GNGTS 2023 - Atti del 41° Convegno Nazionale

Session 3.3 ______ ___ GNGTS 2023 Fig. 2 – a) True resistivity model. b) Regression plot showing the ability of the CNN to predict data misfit on the models used for the training phase (blue markers) and on models on which the network has not been trained (red markers). c) – d) Best model of GA and GA+NN inversion, respectively. e) – f) Prediction error, calculated as absolute value of the difference between true and predicted model, of GA and GA+NN inversion, respectively. Fig. 3 – a) – c) Pseudosections of observed data, of data predicted by GA inversion and of data predicted by GA+NN inversion, respectively. d) – e) Comparison between observed data and data predicted by GA inversion and comparison between observed data and data predicted by GA+NN inversion, respectively.