Enhanced deep learning approach for detecting and locating tectonic tremors in the Nankai subduction zone Yuya Jinde, Amane Sugii, Yoshihiro Hiramatsu Earth Planets and Space, 2025 Tectonic tremors are key indicators of slow-slip phenomena, and detecting them accurately is a challenging task. Conventional techniques often fail to detect tremors during periods of intense tremor activity. We present here a deep learning approach for detecting and locating tremors in the Nankai subduction zone that is more effective than conventional techniques. We utilized two convolutional neural networks (CNNs): a CNN for classification of seismic waveforms into noise, tremors, or earthquakes, and a CNN for regression prediction of tremor epicenters from amplitude data. The accuracy, recall, and precision of the CNN for classification all exceeded 95%. The CNN for regression used ensemble predictions to produce estimates of tremor locations with a median error of 3.2 km. When this approach was applied to continuous data, it successfully mapped key features of tremor activity and improved the detection and location of tremors, especially during high-activity periods. Graphical Abstract
Coseismic slip distribution of the 2024 Noto Peninsula earthquake deduced from dense global navigation satellite system network and interferometric synthetic aperture radar data: effect of assumed dip angle Taisuke Yamada, Yusaku Ohta, Takuya Nishimura, Keisuke Yoshida, Yoshihiro Hiramatsu, et al. Earth Planets and Space, 2025 The Mw 7.5 Noto Peninsula earthquake, which occurred on January 1, 2024, was considerably hazardous to the peninsula and surrounding regions owing to a strong motion, large-scale crustal deformation, and subsequent tsunami. Significant surface displacement was observed by the dense global navigation satellite system (GNSS) stations, including universities and SoftBank corporation sites, and synthetic aperture radar (SAR). To estimate reliable coseismic slip distribution and its uncertainties for this event, we used the dense GNSS and the line-of-sight displacements from the SAR based on the Bayesian optimization framework. Considering the listric fault structure of this source fault, we validated the fault dip angles using the grid-search approach in the slip estimation. The acquired models indicated reverse fault motion, including a right-lateral slip component, and two slip peaks were estimated in the eastern and western regions of the fault in the central peninsula, independent of the assumed dip angles. These locations correspond to regions of significant uplift and westward displacement. The dip angle assumption affects the horizontal and vertical component of the calculated displacements: a higher dip angle model (≥ 45°) well reproduces vertical components of GNSS and synthetic aperture radar displacements, whereas a lower dip angle model (< 45°) well reproduces horizontal displacements. Overall, a fault dip of 45° is plausible, although it is not consistent with the listric structure suggested by the seismic reflection survey and the aftershock distribution below the central part of the peninsula. To test such a listric fault model, we conducted a coseismic slip estimation assuming a relatively high (60°) and low (25°) dip angles for the shallow and deep sections of the fault, respectively. Even in this case, we acquired a slip model similar to that of a plain fault, which reasonably reproduced each component of the surface displacements as well as the simple plane fault models. These results suggest that listric geometry is also acceptable for the source faults of this event, although the flat geometry similarly explains the observations. Graphical Abstract
A possibility of fluid migration due to the 2023 M6.5 Noto Peninsula earthquake suggested from precise gravity measurements Yoshiyuki Tanaka, Ryuichi Nishiyama, Akito Araya, Hiromu Sakaue, Kazuma Nakakoji, et al. Earth Planets and Space, 2025 The Noto Peninsula has experienced seismic swarms accompanied by transient crustal deformation since November 2020, followed by two major earthquakes (M6.5 on May 5, 2023, and M7.6 on Jan. 1, 2024). Previous studies have suggested that fluids are involved in a series of activities. Most evidence on fluids constrains only their existence, and quantitative information on dynamic fluid migration remains scarce. Past precise gravity measurements in volcanic areas captured changes at the μGal scale (10–8 m/s2) due to magma movement. Here, we report the gravity difference caused by the M6.5 earthquake that was obtained via a similar method of measurement. Most of the observed gravity change can be explained by a fault slip model determined from the geodetic inversion of GNSS data. However, a significant change of approximately 10 μGal remains unexplainable in the northern coastal area of the northeastern tip of the Noto Peninsula. To explain this change, we estimate environmental effects, such as groundwater and sea-level variations. These environmental effects are too small to fully explain the change unless large local groundwater changes that are not represented in the groundwater model are considered. Instead, adding a fluid-fed fault that opens above the coseismic fault could reasonably explain both the GNSS and gravity data. The inferred volume of fluids is approximately 10% of the volume to have accumulated in a deeper fault by June 2022, as estimated from GNSS data. This result suggests that fluids migrating to shallower areas may have increased the risk of the M7.6 earthquake. The relatively shallow seismic velocity anomalies inferred by seismic tomography might indicate that such an upward migration process due to large earthquakes has been repeated in the past. Graphical Abstract
