physics.geo-phMar 22, 2026
SaveTRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology
Organizations: School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China. · Shanghai Artificial Intelligence Laboratory, Shanghai, China. · School of Earth and Space Sciences, University of Science and Technology of China, Hefei, China. · Department of Earth and Planetary Sciences,McGill University, Montreal, Canada. · Department of Earth and Planetary Sciences, Harvard University, Cambridge, United States of America. · Institute of Earthquake Forecasting, China Earthquake Administration, Beijing, China.
Abstract
Modern seismic networks resolve earthquake sequences in unprecedented detail, yet explaining how large earthquakes emerge from evolving fault systems remains difficult. We introduce TRACE, a seismology-guided artificial intelligence agent that plans and executes workflows while preserving auditable evidence chains from observations to physical interpretation. We evaluated TRACE through 104 benchmark tasks and two complementary earthquake sequences. For the well-studied 2019 Ridgecrest sequence, TRACE constructed a high-resolution catalog from continuous waveforms and retrospectively recovered delayed cascading activation between the Mw 6.4 and Mw 7.1 earthquakes without a prescribed target interpretation. In the less-understood 2025-2026 Sanriku sequence off northeastern Japan, TRACE developed a testable interpretation of progressive destabilization within a segmented megathrust. Its synthesis linked coupled seismic-aseismic activation around the MJ 6.9 sequence and subsequent persistent, spatially segmented shallow-interface activity to a megathrust patch that lay between regions of past large coseismic slip and later hosted the MJ 7.7 rupture. These results open a path from seismic observations to testable physical insight.
Figures & tables
Figure 1 : TRACE framework for constrained workflow execution and physical interpretation. a , Seismic observations and case-specific geophysical inputs available to TRACE, including station metadata, waveform records, event catalogs, phase-arrival records, fault geometry and velocity models. These inputs define the observational and physical boundary conditions for subsequent analysis. b , Constrained workflow execution. TRACE links waveform preprocessing, event detection and phase picking, association, location and relocation, and seismicity diagnostics through diagnostic checks of intermediate products. Depending on input availability, workflows may enter at different stages. c , Evidence synthesis and physical interpretation. The evidence matrix summarizes qualitative support for candidate interpretations derived from the scientific question and analysis outputs; the lower schematic shows the best-supported interpretation and targets for further validation. d , The coordinated agent layer supports hypothesis planning, workflow execution, diagnostic checking, interpretation evaluation and synthesis. The TRACE record retains data sources, code versions, parameter settings, run metadata and audit logs. Miniature panels illustrate representative inputs, workflow products and evidence domains; quantitative application results are shown in subsequent figures.
Figure 2 : TRACE construction of a reviewable Ridgecrest earthquake catalog workflow. TRACE converts waveform records and task constraints into a documented catalog-building workflow whose data selections, processing parameters, phase picks, associated events, initial locations, local-magnitude estimates and relocation outputs can be inspected. The 2019 Ridgecrest sequence is shown as a worked example: TRACE plans a six-step route and executes waveform acquisition, preprocessing, PhaseNet phase picking, GaMMA association, initial location, and HypoDD-based relocation. Summary cards report 47 stations selected for waveform processing, of which the 30 nearest to the 6.4 epicenter were retained for association and relocation; 34 GiB of requested waveforms; approximately 1.45 million picks and 1.64 million picks; 140,505 associated events with initial locations; 84,474 relocated events; and 4,714 events between the 6.4 and 7.1 earthquakes. These catalog and provenance records provide the observational basis for evaluating triggering pathways from the 6.4 foreshock to the 7.1 mainshock.
