Complex Geological Features Research Articles

A Deep-Learning-Based Geological Parameterization for History Matching Complex Models

A new low-dimensional parameterization based on principal component analysis (PCA) and convolutional neural networks (CNN) is developed to represent complex geological models. The CNN-PCA method is inspired by recent developments in computer vision using deep learning. CNN-PCA can be viewed as a generalization of an existing optimization-based PCA (O-PCA) method. Both CNN-PCA and O-PCA entail post-processing a PCA model to better honor complex geological features. In CNN-PCA, rather than use a histogram-based regularization as in O-PCA, a new regularization involving a set of metrics for multipoint statistics is introduced. The metrics are based on summary statistics of the nonlinear filter responses of geological models to a pre-trained deep CNN. In addition, in the CNN-PCA formulation presented here, a convolutional neural network is trained as an explicit transform function that can post-process PCA models quickly. CNN-PCA is shown to provide both unconditional and conditional realizations that honor the geological features present in reference SGeMS geostatistical realizations for a binary channelized system. Flow statistics obtained through simulation of random CNN-PCA models closely match results for random SGeMS models for a demanding case in which O-PCA models lead to significant discrepancies. Results for history matching are also presented. In this assessment CNN-PCA is applied with derivative-free optimization, and a subspace randomized maximum likelihood method is used to provide multiple posterior models. Data assimilation and significant uncertainty reduction are achieved for existing wells, and physically reasonable predictions are also obtained for new wells. Finally, the CNN-PCA method is extended to a more complex non-stationary bimodal deltaic fan system, and is shown to provide high-quality realizations for this challenging example.

Embedded discrete fracture modeling for compositional reservoir simulation using corner-point grids

Abstract Corner-point is an industry-standard type grid for application in reservoir simulation. The flexible gridding in corner-point grids provides several advantages over Cartesian grids for the representation of complex geological features. In this work, an embedded discrete fracture model (EDFM) is extended to corner-point grids with a full-permeability-tensor formulation to simulate complex fractures in this type of grids. The developed model is implemented in an IMPEC, compositional reservoir simulator. We first describe the formulations of the full-permeability-tensor implementation together with the modified governing equations for EDFM simulations. Then, we present methodologies for computing matrix-fracture intersections and fracture-fracture connections in the EDFM considering the various block geometries in corner-point grids. Subsequently, case studies are presented to verify the developed model, where the impacts of grid distortion and cross derivatives on simulation results are discussed. Three-dimensional case studies are also shown to illustrate the influence of natural fractures on secondary recovery. The results of this study demonstrate the reliability of the developed model, and they also show the compatibility of the EDFM with different types of numerical solution schemes in existing simulators.

Uncertainty quantification and reduction in the characterization of subsurface stratigraphy using limited geotechnical investigation data

Subsurface stratigraphy is critical to the design, construction, and subsequent performance of geotechnical structures. However, in practice it is impossible to identify the stratigraphy of a subsurface geological domain with absolute certainty, due to the limitations imposed by geotechnical investigation techniques and project budgets. This paper presents a subsurface stratigraphic modeling and uncertainty quantification approach, which is established based on an improved and extended geological modeling technique previously established by the author and others, for simulating the stratigraphy of both two-dimensional (2D) and three-dimensional (3D) cases with more complex geological features. Furthermore, this approach provides quantitative evaluation of the amount of stratigraphic uncertainty in the current interpretation and enables the systematic reduction of stratigraphic uncertainty through the investigation of additional targeted borehole drilling locations. Illustrative examples, including artificial cases as well as two real cases from existing geotechnical projects, are presented in this study to demonstrate the use of the proposed analysis approach.