Linking the spatiotemporal distribution of static stress drops to source faults in a fluid-driven earthquake swarm, northeastern Noto Peninsula, central Japan Mitsuteru Fukuoka, Yoshihiro Hiramatsu, Takuji Yamada Earth Planets and Space, 2024 We investigated stress drops during an earthquake swarm in northeastern Noto Peninsula, central Japan, which is characterized by ongoing seismic activity in four clusters. We focused on the spatiotemporal distribution of the static stress drop and its relationship with the source faults of the earthquake swarm. Employing the empirical Green’s function method, we estimated static stress drops for 90 earthquakes of MJMA 3.0–5.4. We obtained logarithmic mean stress drops of 13 MPa and 19 MPa from P-wave and S-wave analyses, respectively, which were typical values for crustal earthquakes. We comprehensively analyzed the spatiotemporal distribution of static stress drops in the northern cluster due to the abundance of available data and clarity of fault structures there. We observed larger static stress drops for earthquakes along shallow portions of the source faults, as defined by the hypocentral distribution during a given period. Conversely, we observed smaller static stress drops for earthquakes at medial parts along the faults. These results suggest higher fault strength at shallower parts along the faults and reduced fault strength at medial parts. We attribute the high fault strength at shallow parts to low pore fluid pressure after only limited fluid diffusion near the fault terminus. In contrast, we attribute the reduction in fault strength at medial parts to high pore fluid pressure within the fault following penetration by migrating fluids. Graphical Abstract
The role of fluids in earthquake swarms in northeastern Noto Peninsula, central Japan: insights from source mechanisms Sayaka Takano, Yoshihiro Hiramatsu, Yohei Yukutake Earth Planets and Space, 2024 A prolonged earthquake swarm has persisted since June 2018 in northeastern Noto Peninsula (central Japan), with activity focused into distinct southern, western, northern, and eastern clusters. To explore the role of fluids in the occurrence of this swarm, we analyzed the focal mechanisms of the earthquakes occurring from 1 January 2018 to 30 November 2022 and performed stress tensor inversions. The western, northern, and eastern clusters were dominated by a reverse fault-type mechanism with a horizontal P-axis oriented NW–SE. One of the nodal planes of those mechanisms aligns closely with the precisely relocated hypocenter distribution. The stress fields in these three clusters, as determined by stress tensor inversion, have maximum principal stresses oriented horizontally in the NW–SE direction and minimum principal stresses oriented vertically, aligning with the regional stress field. From these focal mechanisms and this stress field, we derived small misfit angles and large slip tendencies. These findings suggest that, in these three clusters, fluids diffused into faults largely aligned with the regional stress field, resulting in earthquakes with compatible focal mechanisms. Conversely, normal and strike-slip fault-type focal mechanisms, which are unfavorable to the regional stress field, dominated in the southern cluster. The estimated stress fields, deviating from the regional stress field, have maximum principal stresses closer to vertical and minimum principal stress oriented horizontally in the ENE–WSW direction. For earthquakes deeper than 15 km, this local stress field results in relatively larger misfit angles and lower slip tendency than the other clusters. These results suggest that those earthquakes in the southern cluster occurred on misoriented fault planes due to elevated pore fluid pressures. These findings provide strong evidence of the ascent of high-pore-pressure fluids from depth in the southern cluster and their subsequent diffusion into a southeast-dipping fault zone. Graphical Abstract
