Inversion of time‐dependent nuclear well‐logging data using neural networks

Abstract

A B S T R A C TThe purpose of this work was to investigate a new and fast inversion methodology for the prediction of subsurface formation properties such as porosity, salinity and oil saturation, using time-dependent nuclear well logging data. Although the ultimate aim is to apply the technique to real-field data, an initial investigation as described in this paper, was first required; this has been carried out using simulation results from the time-dependent radiation transport problem within a borehole. Simulated neutron and γ -ray fluxes at two sodium iodide (NaI) detectors, one near and one far from a pulsed neutron source emitting at ∼14 MeV, were used for the investigation. A total of 67 energy groups from the BUGLE96 cross section library together with 567 property combinations were employed for the original flux response generation, achieved by solving numerically the time-dependent Boltzmann radiation transport equation in its even parity form. Material property combinations (scenarios) and their correspondent teaching outputs (flux response at detectors) are used to train the Artificial Neural Networks (ANNs) and test data is used to assess the accuracy of the ANNs. The trained networks are then used to produce a surrogate model of the expensive, in terms of computational time and resources, forward model with which a simple inversion method is applied to calculate material properties from the time evolution of flux responses at the two detectors.The inversion technique uses a fast surrogate model comprising 8026 artificial neural networks, which consist of an input layer with three input units (neurons) for porosity, salinity and oil saturation; and two hidden layers and one output neuron representing the scalar photon or neutron flux prediction at the detector. This is the first time this technique has been applied to invert pulsed neutron logging tool information and the results produced are very promising. The next step in the procedure is to apply the methodology to real data.

Artificial neural network forward modelling and inversion of electrokinetic logging data

“…Maiti, Tiwari and Kümpel (2007) developed a neural network for classifying lithofacies boundaries from well log data. Aristodemou et al (2005) and Carmine et al (2008) described inversion of both steady‐state and time dependent nuclear well logging to predict subsurface formation properties (such as porosity, salinity and oil/water saturation) using neural networks.…”

“…Errors in predicted porosities (seen and unseen) range between 3–20% for permeabilities 10 mD, 100 mD and 1000 mD, whilst higher errors are observed when permeabilities are low (1 mD and lower). It should be noted that there are other methods, such as inversion of nuclear well‐logging data (Aristodemou et al 2005; Carmine et al 2008), that can be used to predict porosity within a 3% average relative error. Therefore, the predicted porosities (Fig.…”