Figure 3 : Evidence for delayed cascading activation between the Ridgecrest 6.4 foreshock and 7.1 mainshock. a , Seismicity over 34 h in three windows (0–4, 4–18 and 18–33.8 h) after the foreshock, with mapped SW-NE- and NW-SE-trending surface-rupture traces [ 18 ] , the 5.4 analytical separator and inferred activation direction toward the NW-SE fault family. Pale blue and red corridors define domains in c,d ; darker dashed outlines mark the two 5 km comparison regions in e . b , Distances to the nearest mapped surface-rupture trace and directional spectrum; reference directions mark the dominant fault-family orientations, and vertical dashed lines mark 1 and 2 km. c , Hourly seismicity rates in the foreshock- and mainshock-side corridors; shading marks the separator interval. d , Grid-cell activation onset times in the same corridors; horizontal bars denote medians. e , Fixed-window -values for the foreshock and mainshock comparison regions before and after the separator and over the full interval. Error bars denote standard uncertainties, event counts and the gray band the regional background range. f , Qualitative evidence-weighting matrix comparing delayed cascading activation with dynamic triggering, ordinary aftershock decay and a coherent migration front; cells summarize diagnostic consistency and do not represent an independent statistical test.
Figure 4 : Persistent shallow-interface activation before the 2026 Sanriku 7.7 earthquake. The physical synthesis links stage-resolved seismicity, the focused shallow-interface geometry and neighboring historical large-slip regions. a–e , Five-stage evolution of relocated seismicity, from background activity through the November 2025 6.9 compound burst, sustained shallow-interface activation, pre- 7.7 intensification and the 7.7 locked-asperity failure. Dashed outlines mark the 6.9 source region, the broader shallow activation zone and the historically bounded 7.7 patch. The central timeline summarizes the transition from distributed activity around the 6.9 source to the 7.7 rupture. f , Along-profile distance-depth projection of the focused shallow-interface region. The 6.9 and 7.7 reference locations are separated by 57 km, and earthquakes persist in spatially separated patches across the focused profile rather than forming a continuous migration front. g , Three-dimensional synthesis of short-term activation and historical rupture geometry. Historical rupture contours mark neighboring regions of large coseismic slip, whereas the focused shallow-interface region occupies a patch bracketed by these regions, with the later 7.7 rupture occurring within the same bounded patch.
Figure 5 : Seismicity-rate, magnitude–frequency and repeating-earthquake evidence for Sanriku shallow-interface activation. a , Relocated catalog colored by depth in the focused Sanriku region. Stars mark the 6.9 and 7.7 earthquakes (red) and the regional 7.5 earthquake (blue). Contours show the 2011 9.0 Tohoku-Oki high-slip region [ 16 ] and the 1994 7.7 Sanriku-Oki and 1968 Tokachi-Oki (approximately 8.3) ruptures [ 24 ] . The inset shows events along the 57-km shallow-interface profile. b , Magnitude-time plots for the November 2025 6.9, December 2025 regional 7.5 and April 2026 7.7 sequences, each aligned to its largest-event origin time. Colors denote 0–30, 30–60 and 60–100 km epicentral-distance bins; diamonds mark events. c , Long-term seismicity rate, cumulative event count, -value and magnitude of completeness. Lines mark the 6.9 and 7.7 events; shading shows uncertainty in -value estimates. d , Repeating-earthquake candidates and high-correlation families near the 6.9 source. Hulls enclose seismicity during the final 2 days before and first 0.5 days after the event; contours show historical coseismic slip. Colors indicate family thresholds; CC, cross-correlation. e , Repeating-family timeline ordered by first event; points denote events, segments family durations and the dashed line the 6.9 origin time. f , Representative waveforms from family F063. Colors denote the two events; vertical lines mark and picks. Labels give station-component cross-correlation and time shift; the title gives the network-median CC.
Figure S1 : Technical architecture and evidence-chain synthesis of TRACE. a , Multi-agent architecture used to convert a seismological request and optional literature or contextual input into candidate plans, executable workflows, scripts, checked data products and a physical interpretation report. Planning, workflow, coding, result-checking, analysis and cross-perspective synthesis agents query the Expert-Validated Case Library, Structured Knowledge Library and Validated Scientific Tools Library. Dashed links distinguish knowledge and case retrieval from tool retrieval and execution. Optional human supervision and expert validation constrain ambiguous task boundaries and return reviewed workflows and summaries to the case library. b , Evidence-chain synthesis used by the Scientific Integration and Inference Module. Checked workflow outputs are converted into perspective-specific evidence summaries, integrated across evidence streams and assembled into a physical interpretation report containing an evidence-supported interpretation, viable alternatives, external validation targets and a trace record.