Automated hypocenter determination of tectonic tremors in the Nankai subduction zone using convolutional neural networks combined with semblance analysis Amane Sugii, Yoshihiro Hiramatsu, Takahiko Uchide, Kazutoshi Imanishi Earth Planets and Space, 2024 Recent advances in deep learning have enhanced our ability to analyze seismic waveforms. Here, we developed and evaluated a convolutional neural network (CNN) model to classify tectonic tremors, earthquakes, and noise in seismic waveform data recorded by a seismic array in the Nankai subduction zone. The trained CNN model achieved high accuracy, with both precision and recall exceeding 97%, and correctly detected 96% of distant earthquakes. The probability of tectonic tremor as a function of the signal-to-noise ratio (SNR) increased steeply from 10 to 90% at an SNR of 4. We highlighted tectonic tremor waveforms using the integrated gradients (IG) method for interpreting CNN models. IG filter averaging over the stations of an array outperforms bandpass filters and other interpretation methods for CNN models in locating tectonic tremors by semblance analysis, providing the largest number of tectonic tremor sources. As reported previously, located sources of tectonic tremor during episodic tremor and slip events migrate along the strike of the subducting plate. The source location error increases significantly at epicentral distances greater than 30 km because of low SNRs. The technique developed in this study equips CNN models with a high ability to distinguish tectonic tremors and earthquakes from noise and to locate tectonic tremors with sources that are not far from seismic stations. Graphical abstract
Shear wave splitting and seismic velocity structure in the focal area of the earthquake swarm and their relation with earthquake swarm activity in the Noto Peninsula, central Japan Tomomi Okada, Martha K. Savage, Shin’ichi Sakai, Keisuke Yoshida, Naoki Uchida, et al. Earth Planets and Space, 2024 Seismic activity in the Noto region of Ishikawa Prefecture, central Japan, has increased since August 2020 and has continued as of August 2023. Stress changes due to subsurface sources and increases in fluid pressure have been discussed as the causes of the seismic activity increase. In this study, S-wave polarization anisotropy was investigated by S-wave splitting analysis using temporary and permanent stations located in the epicenter area. We also investigated the seismic wave velocity structure in the source region by analyzing seismic wave velocity tomography. The fast orientations of anisotropy (fast shear wave oscillation direction, FSOD) were generally NW–SE in the southern part of the focal area and east–west in the northern part. The NW–SE anisotropy generally coincides with the direction of the maximum horizontal compression axis, both near the surface and at earthquake depths. Therefore, stress-induced anisotropy can be the cause of the observed NW–SE anisotropy. On the other hand, faults with strike directions generally east–west have been identified, and structural anisotropy may be the cause of the observed east–west anisotropy. We examined the time variation of anisotropy at N.SUZH, one of the permanent stations. No significant time variation was observed in the FSOD. Larger anisotropy was observed, particularly for the activity in the western part of the focal area, from about June–September 2021 compared to the previous period. A high Vp/Vs region was identified beneath the focal area, at a depth of 18 km. This high Vp/Vs region has slightly larger P-wave velocities than the surrounding area. Since Tertiary igneous rocks are distributed in the target area, the high Vp/Vs region may represent a Tertiary magma reservoir, suggesting that fluids released through the old magma reservoir are involved in this seismic swarm. This seismic activity started in the southern part of the area, where relatively immature fault structure exists, where stress-induced anisotropy is distributed, and where high Vp/Vs regions suggestive of fluid at depth are identified. Subsequently, seismicity became more active in the northern part, where structural anisotropy with well-developed fault structures is distributed. Graphical Abstract
Role of a Hidden Fault in the Early Process of the 2024 Mw7.5 Noto Peninsula Earthquake Keisuke Yoshida, Ryota Takagi, Yo Fukushima, Ryosuke Ando, Yusaku Ohta, et al. Geophysical Research Letters, 2024 The 2024 Mw 7.5 Noto Peninsula, Japan, earthquake was initiated within the source region of intense swarm activity. To reveal the mainshock early process, we relocated the earthquake hypocenters and found that many key phenomena, including the mainshock initiation, foreshocks, swarm earthquakes, and deep aseismic slip, occurred at parts of a previously unrecognized fault in intricate fault network. This fault is subparallel (several kilometers deeper) to a known active fault, and the mainshock initiation and foreshocks occurred at the front of a 2‐year westward swarm migration. The initiation location coincides with the destination of the upward migration of a deeper earthquake cluster via several smaller faults. Fluid supply, small earthquakes, and aseismic slip on the fault likely triggered the mainshock, leading to the first major rupture at the western region, propagating further to the west and east sides, resulting in an Mw7.5 event, exceeding 100 km in length.
