machine learning; inversion; surface nuclear magnetic resonance
Abstract :
[en] BEL1D (Bayesian Evidential Learning 1D imaging) has recently been introduced as a viable option for the stochastic imaging of the subsurface geophysical properties (Michel et al., 2020). This methodology has been applied to surface nuclear magnetic resonance and surface wave data in order to produce sets of probable models of the subsurface. Here, we improve the accuracy of this algorithm by the introduction of iterative prior resampling. We further validate results against a state-of-the-art McMC method.
Aster, R., B. Borchers, and C. Thurber, 2013, Parameters estimation and inverse problems, 2nd ed.: Academic Press.
Behroozmand, A. A., K. Keating, and E. Auken, 2015, A review of the principles and applications of the NMR technique for near-surface characterization: Surveys in Geophysics, 36, 27-85, doi: https://doi.org/10.1007/s10712-014-9304-0.
Hong, T., and K.S. Mrinal, 2009, A new MCMC algorithm for seismic waveform inversion and corresponding uncertainty analysis: Geophysical Journal International, 177, 14-32, doi: https://doi.org/10.1111/j.1365-246X.2008.04052.x.
Kemna, A., F. Nguyen, and S. Gossen, 2007, On linear model uncertainty computation in electrical imaging: SIAM Conference on Mathematical and Computational Issues in Geosciences.
Laloy, E., R. Hérault, D. Jacques, and N. Linde, 2018, Training-image based geostatistical inversion using a spatial generative adversarial neural network: Water Resources Research, 54, 381-406, doi: https://doi.org/10.1002/2017WR022148.
Mariethoz, G., P. Renard, and J. Caers, 2010, Bayesian inverse problem and optimization with iterative spatial resampling:Water Resources Research, 46, doi: https://doi.org/10.1029/2010WR009274.
Michel, H., T. Hermans, T. Kremer, A. Elen, and F. Nguyen, 2020, 1D geological imaging of the subsurface from geophysical data with Bayesian evidential learning: Computers and Geosciences, 1044-56, doi: https://doi.org/10.1016/j.cageo.2020.104456.
Ramirez, A. L., J. J. Nitao, W. G. Hanley, R. Aines, R. E. Glaser, S. K. Sengupta, K. M. Dyer, T. L. Hickling, and W.D. Daily, 2005, Stochastic inversion of electrical resistivity changes using a Markov chain Monte Carlo approach: Journal of Geophysical Research: Solid Earth, 110, doi: https://doi.org/10.1029/2004JB003449.
Scheidt, C., L. Li, and J. Caers, 2018, Quantifying uncertainty in subsurface systems: Wiley-Blackwell.
Socco, L. V., S. Foti, and D. Boiero, 2010, Surface-wave analysis for building near-surface velocity models - Established approaches and new perspectives: Geophysics, 75, no. 5, 75A83, doi: https://doi.org/10.1190/1.3479491.
Storn, R., and K. Price, 1997, Differential evolution - A simple and efficient heuristic for global optimization over continuous spaces: Journal of Global Optimization, 11, 341-59, doi: https://doi.org/10.1023/A:1008202821328.
Vrugt, J. A., 2016, Markov chain Monte Carlo simulation using the DREAM software package: Theory, concepts, and MATLAB implementation: Environmental Modelling and Software, 75, 273-316, doi: https://doi.org/10.1016/j.envsoft.2015.08.013.