Landslide prediction based on low-cost and sustainable early warning systems with IoT

Under heavy rainfall, landslide early warning system (LEWS) is considered to be an effective method for providing timely warnings, but previous LEWS presents deficiencies such as high cost, high power consumption, and difficulties in secondary development. To address the shortcomings, the current study developed a low-cost and sustainable LEWS that integrates the Internet of Things (IoT) and an off-the-grid solar energy-powered integrated platform for data acquisition, data transmission, and data analysis. Obtained data such as soil moisture content, pore water pressure, deflection angle, and real-time factor of safety (F-s) are used as auxiliary warning indicators or cross-warning indicators. The LEWS considers three states before a landslide: monitoring state, alert state, and triggering state. Slope model tests and outdoor embankment slope tests were conducted to check the feasibility of the proposed LEWS. Results show that (1) compared with previous LEWS, the development cost and power consumption are greatly reduced, and the newly IoT-based LEWS provides an open architecture to meet different application scenarios and requirements and (2) a series of slope model tests based on LEWS successfully allows monitoring authorities to identify risk level, send warning signals, and predict potential movement so as to make enough time for risk management. The low-cost and standalone energy harvesting feature of the LEWS allows it to be applicable across the world.

Automated summary

Under heavy rainfall, a low-cost and sustainable landslide early warning system (LEWS) that integrates the Internet of Things (IoT) and off-the-grid solar energy-powered platform has been developed. The system provides timely warnings by utilizing data on soil moisture content, pore water pressure, deflection angle, and real-time factor of safety. Slope model tests have confirmed its feasibility and its capability of identifying risk levels, sending warning signals, and predicting potential movement for risk management. The LEWS's low cost and standalone energy harvesting feature make it applicable worldwide.