Hybrid Validation of a Quality-Controlled, Waveform-Centered AI Framework with Optional Multi-Sensor Support for Seismic Monitoring

Rapid and reliable seismic monitoring requires accurate waveform inference, together with robustness to noise, incomplete sensing, and unstable predictions. This study investigates a quality-controlled, waveform-centered, AI-assisted framework for seismic event detection, P- and S-phase picking, graph-aware inter-station refinement, and rapid hazard-related characterization. The framework includes optional DAS, MEMS, and high-rate GNSS branches; however, the primary empirical validation is based on real waveform-centered IRIS records from the Almaty seismic region, not on a fully synchronized multimodal field deployment. The dataset includes seven seismic stations, HHZ waveforms sampled at 100 Hz, 219 seismic events, 1260 event traces, and 240 s P-centered windows from 1 January 2023 to 31 December 2024. Optional auxiliary branches are evaluated through controlled branch-availability, reduced-input, fallback, and stress-test scenarios. Under the standard-condition benchmark, the proposed framework achieved a precision of 0.941, recall of 0.932, F1 score of 0.936, false-alarm rate of 0.051, detection latency of 173 ms, and P- and S-pick mean absolute errors of 31 ms and 54 ms. Under controlled low-SNR testing, it retained an F1 score of 0.846. The findings support waveform-centered, quality-controlled monitoring, while broader cross-domain and fully synchronized multimodal validation remain necessary.