EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Deep Learning-Based Denoising Method for Airborne Electromagnetic Data

Yuhang Li iD, Chong Zhang iD, Wei Huang iD, Qingtian Lü iD

Sensors · 06.11.2026 · 26 (21) · 7021

DOI: 10.3390/s26217021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.11.2026. Verfasst von Yuhang Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Deep Earth and Mineral Exploration, Chinese Academy of Geological Sciences, Beijing 100037, China. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Natural Resources, Chinese Academy of Geological Sciences, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Airborne electromagnetic (AEM) measurements are vulnerable to mixed environmental noise, and rapid signal decay hampers weak transient recovery. We propose WL-CNN-BiLSTM, integrating dual-stage wavelet filtering, parallel multi-scale convolutions, residual skip connections, bidirectional recurrent units, and a hybrid reconstruction objective for complex TEM waveforms. On the archived 20,000-trace benchmark’s 3000-trace test subset, it achieved an aggregate physical-domain SNR 17.53 dB (RMSE 1.48 × 10−10 T; PCC 0.989), versus 11.49 dB for PC-BiLSTMNet, 11.76 dB for validation-selected Median filtering, and 13.04 dB for VMD; the per-trace SNR P10 was −3.41 dB (minimum −25.45 dB). These archived results characterize stored numerical targets, not independently verified AEM responses. On an independent 1000-trace blind test, a separately trained layered-earth configuration using training-only scalers achieved a median SNR of 5.91 dB versus 0.39 dB (Median) and −0.05 dB (VMD), but poorer lower-tail SNR (P10 −43.93 dB) and a median of NRMSE 7.402 over 101–1001 μs. Proprietary iFTEM-II windows showed waveform changes versus the engineering curve, but unavailable proxy provenance/calibration made this qualitative evidence, not field-accuracy validation. A matched p = 0 comparison, three-seed ablations, complete training-only-scaler retraining, and out-of-distribution diagnostics delineate distributional dependencies; temporal feature weighting is an implemented design component, not a demonstrated late-time enhancer. It shows aggregate reconstruction gains within the benchmark and characterizes dataset- and protocol-dependent limitations.

Schlagwörter

Stichwörter der Autor:innen

airborne electromagnetic datadeep learningdenoisingsignal reconstructionsignal-to-noise ratiotransient electromagnetic

Autor:innen und Institutionen

  • State Key Laboratory of Deep Earth and Mineral Exploration, Chinese Academy of Geological Sciences, Beijing 100037, China.
  • Institute of Geophysical and Geochemical Exploration, Chinese Academy of Geological Sciences, Tianjin 300309, China.

ORCID-Profile: Yuhang Li, Chong Zhang, Wei Huang, Qingtian Lü

Förderung

  • Ministry of Natural Resources
  • Chinese Academy of Geological Sciences
  • National Natural Science Foundation of China
  • Deep Earth Probe and Mineral Resources Exploration—National Science and Technology Major Project

Zitieren

APA

Li, Y., Zhang, C., Huang, W., & Lü, Q. (2026). A Deep Learning-Based Denoising Method for Airborne Electromagnetic Data. Sensors, 26(21), 7021. https://doi.org/10.3390/s26217021

Vancouver

Li Y, Zhang C, Huang W, Lü Q. A Deep Learning-Based Denoising Method for Airborne Electromagnetic Data. Sensors. 2026;26(21):7021. doi:10.3390/s26217021

BibTeX
@article{Li2026,
  author = {Li, Yuhang and Zhang, Chong and Huang, Wei and Lü, Qingtian},
  title = {A Deep Learning-Based Denoising Method for Airborne Electromagnetic Data},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {7021},
  doi = {10.3390/s26217021}
}
Kostenlos starten →