GNGTS 2021 - Atti del 39° Convegno Nazionale

391 GNGTS 2021 S essione 3.1 The dramatic speed-up of the inversion by means of the NN use makes possible on-the-fly inversion with possible applications on real-time survey design optimizations. On the other hand, in the most conservative scenario, the discussed neural network inversion can serve as a starting model for faster deterministic inversions and/or as a QC tool during the data collection phases. Acknowledgments The original research was partially supported: by the initiative PON-RI 2014-2020, Asse I ”Capitale Umano” - Azione I.1 ”Dottorati innovativi con caratterizzazione industriale Ciclo XXXIII” – project: ”GEOPROBARE: stochastic inversion of time-domain electromagnetic data”; by the initiative POR-FESR Sardegna 2014-2020, Asse I Azione I.1.3 ”Creare opportunità di lavoro favorendo la competitività delle imprese” - project: ”Tecnologie di CARatterizzazione Monitoraggio e Analisi per il ripristino e la bonifica (CARMA)”; by the project ”GETHERE” (RAS/ FBS grant-number: F71/17000190002). References Bai, P., Vignoli, G., Viezzoli, A., Nevalainen, J. and Vacca, G., 2020. (Quasi-) Real-Time Inversion of Airborne Time-Domain Electromagnetic Data via Artificial Neural Network. Remote Sensing, 12, p.3440. Ley-Cooper, A.Y., Viezzoli, A., Guillemoteau, J., Vignoli, G., Macnae, J., Cox, L., Munday, T., 2015. Airborne electromagnetic modelling options and their consequences in target definition. Explor. Geophys., 46, p.74–84. Viezzoli, A., Auken, E., Munday, T., 2009. Spatially constrained inversion for quasi 3D modelling of airborne electromagnetic data–an application for environmental assessment in the Lower Murray Region of South Australia. Explor. Geophys., 40, p.173–183. Vignoli, G., Fiandaca, G., Christiansen, A.V., Kirkegaard, C., Auken, E. 2014. Sharp spatially constrained inversion with applications to transient electromagnetic data. Geophys. Prospect., 63, p.243–255. Vignoli, G., Sapia, V., Menghini, A., Viezzoli, A., 2017. Examples of improved inversion of different airborne electromagnetic datasets via sharp regularization. J. Environ. Eng. Geophys, 22, p.51–61. Vignoli, G., Guillemoteau, J., Barreto, J., Rossi, M., 2021. Reconstruction, with tunable sparsity levels, of shear wave velocity profiles from surface wave data. Geophysical Journal International, 225, p.1935- 1951. Corresponding author: giulio.vignoli@gmail.com ; gvignoli@unica.it