Work

DTPP:An efficient depthwise separable TCN for seismic phase picking

Year: 2026

Type: article

Abstract: With the rapid development of artificial intelligence in seismology, various deep learning-based seismic phase picking models have emerged in recent years. However, existing models face challenges in balancing picking accuracy with computational efficiency for real-time applications. To address this issue, we propose DTPP, a novel seismic phase picking network that integrates depthwise separable convolution and temporal dilated convolution. The model adopts a backbone-feature fusion-decoder architecture, utilizing depthwise separable convolution and dilated convolution to significantly expand the receptive field while reducing computational complexity. We trained the model on the STEAD dataset and evaluated its performance on the global GEEDataset V1.0(84,782 independent samples after excluding overlapping STEAD data to ensure fair cross-dataset evaluation). Experimental results demonstrate that DTPP achieves a P-wave recall of 0.877, F1 score of 0.878, and average P/S F1 score of 0.714, ranking first among all comparison models. Meanwhile, DTPP maintains high computational efficiency with only 0.25M parameters, 0.98MB model size, and 3ms single-sample inference time per batch, making it suitable for real-time seismic monitoring applications. The proposed method provides an effective solution to the accuracy-efficiency trade-off problem in seismic phase picking tasks. • We propose DTPP, a novel seismic phase picking network that fuses depthwise separable convolution and temporal dilated convolution, achieving an optimal balance between picking accuracy and computational efficiency. • DTPP attains a P - wave recall of 0.877, an F1 score of 0.878, and an average P/S F1 score of 0.714 on the global GEEDataset V1.0, ranking first among all compared models. • With only 0.25M parameters, a 0.98MB model size, and a 3ms single - sample inference time per batch, DTPP is well - suited for real - time seismic monitoring applications. • The model's architecture, including the Stem Block, SeismicBackbone, SeismicASPP, and Decoder, effectively expands the receptive field while reducing computational complexity, leveraging seismological prior knowledge for multi - scale feature aggregation.

Source: Artificial Intelligence in Geosciences

DOI: 10.1016/j.aiig.2026.100189

Authors: Shuai Lv, Yuxiang Peng

Institution: China University of Geosciences (Beijing)

Language: English

Topic: Seismology and Earthquake Studies

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $700

Funder: China Earthquake Administration