Redressing the balance: quantifying net intercatchment groundwater flows

Abstract. Intercatchment groundwater flows (IGFs), defined as groundwater flows across topographic divides, can occur as regional groundwater flows that bypass headwater streams and only drain into the channel further downstream or directly to the sea. However, groundwater flows can also be diverted to adjacent river basins due to geological features (e.g., faults, dipping beds and highly permeable conduits). Even though intercatchment groundwater flows can be a significant part of the water balance, they are often not considered in hydrological studies. Yet, assuming this process to be negligible may introduce misrepresentation of the natural system in hydrological models, for example in regions with complex geological features. The presence of limestone formations in France and Belgium potentially further exacerbates the importance of intercatchment groundwater flows, and thus brings into question the validity of neglecting intercatchment groundwater flows in the Meuse basin. To isolate and quantify the potential relevance of net intercatchment groundwater flows in this study, we propose a three-step approach that relies on the comparison and analysis of (1) observed water balance data within the Budyko framework, (2) results from a suite of different conceptual hydrological models and (3) remote-sensing-based estimates of actual evaporation. The data of 58 catchments in the Meuse basin provide evidence of the likely presence of significant net intercatchment groundwater flows occurring mainly in small headwater catchments underlain by fractured aquifers. The data suggest that the relative importance of net intercatchment groundwater flows is reduced at the scale of the Meuse basin, as regional groundwater flows are mostly expected to be self-contained in large basins. The analysis further suggests that net intercatchment groundwater flow processes vary over the year and that at the scale of the headwaters, net intercatchment groundwater flows can make up a relatively large proportion of the water balance (on average 10 % of mean annual precipitation) and should be accounted for to prevent overestimating actual evaporation rates.

Occurrence characteristics and influential factors of movable fluids in pores with different structures of Chang 63 reservoir, Huaqing Oilfield, Ordos Basin, China

Abstract Exploration and development of Chang 63 reservoir in the Huaqing Oilfield, Ordos Basin is challenging because of the complex geological features, including strong heterogeneity, complicated microscopic pore structures, low saturation of movable fluids, and distinct fluid distribution characteristics. Confronted with this challenge, this study used the nuclear magnetic resonance (NMR) technique to quantitatively evaluate the movable fluids in pores with different structures. Moreover, microscopic experiments were conducted to analyze the occurrence characteristics and influential factors of movable fluids in pores with different structures, including conventional physical property analysis, image porosity measurement, casting thin section observation, SEM analysis, high pressure mercury intrusion testing, and constant pressure mercury intrusion testing. The results showed that gray and grayish brown lithic feldspar sandstones were the dominant types of sandstone. Residual intergranular pores and feldspar dissolved pores were the main pore types, with unevenly distributed pore throat radii, among which small pores and micropores were primary. Four types of pore structures could be divided according to comprehensive analysis of capillary pressure curves, namely Types I, II, III, and IV, and they were featured by movable fluids with distinct occurrence characteristics in them. Reservoir permeability was well correlated with movable fluid saturation. Multiple factors were demonstrated to influence the movable fluid saturation in pores with different structures, including pore throat radius, pore-throat radius ratio, sorting coefficient, effective pore and throat volume, maximum mercury saturation in pores and throats, and interstitial clay minerals. Generally, good physical properties led to larger variation of movable fluid saturation. Among them, effective pore throat radius and pore-throat radius ratio were the dominant factors, effective pore and throat volume as well as sorting coefficient had some degree of influence, and maximum mercury saturation and physical properties had little effect on the movable fluid saturation.

A challenging dam structural analysis: large-scale implicit thermo-mechanical coupled contact simulation on Tianhe-II

Due to huge bulk volume and extremely complex geometrical and geological features, it is forbiddingly difficult to perform a dam structural analysis with even moderate geometry fidelity in engineering practices. We present a high resolution of engineering structural analysis of the first ultra-high concrete-faced rockfill dam in China. Mesh resolution is taken to be 20 cm along slab thickness for the bulk volume of 20M $$\hbox {m}^{3}$$ of the whole dam. The engineering problem is solved by considering nonlinear behaviors such as joints’ contact nonlinearity, creep deformation, and strong thermo-mechanical coupling, as well as blended continuous-discontinuous approximation, on a mesh model of 1.1 billion dofs using 16K CPU cores of Tianhe-II. The problem to be solved is a challenging non-positive definite, non-symmetric and ill-conditioned matrix problem. The simulation confirms in the first time that the sunlight temperature effect can contribute up to a contact stress increment of maximum 10.9 MPa and explains frequent extrusion damage observed for the dam. As model tests are difficult to perform for high dams, with this first success, we envision that extreme-scale simulation would pose broad impact on the safety evaluation of high dams in future.

