TerraAlert: An Arduino-Based Alert System for Landslide Detection Using Soil Moisture and Tilt Sensors

Proponent/s Name/s (Last Name, First Name, Middle Initial)

• Elyza A. Ariola, University of the CordillerasFollow
• Beyoncy D. Belwigan, University of the CordillerasFollow
• Justine Raizen S. Querido, University of the CordillerasFollow
• Athea M. Aquinde, University of the CordillerasFollow

Document Types

Paper Presentation

Research Theme (for Paper Presentation and Poster Presentation submissions only)

Computer and Software Technology, and Robotics (CSR)

School Name

University of the Cordilleras

Track or Strand

Science, Technology, Engineering, and Mathematics (STEM)

Research Advisor (Last Name, First Name, Middle Initial)

Mary Grace D. Diso & Jyka Reego S. Hipona

Start Date

25-6-2026 10:30 AM

End Date

25-6-2026 12:00 PM

Zoom Link/ Room Assignment

Online - https://zoom.us/j/91936856247?pwd=oCMfMsh44I2wb0dYsEgoInDJy59bOq.1 Meeting ID: 919 3685 6247 | Passcode: research

Abstract/Executive Summary

Landslides have been a threat causing property damage, loss of life, and other destruction in the environment. This study was conducted to create an Arduino based warning system that can detect two signs of an incoming landslide which are the soil moisture and ground tilt. The prototype was made with an attached tilt sensor, soil moisture sensor, and a gsm module that will send alert messages once the moderate risk and dangerous conditions are reached; soil moisture being above 45% and the tilt being over 45°. The research aims to evaluate the prototype’s classification performance based on the sensor’s accuracy and the speed of SMS alert transmission. The tests were held in a controlled environment using a tiltable platform and the prototype was tested on Benguet clay loam soil. Using confusion matrix analysis, the system achieved a true positive rate (TPR) of 1 and a false positive rate (FPR) of 0. This indicates that TerraAlert correctly detected all dangerous conditions while avoiding false alarms. Its scalability, reliability, and accessibility make it a viable community-based early warning tool for landslide-prone areas. In conclusion, the TerraAlert prototype proved feasible and efficient for disaster risk reduction. The researchers recommend adoption by local authorities to strengthen community preparedness and encourage continued support from national agencies for further development, field testing, and large-scale implementation to ensure consistent performance under real environmental conditions.

Keywords

arduino-based system; landslide detection; real-time monitoring; soil moisture; ground tilt

Initial Consent for Publication

yes

Statement of Originality

yes