| Levels | Description | Number of Tasks |
| Level 1: Atomic task capability | Performs fundamental seismological operations with procedural correctness and execution stability, including seismic data acquisition, format conversion, preprocessing, signal feature extraction, and scientific visualization. Emphasizes accurate tool invocation, parameter handling, and computational consistency in routine seismic data processing workflows. | 74 |
| Level 2: Multi-step analytical capability | Solves workflow-level seismological problems requiring coordinated multi-tool orchestration and dependency management. Integrates sequential toolchains, heuristic branching strategies, large-scale batch scanning, and parameter-space exploration under physical constraints. Evaluates adaptive pathway selection, intermediate state management, and long-chain analytical coherence. | 30 |
| Level 3: Integrated scientific analysis capability | Conducts end-to-end scientific investigations under realistic research scenarios. Integrates cross-module data processing, multi-perspective analysis, hypothesis formulation, and evidence synthesis to assemble evidence-supported, testable interpretations. Assesses workflow coherence, cross-task integration, and interpretation boundaries in complex seismological studies. | 2 |
Table S1 : Task-complexity levels and representative TRACE capabilities in the seismological evaluation framework.
| Score | Quantitative Accuracy | Scientific Correctness | Visualization and Reporting Quality |
| 5 points | Numerical outputs match reference solutions within predefined numerical tolerances. | All results are scientifically valid, logically consistent, and fully aligned with task objectives. No conceptual or methodological errors. | Figures are accurate, clearly labeled (axes, units, scales), and publication-ready. Visual design enhances interpretability. Text and figures are fully consistent. |
| 4 points | Minor numerical deviations from reference results but within acceptable tolerance. No impact on overall conclusions. | Results are scientifically correct with only minor interpretative omissions or limited analytical depth. | Figures are correct and interpretable, but minor issues exist (e.g., formatting inconsistencies, limited annotations). Overall presentation is clear. |
| 3 points | Moderate deviation from reference values, but core trends or magnitudes remain correct. | Partial correctness: main scientific conclusion is identifiable, but secondary errors or incomplete interpretation exist. | Figures are understandable but contain noticeable labeling issues, limited clarity, or insufficient explanation. |
| 2 points | Significant numerical errors or unstable results that affect reliability. | Results contain conceptual misunderstandings or incorrect scientific interpretations. | Figures are poorly constructed or partially incorrect, limiting interpretability. |
| 1 point | Numerical results are incorrect or fail to match reference benchmarks. | Scientific conclusions are invalid or inconsistent with task requirements. | No meaningful figures or coherent result presentation provided. |
Table S2 : Five-point criteria for qualitative Level 1 and Level 2 benchmark outputs.
| Provenance layer | Information retained | Audit function |
| Input boundary | Scientific question; data sources; spatial and temporal selections; permitted contextual information; stage at which external evidence entered | Establishes what information was available at each stage |
| Planning | Physical constraints; candidate physical interpretations; selected and retained analysis branches | Links the scientific question to the analyses without prescribing a conclusion |
| Execution | Tool choices; executable scripts; parameter settings; input–output paths; intermediate products | Reconstructs the computational path from observations to analytical products |
| Diagnostics and revision | Computational and physical checks; failed steps; diagnostic flags; permitted revisions; intervention status and source, when applicable | Distinguishes accepted outputs from unresolved failures and records how the workflow changed |
| Evidence extraction | Source data product; method and parameters; diagnostic status; interpretation-relevant observation | Links each evidence statement to a checked analytical output |
| Synthesis | Supporting, inconsistent or unresolved relations; evidence-supported interpretation; viable alternatives; external validation targets | Links the physical interpretation to the evidence while preserving its boundaries |
Table S3 : Core fields in the curated TRACE provenance record. Each workflow layer retains the information needed to trace a physical interpretation back to its observational and computational basis.
