- National Yunlin University of Science and Technology, Taiwan (cpkuo@yuntech.edu.tw)
Monitoring slope stability in mountainous regions is often constrained by limited power supply and communication capacity. Under such conditions, low-power wireless transmission technologies, such as LoRa and NB-IoT, become indispensable for ensuring reliable data delivery in long-term monitoring systems. Real-time image monitoring of slope deformation, combined with automated image recognition and early-warning mechanisms, has emerged as a rapidly advancing approach in geotechnical hazard mitigation. These technologies enable continuous observation of slope variability and provide timely alerts that can significantly reduce the risk of catastrophic slope failures. However, the enormous volume of image data generated by continuous monitoring poses substantial challenges for transmission efficiency, data storage, and timely analysis. To address these issues, edge computing is increasingly employed at the monitoring site. By processing data locally, edge devices can filter and preserve only critical events before transmitting them to central servers for further recognition and decision-making. This strategy not only accelerates the early-warning process but also reduces false alarms, thereby enhancing the reliability of hazard detection. Furthermore, integrating edge computing with low-power wireless transmission creates a synergistic framework that balances energy efficiency, communication constraints, and analytical accuracy. Such integration is particularly valuable in remote or resource-limited environments where conventional high-bandwidth communication is impractical. The proposed approach highlights the importance of combining advanced sensing technologies with intelligent data management to achieve robust slope monitoring systems. Ultimately, this framework contributes to improving disaster preparedness, reducing misjudgment in early-warning systems, and supporting sustainable infrastructure development in mountainous regions.
How to cite: Kuo, C.: The critical role of edge computing and energy-efficient wireless transmission in real-time image-based recognition of slope deformation, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-188, https://doi.org/10.5194/egusphere-egu26-188, 2026.