Analysis of topographic characteristics of ancient dunes and old fans using a DEM based on aerial photographs of the Western Coast of the Noto Peninsula in Central Japan Chikei Transactions Japanese Geomorphological Union, 2014
Detection of landslide displacement at the hakusan volcano from interferometric analysis of ALOS/PALSAR data Journal of the Geodetic Society of Japan, 2010
Helium isotope anomaly in groundwater prior to the 2024 Noto Peninsula earthquake T Kagoshima, Y Sano, N Takahata, Y Kawamoto, T Shibata, Y Li, ... Nature Communications 16 (1), 10414 , 2025 2025
Enhanced deep learning approach for detecting and locating tectonic tremors in the Nankai subduction zone Y Jinde, A Sugii, Y Hiramatsu Earth, Planets and Space 77 (1), 121 , 2025 2025 Citations: 1
A possibility of fluid migration due to the 2023 M6. 5 Noto Peninsula earthquake suggested from precise gravity measurements Y Tanaka, R Nishiyama, A Araya, H Sakaue, K Nakakoji, T Takata, ... Earth, Planets and Space 77 (1), 32 , 2025 2025 Citations: 8
Coseismic slip distribution of the 2024 Noto Peninsula earthquake deduced from dense global navigation satellite system network and interferometric synthetic aperture radar … T Yamada, Y Ohta, T Nishimura, K Yoshida, Y Hiramatsu, Y Kinoshita Earth, Planets and Space 77 (1), 19 , 2025 2025 Citations: 20
Automated hypocenter determination of tectonic tremors in the Nankai subduction zone using convolutional neural networks combined with semblance analysis A Sugii, Y Hiramatsu, T Uchide, K Imanishi Earth, Planets and Space 76 (1), 179 , 2024 2024 Citations: 4
The role of fluids in earthquake swarms in northeastern Noto Peninsula, central Japan: insights from source mechanisms S Takano, Y Hiramatsu, Y Yukutake Earth, Planets and Space 76 (1), 151 , 2024 2024 Citations: 8
Linking the spatiotemporal distribution of static stress drops to source faults in a fluid-driven earthquake swarm, northeastern Noto Peninsula, central Japan M Fukuoka, Y Hiramatsu, T Yamada Earth, Planets and Space 76 (1), 125 , 2024 2024 Citations: 3
Role of a Hidden Fault in the Early Process of the 2024 M w 7.5 Noto Peninsula Earthquake K Yoshida, R Takagi, Y Fukushima, R Ando, Y Ohta, Y Hiramatsu Geophysical Research Letters 51 (16), e2024GL110993 , 2024 2024 Citations: 45
Shear wave splitting and seismic velocity structure in the focal area of the earthquake swarm and their relation with earthquake swarm activity in the Noto Peninsula, central Japan T Okada, MK Savage, S Sakai, K Yoshida, N Uchida, R Takagi, S Kimura, ... Earth, Planets and Space 76 (1), 24 , 2024 2024 Citations: 16
Episodic transient deformation revealed by the analysis of multiple GNSS networks in the Noto Peninsula, central Japan T Nishimura, Y Hiramatsu, Y Ohta Scientific Reports 13 (1), 8381 , 2023 2023 Citations: 105
Long‐living earthquake swarm and intermittent seismicity in the northeastern tip of the Noto Peninsula, Japan Y Amezawa, Y Hiramatsu, A Miyakawa, K Imanishi, M Otsubo Geophysical Research Letters 50 (8), e2022GL102670 , 2023 2023 Citations: 82
Gravity gradient tensor analysis and its application to the Eastern Boundary Fault Zone of the Shonai Plain, Northeastern Japan T Tanaka, Y Hiramatsu, R Honda, A Sawada, S Okada Exploration Geophysics 53 (4), 455-467 , 2022 2022 Citations: 1