| Benchmark group | Benchmark category | Capability tested | Operation pattern | Tasks (n) |
| L1-A | Data access and retrieval | Data retrieval | Single-step | 7 |
| L1-B | Data representation and formatting | Data formatting | Single-step | 12 |
| L1-C | Signal processing | Signal processing | Single-step | 22 |
| L1-D | Statistics and feature extraction | Statistical feature extraction | Single-step | 18 |
| L1-E | Scientific visualization | Scientific plotting | Single-step | 15 |
| Level 1 subtotal | 74 | |||
Table S4 : Coverage of Level 1 and Level 2 benchmark tasks. Counts are grouped by benchmark group, tested capability and operation pattern.
| Task ID | Benchmark category | Representative task | Operation pattern | Complexity |
| L1-A-1 | Data access and retrieval | Download an event catalog from an FDSN server | Single-step | Low |
| L1-B-1 | Data representation and formatting | Convert ASCII waveform data to MiniSEED | Single-step | Low |
| L1-C-1 | Signal processing | Apply an AIC picker to a seismic trace | Single-step | Low |
| L1-D-1 | Statistics and feature extraction | Compute an array response function | Single-step | Low |
| L1-E-1 | Scientific visualization | Plot a focal-mechanism beachball from a QuakeML event | Single-step | Low |
| L2-A-1 | Sequential chaining | Estimate back azimuth from STEAD waveforms using BazNet | Multi-step | Medium |
Table S5 : Representative Level 1 and Level 2 benchmark tasks. One task is shown for each benchmark category.
| Model | Model–task runs | Success rate | Statistical analysis rating | Visualization rating | Mean correction rounds | Mean score |
| Claude Sonnet 4 | 104 | 98.08% | 4.49 | 4.88 | 2.28 | 4.79 |
| Gemini 3 Flash preview | 104 | 100.00% | 4.64 | 4.86 | 2.26 | 4.82 |
| GPT-5.1 | 104 | 100.00% | 4.72 | 4.83 | 1.64 | 4.85 |
Table S6 : Model-level results for the Level 1 and Level 2 benchmark. Each backbone contributed 104 model–task runs. Ratings and mean scores are reported on a five-point scale. Statistical-analysis and visualization ratings were calculated only when the corresponding component formed part of a task’s predefined output requirements.
| Task ID | Case study | Scientific question | Workflow inputs and information boundary | Required report |
| L3-001 | Ridgecrest | How was seismicity organized between the 6.4 foreshock and the 7.1 mainshock? | Initial observations: continuous waveforms and station metadata; auxiliary geospatial data: mapped surface-rupture traces; quality control and alignment: reference catalogs | Evidence-supported physical interpretation and viable alternatives, followed by retrospective comparison with published interpretations after the analysis was complete |
| L3-002 | Sanriku | What evidence constrains shallow-interface activation before the April 2026 7.7 rupture? | Initial observations: JMA event catalog and phase-arrival records; analysis-stage data: event waveforms for repeating-earthquake analysis; synthesis-stage constraints: historical rupture models and convergence estimates; external validation: independent S-net strain observations | Evidence-supported physical interpretation, viable alternatives and external validation targets |
Table S7 : Integrated Level 3 scientific case-study evaluations. The information boundary distinguishes initial observations from auxiliary, quality-control, synthesis and external-validation inputs.
| Dimension | Assessment criterion | Common failure mode | Assessment evidence |
| Planning | Scientific question decomposed into executable, physically relevant analyses | Missing analysis branch or unsupported assumption | Workflow plan and task decomposition |
| Implementation | Executable scripts and tool calls linked to expected products | Broken execution, unstable parameters or missing quality control | Code, logs and output products |
| Synthesis | Report separates observations from interpretation and records viable alternatives and external validation targets | Overclaiming, unsupported interpretation or unacknowledged uncertainty | Structured report and expert review |
Table S8 : Expert-assessment dimensions for Level 3 case reports. The table defines the review criteria, common failure modes and the records used for assessment.
