A Bayesian cure model for earthquake parameter estimation using crowdsourced smartphone data

Earthquake Early Warning Systems (EEWS) are critical\r\ntools for regions prone to seismic activity. However, their widespread\r\nadoption is hampered by the high cost of traditional systems, particularly\r\nin low-income areas. Recently, researchers have proposed low-cost alternatives,\r\nsuch as smartphone-based EEWSs, despite the reliability challenges\r\nof smartphones. This work presents a statistical methodology for\r\nestimating key earthquake parameters using smartphone data. Borrowing\r\nfrom survival data analysis, a Bayesian cure model is proposed that\r\ntreats smartphones as patients in a clinical trial, with earthquake detection\r\nas the censoring event. Incorporating spatial and temporal data,\r\na mixture of parametric densities is developed to represent detectable\r\nearthquake waves. The model is fitted using an adaptive Markov chain\r\nMonte Carlo algorithm. A real-world case study demonstrates the robustness\r\nof the model and provides insights into smartphone-based earthquake\r\nmonitoring.