부산대학교 도서관

Small streams, despite their rich ecosystems, face challenges in vegetation assessment due tothe limitations of traditional, time-consuming methods. This study presents a groundbreaking approach,combining unmanned aerial vehicles (UAVs), convolutional neural networks (CNNs), and the vegetationdifferential vegetation index (VDVI), to revolutionize both assessment and management of streamvegetation. Focusing on Idong Stream in South Korea (2.7 km long, 2.34 km² basin area) with eight diverserevetment methods, we leveraged high-resolution RGB images captured by UAVs across five dates (July–December). These images trained a ResNeXt101 CNN model, achieving an impressive 89% accuracy inclassifying vegetation cover (soil, water, and vegetation). This enabled detailed spatial and temporal analysisof vegetation distribution. Further, VDVI calculations on classified vegetation areas allowed assessmentof vegetation vitality. Our key findings showcase the power of this approach: (a) The CNN model generatedhighly accurate cover maps, facilitating precise monitoring of vegetation changes over time and space. (b)August displayed the highest average VDVI (0.24), indicating peak vegetation growth crucial for stabilizingstreambanks and resisting flow. (c) Different revetment methods impacted vegetation vitality. Fieldstonesections exhibited initial high vitality followed by decline due to leaf browning. Block-type sections andthe control group showed a gradual decline after peak growth. Interestingly, the “H environment block”exhibited minimal change, suggesting potential benefits for specific ecological functions. (d) Despite initialdifferences, all sections converged in vegetation distribution trends after 15 years due to the influence ofsurrounding vegetation. This study demonstrates the immense potential of UAV-based remote sensingand CNNs for revolutionizing small-stream vegetation assessment and management. By providing high-resolution, temporally detailed data, this approach offers distinct advantages over traditional methods,ultimately benefiting both the environment and surrounding communities through informed decision-making for improved stream health and ecological conservation.