{"paper":{"title":"DANTE: Physics-Informed Neural Operator for DAS-to-Velocity Waveform Reconstruction Without Co-located Seismometers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Physics-informed neural operator reconstructs particle velocity from DAS strain rate without seismometers","cross_cats":[],"primary_cat":"physics.geo-ph","authors_text":"Isao Kurosawa","submitted_at":"2026-05-18T13:22:12Z","abstract_excerpt":"Distributed Acoustic Sensing (DAS) converts existing fibre-optic cables into dense seismic arrays at near-zero deployment cost, but measures strain rate rather than particle velocity -- the quantity required by virtually all seismological analysis tools. Converting strain rate to particle velocity by numerical integration is ill-posed: the integration constant is undefined and noise accumulates without bound. We present DANTE (DAS-to-velocity via physics-informed neural operator for Acoustic-wave recoNstruction in heTErogeneous media), a Fourier Neural Operator (FNO) trained entirely on synthe"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On a test set of 200 heterogeneous synthetic wavefields, DANTE achieves a mean output SNR of 15.3 ± 8.8 dB, Pearson correlation r = 0.907, and SSIM = 0.976, corresponding to a mean SNR improvement of approximately +15 dB over the best conventional baseline, and up to +28.8 dB on the most challenging samples. Zero-shot inference on seven real microseismic events yields a kinematic residual of 0.003–0.005.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that enforcing the exact kinematic relation between DAS strain rate and the spatial gradient of particle velocity together with the one-dimensional elastic wave equation on synthetic heterogeneous media is sufficient to resolve the undetermined integration constant and suppress noise when the model is applied zero-shot to real field data whose heterogeneity and noise statistics may differ from the training distribution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A physics-informed Fourier Neural Operator reconstructs particle velocity from DAS strain-rate measurements by enforcing kinematic and elastic-wave-equation constraints, yielding 15.3 dB mean SNR on synthetic tests and low kinematic residuals on real Utah FORGE data without fine-tuning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Physics-informed neural operator reconstructs particle velocity from DAS strain rate without seismometers","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"695ddc67d892a6f2708ed5809087b6539057c7b5d75cf00875a2150db6c2524d"},"source":{"id":"2605.18375","kind":"arxiv","version":1},"verdict":{"id":"227477f9-31ed-4ab5-8983-8dc125bc467e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T23:34:11.777289Z","strongest_claim":"On a test set of 200 heterogeneous synthetic wavefields, DANTE achieves a mean output SNR of 15.3 ± 8.8 dB, Pearson correlation r = 0.907, and SSIM = 0.976, corresponding to a mean SNR improvement of approximately +15 dB over the best conventional baseline, and up to +28.8 dB on the most challenging samples. Zero-shot inference on seven real microseismic events yields a kinematic residual of 0.003–0.005.","one_line_summary":"A physics-informed Fourier Neural Operator reconstructs particle velocity from DAS strain-rate measurements by enforcing kinematic and elastic-wave-equation constraints, yielding 15.3 dB mean SNR on synthetic tests and low kinematic residuals on real Utah FORGE data without fine-tuning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that enforcing the exact kinematic relation between DAS strain rate and the spatial gradient of particle velocity together with the one-dimensional elastic wave equation on synthetic heterogeneous media is sufficient to resolve the undetermined integration constant and suppress noise when the model is applied zero-shot to real field data whose heterogeneity and noise statistics may differ from the training distribution.","pith_extraction_headline":"Physics-informed neural operator reconstructs particle velocity from DAS strain rate without seismometers"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.18375/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-20T00:01:20.363144Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T23:50:05.560900Z","status":"completed","version":"0.1.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T23:40:55.552428Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:30.004087Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T23:31:48.138341Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.769480Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"020569aa4973613ce538b4ca8c756054728b3e047335b443b38c8798f345f624"},"references":{"count":14,"sample":[{"doi":"","year":null,"title":"International Conference on Learning Representations , year =","work_id":"9e007f1f-858e-4891-bc51-b76ce8f0779d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Physics-informed neural networks:","work_id":"54c9d857-fbca-4c6d-a6ba-6e28208752dd","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Seismological Research Letters , volume =","work_id":"32eebb32-8a2b-45e3-a181-4281b7addc05","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Ultrastable laser interferometry for earthquake detection with terrestrial and submarine cables , journal =","work_id":"1287dbe9-b1c4-4a48-9239-c5d2e043318c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Annual Review of Earth and Planetary Sciences , volume =","work_id":"67d2376c-66d1-4da0-ae42-89d0928346a0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":14,"snapshot_sha256":"e451fe86b3f467554e16b7f50254bba3302262a710dd16191232fa77b3f11652","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}