Regional structural mapping using a combined geological and geophysical approach – A preliminary study at Cairo-Suez district, Egypt

Contrary to the usual application of individual geological and/or geophysical surveys, this paper represented a sequential use of surface structural mapping and DCR method to afford a sensible structural model in a cost effective way. Understanding the geological setting of a non-mapped area at the central part of Cairo-Suez District (CSD), Egypt, is an immediate engineering concern due to its complex deformation history. Field work is carried out to measure stratigraphic sections and establish structural characteristics of the rock units. Surface geophysical DCR sounding and electrical resistivity tomography (ERT) surveys are performed. To overcome the non-uniqueness problem of DCR interpretation, the available borehole data, detailed surface geological measurements and a sequential use of linear and non-linear inversion algorithms are applied. The practical benefits of detailed surface structural mapping are demonstrating in considering all geological parameters to a conceptual subsurface model, which would have not been identified or misinterpreted otherwise. In an integrative approach, such detailed surface data allow us to confirm the uncertain inferred regional subsurface structures based on DCR data inversion. For detailed subsurface structural characterization, the results of ERTs using coarse triangular mesh and iteratively reweighted algorithm show a good agreement with prior known surface and underground structural features. Additionally, ERTs significantly resolve the complex geological features, which constitute uncertain structures in the surface structural model. The main impact of presented integrative approach is to (i) constraint the DCR data interpretation and (ii) inform a preliminary study plan of regional structural investigation, which can be used as a platform for engineering decision–making and/or further detailed geophysical and geotechnical investigations.

Probabilistic approach toward Darjeeling Himalayas landslides-A case study

The Himalayan region with its complex geological features, steep slopes, rugged topography, and intense monsoonal rainfall create ideal conditions for landslides. The damage caused due to landslide...

Calcium Carbonate Production, Coral Cover and Diversity along a Distance Gradient from Stone Town: A Case Study from Zanzibar, Tanzania

Photosymbiotic scleractinian corals are major bioengineers in tropical coastal waters, where they build structurally complex geological features and provide substrata for a manifold of macro and microhabitats. On a local scale, ecological competition and physical parameters - natural as well as human-derived, alter species richness, biodiversity, and morphological adaptation on tropical coral reefs. Here, we compared four coral reefs in the Zanzibar Archipelago at different distances from Stone Town and under different management regimes. To assess the ecological health of these reefs, calcium carbonate production, structural complexity, and α-diversity were determined. The unprotected reefs in the direct vicinity of Stone Town, which are exposed to fishing pressure, land-derived pollution, unregulated tourism, and careless anchoring, showed the lowest calcium carbonate production (8.47 ± 4.37 kg CaCO3 m-2 yr-1), coral cover (52.4 ± 13.9%), and diversity (H´=0.94 ± 0.37). Conversely, the furthest reef and marine protected area showed the highest net calcium carbonate production (16.90 ± 9.70 kg CaCO3 m-2 yr-1), coral cover (67.4 ± 8.7%), and diversity (H´=1.74 ± 0.20). In comparison to other bioregions and/or reefs of the Indian Ocean, estimates of calcium carbonate production and coral cover (>50%) were relatively high. Moreover, coral community structure differs significantly with distance from Stone Town, in that, the most homogenous reefs dominated by massive and submassive species (Porites lobata and P. rus) occurred the closest to Stone Town.