| Processing output | Count (n) | Workflow use |
| Selected three-component stations | 47 | Waveform processing and phase picking station set |
| Stations used for association and relocation | 30 | Stations nearest to the 6.4 epicenter |
| Quality-controlled station-day waveform inputs | 853 | Waveform inputs retained after station-day quality control |
| arrivals retained after PhaseNet filtering | 1,454,311 | Thresholded PhaseNet picks before 30-station association |
| arrivals retained after PhaseNet filtering | 1,641,210 | Thresholded PhaseNet picks before 30-station association |
| Picks assigned to associated events | 2,120,090 | Event-level picks after station and association filtering |
Table S9 : Processing counts for the Ridgecrest TRACE catalog.
| Stage | Setting | Value |
| Phase picking | PhaseNet probability threshold | ; |
| Phase picking | Waveform sampling rate | 100 Hz |
| Association | Association model | GaMMA Bayesian Gaussian-mixture model |
| Association | DBSCAN pre-clustering | Enabled; km; minimum samples, 3 |
| Association | Oversampling factor | 3 |
| Association | Amplitude term | Not used |
Table S10 : Association and relocation parameters for the Ridgecrest catalog.
| Catalog | Events | Median | Use in TRACE audit | |||
| Ross et al. high-resolution catalog, [ 35 ] | 4,138 | 2,499 | 605 | 111 | 1.15 | High-resolution reference |
| USGS/ANSS ComCat (USGS/CI) [ 45 ] | 3,484 | 2,686 | 704 | 145 | 1.37 | Operational reference |
| TRACE associated catalog before relocation | 6,351 | 3,907 | 817 | 163 | 1.14 | Unrelocated TRACE reference |
| TRACE HypoDD relocated catalog | 4,714 | 3,205 | 734 | 151 | 1.23 | Final catalog used for diagnostic tests |
Table S11 : Reference-catalog comparison for the Ridgecrest 6.4 to 7.1 interval.
Figure S3 : Relocation sharpening for the Ridgecrest 6.4 to 7.1 interval. a , Initial associated events and double-difference relocated events between the 6.4 and 7.1 earthquakes. Blue points show the GaMMA-associated catalog, red points show relocated events, and stars mark the two earthquakes. Relocation retains the principal activation corridor while reducing diffuse scatter away from the corridor. b , Cumulative distribution of absolute cross-profile distance from the activation corridor for the initial and relocated catalogs. The relocated catalog is more concentrated near the corridor. c , Along-profile and cross-profile density distributions for the same events. Relocation preserves the broad along-profile activation pattern while sharpening the cross-profile distribution. These diagnostics evaluate whether the relocated catalog is suitable for the spatial analyses in Supplementary Note 4. They are not used by themselves as evidence for delayed cascading activation.
Figure S4 : Spatial coverage of Ridgecrest reference catalogs and the 6.4 to 7.1 analysis subset. a–c , Full-window spatial distributions for the Ross et al. high-resolution catalog [ 35 ] , the USGS/ANSS ComCat operational catalog [ 45 ] and the TRACE relocated catalog from 4 to 26 July 2019. The black rectangle marks the analysis region between the 6.4 and 7.1 earthquakes, and stars mark their epicenters. Event counts report the number of events shown under the corresponding catalog selection. d–f , Enlarged spatial distributions between the 6.4 and 7.1 origin times. The three catalogs recover the same fault-aligned activation corridor, supporting use of the TRACE relocated catalog for delayed cascading diagnostics.
Figure S5 : Temporal and magnitude consistency of Ridgecrest reference catalogs. a , Full-window time–magnitude distributions for the Ross et al. high-resolution catalog [ 35 ] , the USGS/ANSS ComCat operational catalog [ 45 ] and the TRACE relocated catalog from 4 to 26 July 2019. The yellow and red dashed lines mark the 6.4 and 7.1 origin times, respectively, and the shaded interval marks the analysis window used for delayed cascading diagnostics. Event counts report the full-window catalog selections shown in this panel. b , Cumulative magnitude-frequency distributions for events in the analysis window. c , Event counts above , and in the same window, matching the magnitude thresholds used to compare catalog completeness for the diagnostic analyses. d , Hourly and cumulative event counts after the 6.4 earthquake. Thin lines show hourly counts and thick lines show cumulative counts. These comparisons show that the TRACE relocated catalog preserves the main temporal and magnitude structure of independent catalogs over the interval used for delayed cascading diagnostics.
