Summary: | Mapping of Antarctic Specially Protected Areas (ASPAs) is a critical aspect of conservation efforts. However, traditional ground-based methods can be time-consuming, expensive, and risky, particularly in remote and extreme environments such as Antarctica. Another challenge is the limited availability of high-quality and up-to-date satellite data, which can hinder the accuracy of the mapping process. This limitation highlights the need for more advanced remote sensing techniques that can provide more precise and real-time data. The use of drones and spectral imaging has emerged as an efficient and cost-effective solution for mapping and has demonstrated significant potential in environmental monitoring and assessment. However, there is still the need for robust and accurate machine learning algorithms that can handle the large amount of data collected by drones and spectral imaging devices. As such, the development of advanced machine learning models that can process and analyse the data in real-time is a crucial area of research for the mapping and monitoring of ASPAs. This study demonstrates the use of innovative drones, multispectral/hyperspectral data, and applied AI for detecting and mapping the distribution of moss, lichens, and other vegetation in an ASPA managed by the Australian Antarctic Division (AAD). By utilizing machine learning algorithms, we processed the data to identify the spectral signatures of different habitats and species. The integration of advanced technologies resulted in accurate mapping and monitoring of vegetation in extreme environments compared to traditional methods. This technology has significant potential to aid in the monitoring and assessment of the impact of climate change on the Antarctic ecosystem. Overall, our study highlights the value of innovative technologies in environmental monitoring and provides insight into the future of conservation and management practices in Antarctica.
|
|---|