SeisMamba: Low-Latency Single-Station Seismic Magnitude Estimation for Spatially Distributed Earthquake Early Warning

• URL: http://arxiv.org/abs/2608.24561v1
• Date: Tue, 25 Aug 2026 13:44:42 GMT
• Title: SeisMamba: Low-Latency Single-Station Seismic Magnitude Estimation for Spatially Distributed Earthquake Early Warning
• Abstract summary: Single-station learning offers a lower-cost alternative, but existing models often face an accuracy--latency trade-off and may degrade under regional distribution shift.<n>We present SeisMamba, a lightweight Mamba-based architecture for low-latency magnitude estimation from minimally processed three-component seismic waveforms recorded at a single station.<n>On the STEAD benchmark, SeisMamba achieves the best MSE, RMSE, and $R2$ among tested baselines while requiring only 0.55 ms for a batch of 32 waveforms on an NVIDIA T4 GPU.
• Score: 6.287665222121476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rapid earthquake magnitude estimation is central to earthquake early warning, yet many operational systems depend on dense regional seismic networks and region-specific calibration. This creates a spatial coverage barrier for high-risk areas with sparse sensing infrastructure. Single-station learning offers a lower-cost alternative, but existing models often face an accuracy--latency trade-off and may degrade under regional distribution shift. We present SeisMamba, a lightweight Mamba-based architecture for low-latency magnitude estimation from minimally processed three-component seismic waveforms recorded at a single station. SeisMamba combines hierarchical convolutional encoding, sparse selective state-space modelling, multi-scale feature fusion, and an auxiliary temporal prediction head to support efficient long-sequence waveform analysis. On the STEAD benchmark, SeisMamba achieves the best MSE, RMSE, and $R^2$ among tested baselines while requiring only 0.55 ms for a batch of 32 waveforms on an NVIDIA T4 GPU, making it about three times faster than transformer-based baselines. We further conduct a Chile--Taiwan regional hold-out experiment as a diagnostic test of cross-region deployment, where SeisMamba retains useful performance on geographically unseen seismic regions. These results suggest that selective state-space waveform modelling provides a promising accuracy--latency backbone for spatially distributed, low-cost earthquake early warning.

Related papers

• Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models [81.26524429852992]
  PuRF is a novel PuRiFication-driven cache-based method for multi-label test-time adaptation of vision-language models.<n>We show PuRF consistently outperforms state-of-the-art methods, achieving a notable 4.05% mAP improvement on ViT-B/32 across five datasets.
  arXiv  Detail & Related papers  (2026-08-26T11:36:11Z)
• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• Real-Time Earthquake Magnitude Classification from Initial P-Waves: Models, Dataset, and Comparative Analysis for South Asia [0.0]
  We present a comprehensive study of magnitude classification using only the vertical component of the initial 7-second P-wave window from a single station.<n>We compare six machine learning approaches that range from traditional models to state-of-the-art deep learning architectures.<n>Our experiments show that deep learning models substantially outperform traditional approaches.
  arXiv  Detail & Related papers  (2026-05-10T16:25:05Z)
• ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space Model [51.83639270669481]
  Unsupervised anomaly detection in hyperspectral images (HSI) aims to detect unknown targets from backgrounds.<n>HSI studies are hindered by steep computational costs due to the high-dimensional property of HSI and dense sampling-based training paradigm.<n>We propose an Asymmetrical Consensus State Space Model (ACMamba) to significantly reduce computational costs without compromising accuracy.
  arXiv  Detail & Related papers  (2025-04-16T05:33:42Z)
• Spatio-Temporal Graph Structure Learning for Earthquake Detection [1.6044444452278062]
  We propose a Spatio-Temporal Graph Convolutional Network (GCN) to model static and dynamic relationships across seismic stations.<n>Our approach processes multi-station waveform data and generates station-specific detection probabilities.<n> Experiments show superior performance over a conventional GCN baseline in terms of true positive rate (TPR) and false positive rate (FPR)
  arXiv  Detail & Related papers  (2025-03-14T09:07:18Z)
• SeisMoLLM: Advancing Seismic Monitoring via Cross-modal Transfer with Pre-trained Large Language Model [63.723408707172894]
  This work presents SeisMoLLM, the first foundation model that utilizes cross-modal transfer for seismic monitoring.<n>It achieves state-of-the-art performance on the DiTing and STEAD datasets across five critical tasks.<n>In addition to its superior performance, SeisMoLLM maintains efficiency comparable to or even better than lightweight models in both training and inference.
  arXiv  Detail & Related papers  (2025-02-27T10:35:53Z)
• An Attention-based Framework with Multistation Information for Earthquake Early Warnings [10.33741515490406]
  This paper proposes a deep learning-based framework, called SENSE, for the intensity prediction task of earthquake early warning systems.<n>The SENSE model is designed to learn the relationships among the set of input stations and the locality-specific characteristics of each station.<n>This study conducted extensive experiments on datasets from Taiwan and Japan.
  arXiv  Detail & Related papers  (2024-12-24T02:18:17Z)
• Fast Information Streaming Handler (FisH): A Unified Seismic Neural Network for Single Station Real-Time Earthquake Early Warning [56.45067876391473]
  Existing EEW approaches treat phase picking, location estimation, and magnitude estimation as separate tasks, lacking a unified framework. We propose a novel unified seismic neural network called Fast Information Streaming Handler (FisH) FisH is designed to process real-time streaming seismic data and generate simultaneous results for phase picking, location estimation, and magnitude estimation in an end-to-end fashion.
  arXiv  Detail & Related papers  (2024-08-13T04:33:23Z)
• Estimating Earthquake Magnitude in Sentinel-1 Imagery via Ranking [5.71478837100808]
  We propose to pose the estimation of earthquake magnitudes as a metric-learning problem. We train models to estimate earthquake magnitude from Sentinel-1 satellite imagery and to additionally rank pairwise samples. Our experiments show at max a 30%+ improvement in MAE over prior regression-only based methods.
  arXiv  Detail & Related papers  (2024-07-25T15:35:44Z)
• Generalized Neural Networks for Real-Time Earthquake Early Warning [22.53592578343506]
  We employ a data recombination method to create earthquakes occurring at any location with arbitrary station distributions for neural network training. The trained models can then be applied to various regions with different monitoring setups for earthquake detection and parameter evaluation. Our models reliably report earthquake locations and magnitudes within 4 seconds after the first triggered station, with mean errors of 2.6-6.3 km and 0.05-0.17, respectively.
  arXiv  Detail & Related papers  (2023-12-23T10:45:21Z)
• DETR Doesn't Need Multi-Scale or Locality Design [69.56292005230185]
  This paper presents an improved DETR detector that maintains a "plain" nature. It uses a single-scale feature map and global cross-attention calculations without specific locality constraints. We show that two simple technologies are surprisingly effective within a plain design to compensate for the lack of multi-scale feature maps and locality constraints.
  arXiv  Detail & Related papers  (2023-08-03T17:59:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.