The scientific observation campaign of the Hayabusa-2 capsule re-entry EK Sansom, HAR Devillepoix, M Yamamoto, S Abe, S Nozawa, ... Publications of the Astronomical Society of Japan 74 (1), 50-63 , 2022 2022 Citations: 21
Mineralogy, chronology and formation process of the epithermal gold–silver vein deposits in the historical Togi mine, Noto Peninsula, Japan M Hamada, W Kobayashi, Y Hiramatsu, N Hasebe Resource geology 72 (1), e12294 , 2022 2022 Citations: 5
Variations in the Characteristic Amplitude of Tectonic Tremor Induced by Long‐Term Slow Slip Events K Nakamoto, Y Hiramatsu, T Matsuzawa, T Mizukami Journal of Geophysical Research: Solid Earth 126 (5), e2020JB021138 , 2021 2021 Citations: 1
Cascading rupture of patches of high seismic energy release controls the growth process of episodic tremor and slip events K Nakamoto, Y Hiramatsu, T Uchide, K Imanishi Earth, Planets and Space 73 (1), 59 , 2021 2021 Citations: 13
Cascading rupture of patches of high seismic energy release controls the growth process of episodic tremor and slip events N Keita, H Yoshihiro, U Takahiko, I Kazutoshi Earth, Planets and Space (Online) 73 (1) , 2021 2021 Citations: 1
Temporal variation in seismic moment release rate of slow slips inferred from deep low-frequency tremors in the Nankai subduction zone Y Kono, K Nakamoto, Y Hiramatsu Earth, Planets and Space 72 (1), 12 , 2020 2020 Citations: 5
Gravity gradient tensor analysis to an active fault: a case study at the Togi-gawa Nangan fault, Noto Peninsula, central Japan Y Hiramatsu, A Sawada, W Kobayashi, S Ishida, M Hamada Earth, Planets and Space 71 (1), 1-8 , 2019 2019 Citations: 24
Temporal stability of coda Q in the northeastern part of an inland high strain rate zone, central Japan: implication of a persistent ductile deformation in the crust M Dojo, Y Hiramatsu Earth, Planets and Space 71 (1), 32 , 2019 2019 Citations: 5
MOST CITED SCHOLAR PUBLICATIONS
Episodic transient deformation revealed by the analysis of multiple GNSS networks in the Noto Peninsula, central Japan T Nishimura, Y Hiramatsu, Y Ohta Scientific Reports 13 (1), 8381 , 2023 2023 Citations: 105
Long‐living earthquake swarm and intermittent seismicity in the northeastern tip of the Noto Peninsula, Japan Y Amezawa, Y Hiramatsu, A Miyakawa, K Imanishi, M Otsubo Geophysical Research Letters 50 (8), e2022GL102670 , 2023 2023 Citations: 82
Scaling law between corner frequency and seismic moment of microearthquakes: Is the breakdown of the cube law a nature of earthquakes? Y Hiramatsu, H Yamanaka, K Tadokoro, K Nishigami, S Ohmi Geophysical Research Letters 29 (8), 52-1-52-4 , 2002 2002 Citations: 66
Detailed mapping of focal mechanisms in/around the 1995 Hyogo-ken Nanbu earthquake rupture zone H Katao, N Maeda, Y Hiramatsu, Y Iio, S Nakao Journal of Physics of the Earth 45 (2), 105-119 , 1997 1997 Citations: 65
Seismological evidence on characteristic time of crack healing in the shallow crust Y Hiramatsu, H Honma, A Saiga, M Furumoto, T Ooida Geophysical Research Letters 32 (9) , 2005 2005 Citations: 62
Spatial variation in the crustal anisotropy and its temporal variation associated with a moderate-sized earthquake in the Tokai region, central Japan A Saiga, Y Hiramatsu, T Ooida, K Yamaoka Geophysical Journal International 154 (3), 695-705 , 2003 2003 Citations: 59
