Estimating Liquefaction Susceptibility Using Machine Learning Algorithms with a Case of Metro Manila, Philippines

Soil liquefaction is a phenomenon that can occur when soil loses strength and behaves like liquid during an earthquake. A site investigation essential for determining site’s susceptibility to liquefaction, these investigations frequently generate project-specific geotechnical reports. However, many of reports are stored unused after construction projects completed. This study suggests consolidated integrated, they provide valuable information identifying potential challenges, such as liquefaction. The evaluates the by considering several factors modeled machine learning algorithms. estimated site-specific characteristics, ground elevation, groundwater table SPT N-value, type, fines content. Using calibrated model represented equation, determined properties, including unit weight peak acceleration (PGA). PGA using linear model, which revealed significant positive correlation (R2 = 0.89) between PGA, earthquake magnitude, distance from seismic source. On Marikina West Valley Fault, also assessed hazard anticipated 7.5 M delineated map was validated prior studies.