本日選文（共 2 篇）。

[1755] 將基於深度神經網路與地震水平對垂直頻譜比之地震動模型應用於日本2024年能登半島地震

Application of Ground‐Motion Model Based on Deep Neural Network and Earthquake Horizontal‐to‐Vertical Spectral Ratio to the 2024 Noto Peninsula Earthquake in Japan

  • 期刊：Geophysics (GeoScienceWorld) — Advance Access
  • Published：Mon, 11 May 2026 00:00:00 GMT
  • DOI：10.1785/0120250265/730571
  • 原文連結：連結

Summary (EN) The paper tests a deep‑neural‑network ground‑motion model that incorporates earthquake horizontal‑to‑vertical spectral ratios (EHVRs) against recordings from the 2024 Noto Peninsula (Mw 7.5) earthquake. The DNN was retrained on an updated strong‑motion database with site‑specific EHVRs and used data augmentation (adding random noise to response spectra and EHVRs) to better represent large‑amplitude motions. Evaluation against observed spectra and independent 2024 events shows the augmented model outperformed the original, especially in near‑field areas, and generalized well while capturing complex site‑specific spectral features including peak shifts under strong shaking.

重點摘要（繁中） 本文將結合地震水平與垂直譜比（EHVR）的深度神經網路（DNN）地震動模型應用於2024年能登半島（Mw 7.5）地震的記錄。研究將最新的強震資料庫與場站特定的EHVR整合並重新訓練模型，並透過在反應譜與EHVR中加入隨機雜訊的資料擴增以補強大振幅資料的不足。與觀測譜及2024年其他獨立事件比對結果顯示，擴增後的模型較原始模型表現更佳（尤以近場為著），且具良好泛化能力，能有效擬合包括峰值位移在內的複雜場站特性。

[1769] 中國共和盆地增強型地熱系統的誘發地震由既有構造與應力變化共同控制

Pre‐Existing Structures and Stress Variations Jointly Control the Induced Seismicity in Enhanced Geothermal System of Gonghe Basin, China

  • 期刊：Earth and Space Science (AGU/Wiley) — eTOC
  • Published：Tue, 12 May 2026 08:10:47 -0700
  • DOI：10.1029/2025JB033158
  • 原文連結：連結

Summary (EN) This study analyzes 7,346 seismic events recorded during 2021 hydraulic stimulation and circulation tests at China’s first EGS in the Gonghe Basin using a machine‑learning catalog and principal‑stress modeling. The events form a donut‑like pattern of four clusters and indicate reactivation of weak, low‑friction faults (μ ≈ 0.23, 95% CI 0.19–0.48) consistent with chlorite‑rich gouges, with modest fluid overpressure (~0.8–34 MPa) needed to trigger slip. Seismicity is controlled by scale‑dependent factors: at ~1 km scale it localizes on pre‑existing faults via shear reactivation, while at 1–100 m scale it aligns with SHmax rotations tied to lithologic contrasts and fault‑damage zones, implying hazard assessments must include low‑friction minerals and structural/stress heterogeneity.

重點摘要（繁中） 本研究以機器學習建立的目錄與主應力模擬，分析了2021年在中國共和盆地首座強化地熱系統（EGS）水力刺激與循環測試期間記錄到的7,346次地震事件。地震呈現四個聚集的甜甜圈狀分布，顯示為低摩擦係數（μ ≈ 0.23，95% CI 0.19–0.48）的薄弱斷層再活動，與含綠泥石的破碎帶相符，且需低至中等的流體超壓（約0.8–34 MPa）才能啟動滑動。研究指出誘發地震受尺度依賴控制：在約1 km尺度上事件沿已存在的自然斷層以剪切再活化為主；在1–100 m的井孔尺度則與最大主應力（SHmax）旋轉、岩性差異及斷層損傷帶相關，顯示地震危險評估應納入低摩擦礦物與結構與應力異質性。