The integration of GPR data at various frequencies, collected with different antennas or with the use of swept-frequency radars opens up interesting perspectives in the study of the subsurface at different resolutions. The proposed methodology is a semi-supervised DL algorithm based on Bi-Directional Long-Short Term Memory to automatically merge varying numbers of data sets at different frequencies. Neural Network training is done directly on the inference data by minimizing a custom loss function based on the L2 norm of all the input data, weighted on the custom merging area and the single output trace. The inference of the trained Neural Network is applied to the same data. The proposed algorithm is tested on synthetic data simulating the Mars conditions and on RIMFAX radar data collected in the Jezero crater during the Mars 2020 mission of Perseverance rover, showing successful performances and robustness.

Merging gated Frequency-Modulated Continuous-Wave Mars2020 RIMFAX GPR data

Roncoroni, Giacomo
;
Forte, Emanuele;Pipan, Michele
2023-01-01

Abstract

The integration of GPR data at various frequencies, collected with different antennas or with the use of swept-frequency radars opens up interesting perspectives in the study of the subsurface at different resolutions. The proposed methodology is a semi-supervised DL algorithm based on Bi-Directional Long-Short Term Memory to automatically merge varying numbers of data sets at different frequencies. Neural Network training is done directly on the inference data by minimizing a custom loss function based on the L2 norm of all the input data, weighted on the custom merging area and the single output trace. The inference of the trained Neural Network is applied to the same data. The proposed algorithm is tested on synthetic data simulating the Mars conditions and on RIMFAX radar data collected in the Jezero crater during the Mars 2020 mission of Perseverance rover, showing successful performances and robustness.
File in questo prodotto:
File Dimensione Formato  
geo2022-0466.1.pdf

accesso aperto

Tipologia: Bozza finale post-referaggio (post-print)
Licenza: Creative commons
Dimensione 3.55 MB
Formato Adobe PDF
3.55 MB Adobe PDF Visualizza/Apri
geo2022-0466.1.pdf

Accesso chiuso

Tipologia: Documento in Versione Editoriale
Licenza: Copyright Editore
Dimensione 4.41 MB
Formato Adobe PDF
4.41 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11368/3036670
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 3
social impact