Figure S6 : Spatiotemporal activation during the Ridgecrest 6.4 to 7.1 interval. a–d , Relocated seismicity in successive time windows after the 6.4 earthquake and over the full interval between the 6.4 and 7.1 earthquakes. The windows contain 550, 1,969, 2,194 and 4,714 events, respectively. Points are colored by time after the 6.4 earthquake; mapped surface-rupture traces [ 18 ] and earthquake locations provide spatial reference. e , Cumulative activation of 1 km grid cells and newly activated cells through time, with the shaded band marking the 5.4 analytical separator. f , Spatial distribution of grid cell activation onset times. g , Distribution of grid cell onset times, with a median of 6.2 h. h , Comparison of onset times between the 6.4 and 7.1 side corridors. i , Time-distance structure in easting and northing components. j , Hourly centroid distance to the 7.1 epicenter and event counts. The panels show delayed, spatially organized activation toward the 7.1 fault system. Timing alone is not used by itself to determine the triggering mechanism.
Figure S7 : Organization of Ridgecrest seismicity near mapped surface ruptures. a,b , Relocated seismicity during the 6.4 to 5.4 and 5.4 to 7.1 intervals, plotted with mapped surface-rupture traces [ 18 ] and the 6.4, 5.4 and 7.1 locations. The windows contain 2,420 and 2,208 events, respectively. c , Cumulative distribution of distance to the nearest mapped surface-rupture trace, with 1 km and 2 km references. d , Directional strength through time, with the SW–NE and NW–SE fault-family directions marked. e , Integrated directional spectrum over the interval between the 6.4 and 7.1 earthquakes, showing enhanced directional strength near 48 ∘ and 128 ∘ . f , Cumulative activation of segments defined from the mapped surface-rupture traces, with new segment activations shown as gray bars. The panels show fault-referenced and directionally organized activation rather than diffuse spatial expansion.
Figure S8 : Fault system seismicity rate and Omori-Utsu diagnostics. a–c , Fault system scale comparison between the two conjugate fault systems associated with the 6.4 and 7.1 ruptures. Panel a maps event assignments to the two fault systems, panel b shows the timing of events with symbol size scaled by magnitude, and panel c compares hourly and cumulative seismicity rates. d–f , North and south partitioning within the 7.1 fault system. Panel d maps the southern and northern sections, panel e shows the timing of events within these sections, and panel f compares their cumulative and hourly counts. g–i , Omori-Utsu diagnostics for the 7.1 fault system. Panel g shows a power-law rate fit for the full 7.1 fault system, with and a 95% confidence interval of 0.67–0.96. Panel h shows cumulative window decay parameter estimates for the full, southern and northern sections. Panel i shows cumulative residuals between observed and expected counts for the southern and northern subsets. These diagnostics indicate heterogeneous seismicity rate evolution within the 7.1 fault system rather than a single spatially uniform aftershock decay.
Figure S9 : -value stress proxy diagnostics for the Ridgecrest 6.4 to 7.1 interval. a , Definition of 5 km comparison regions centered on the 6.4 and 7.1 reference locations. b , Fixed window -value estimates for the two comparison regions before and after the 5.4 separator and over the full interval between the 6.4 and 7.1 earthquakes. The 7.1 estimate before the separator is exploratory because of limited event support, whereas the estimate after the separator remains lower than the 6.4 comparison region ( ) and below the background level over the previous two years. c , Sliding window dynamic -value estimates from 100-event windows. d , Spatial -value field after 5.4, estimated with a 5 km radius and fixed . e , Event support for the spatial -value estimates, shown as the number of events above ; valid nodes require . f , Along-strike -value profile on the 7.1 fault system, with an inset showing radius sensitivity of the comparison region estimates. The results document a relative low stress proxy contrast in the 7.1 comparison region after 5.4, while treating the -value estimate as complementary evidence.