Temporal changes in coda Q −1 and b value due to the static stress change associated with the 1995 Hyogo‐ken Nanbu earthquake Y Hiramatsu, N Hayashi, M Furumoto, H Katao Journal of Geophysical Research: Solid Earth 105 (B3), 6141-6151 , 2000 2000 Citations: 59
Scaling relationship between the duration and the amplitude of non‐volcanic deep low‐frequency tremors T Watanabe, Y Hiramatsu, K Obara Geophysical research letters 34 (7) , 2007 2007 Citations: 58
Deep low‐frequency tremors as a proxy for slip monitoring at plate interface Y Hiramatsu, T Watanabe, K Obara Geophysical Research Letters 35 (13) , 2008 2008 Citations: 54
Role of a Hidden Fault in the Early Process of the 2024 M w 7.5 Noto Peninsula Earthquake K Yoshida, R Takagi, Y Fukushima, R Ando, Y Ohta, Y Hiramatsu Geophysical Research Letters 51 (16), e2024GL110993 , 2024 2024 Citations: 45
ScS wave splitting of deep earthquakes around Japan Y Hiramatsu, M Ando, Y Ishikawa Geophysical Journal International 128 (2), 409-424 , 1997 1997 Citations: 43
The 1998 Miyako fireball’s trajectory determined from shock wave records of a dense seismic array Y Ishihara, S Tsukada, S Sakai, Y Hiramatsu, M Furumoto Earth, Planets and Space 55 (5), e9-e12 , 2003 2003 Citations: 42
Three‐dimensional image of the anisotropic bodies beneath central Honshu, Japan Y Hiramatsu, M Ando, T Tsukuda, T Ooida Geophysical Journal International 135 (3), 801-816 , 1998 1998 Citations: 41
Detection of acoustic/infrasonic/seismic waves generated by hypersonic re-entry of the HAYABUSA capsule and fragmented parts of the spacecraft M Yamamoto, Y Ishihara, Y Hiramatsu, K Kitamura, M Ueda, Y Shiba, ... Publications of the Astronomical Society of Japan 63 (5), 971-978 , 2011 2011 Citations: 40
Fault model of the 2007 Noto Hanto earthquake estimated from coseismic deformation obtained by the distribution of littoral organisms and GPS: Implication for neotectonics in … Y Hiramatsu, K Moriya, T Kamiya, M Kato, T Nishimura Earth, planets and space 60 (9), 903-913 , 2008 2008 Citations: 40
Two types of antigorite serpentinite controlling heterogeneous slow-slip behaviours of slab–mantle interface T Mizukami, H Yokoyama, Y Hiramatsu, S Arai, H Kawahara, T Nagaya, ... Earth and Planetary Science Letters 401, 148-158 , 2014 2014 Citations: 36
Spatial variation in shear wave splitting of the upper crust in the zone of inland high strain rate, central Japan Y Hiramatsu, K Iwatsuki, S Ueyama, T Iidaka, ... Earth, planets and space 62 (9), 675-684 , 2010 2010 Citations: 35
Infrasound/seismic observation of the Hayabusa reentry: Observations and preliminary results Y Ishihara, Y Hiramatsu, M Yamamoto, M Furumoto, K Fujita Earth, planets and space 64 (7), 655-660 , 2012 2012 Citations: 30
Thick and anisotropic D ″layer beneath Antarctic Ocean Y Usui, Y Hiramatsu, M Furumoto, M Kanao Geophysical Research Letters 32 (13) , 2005 2005 Citations: 28
An overview of JAXA's ground-observation activities for HAYABUSA reentry K Fujita, M Yamamoto, S Abe, Y Ishihara, O Iiyama, Y Kakinami, ... Publications of the Astronomical Society of Japan 63 (5), 961-969 , 2011 2011 Citations: 26