A fully-coupled discontinuous Galerkin spectral element method for two-phase flow in petroleum reservoirs

A high-order spectral element discontinuous Galerkin method is presented for simulating immiscible two-phase flow in petroleum reservoirs. The governing equations involve a coupled system of strongly nonlinear partial differential equations for the pressure and fluid saturation in the reservoir. A fully implicit method is used with a high-order accurate time integration using an implicit Rosenbrock method. Numerical tests give the first demonstration of high order hp spatial convergence results for multiphase flow in petroleum reservoirs with industry standard relative permeability models. High order convergence is shown formally for spectral elements with up to 8th order polynomials for both homogeneous and heterogeneous permeability fields. Numerical results are presented for multiphase fluid flow in heterogeneous reservoirs with complex geometric or geologic features using up to 11th order polynomials. Robust, stable simulations are presented for heterogeneous geologic features, including globally heterogeneous permeability fields, anisotropic permeability tensors, broad regions of low-permeability, high-permeability channels, thin shale barriers and thin high-permeability fractures.A major result of this paper is the demonstration that the resolution of the high order spectral element method may be exploited to achieve accurate results utilizing a simple cartesian mesh for non-conforming geological features. Eliminating the need to mesh to the boundaries of geological features greatly simplifies the workflow for petroleum engineers testing multiple scenarios in the face of uncertainty in the subsurface geology.

A fast complex domain-matching pursuit algorithm and its application to deep-water gas reservoir detection

The main emphasis of exploration and development is shifting from simple structural reservoirs to complex reservoirs, which all have the characteristics of complex structure, thin reservoir thickness and large buried depth. Faced with these complex geological features, hydrocarbon detection technology is a direct indication of changes in hydrocarbon reservoirs and a good approach for delimiting the distribution of underground reservoirs. It is common to utilize the time–frequency (TF) features of seismic data in detecting hydrocarbon reservoirs. Therefore, we research the complex domain-matching pursuit (CDMP) method and propose some improvements. First is the introduction of a scale parameter, which corrects the defect that atomic waveforms only change with the frequency parameter. Its introduction not only decomposes seismic signal with high accuracy and high efficiency but also reduces iterations. We also integrate jumping search with ergodic search to improve computational efficiency while maintaining the reasonable accuracy. Then we combine the improved CDMP with the Wigner–Ville distribution to obtain a high-resolution TF spectrum. A one-dimensional modeling experiment has proved the validity of our method. Basing on the low-frequency domain reflection coefficient in fluid-saturated porous media, we finally get an approximation formula for the mobility attributes of reservoir fluid. This approximation formula is used as a hydrocarbon identification factor to predict deep-water gas-bearing sand of the M oil field in the South China Sea. The results are consistent with the actual well test results and our method can help inform the future exploration of deep-water gas reservoirs.

Evolution of iron crust and clayey Ferralsol in deeply weathered sandstones of Marília Formation (Western Minas Gerais State, Brazil)

Extensive flat plateaus are typical landforms in the cratonic compartment of tropical regions. Paleoclimate, pediplanation, laterization, and dissection have created complex and distinct geological, geomorphological, and pedological features in these landscapes. In the Brazilian territory, the flat plateau sculpted in sandstone of Marília Formation (Neocretaceous) belonging to the Sul-Americana surface presents a very clayey and pisolitic Ferralsol (Red and Yellow Latossolo in the Brazilian soil classification). The clayey texture of soil and the pisolites have been considered as weathering products of a Cenozoic detritical formation which is believed to overlay the Marília Formation sandstones. Using data of petrography (optical microscopy and SEM), mineralogy (RXD), and macroscopic structures (description in the field of the arrangement of horizons and layers), a complete profile of Ferralsol with ferricrete and pisolites was studied. The complex succession of facies is in conformity with a sedimentary structure of Serra da Galga member (uppermost member of Marília Formation). The hardening hematite concentration appears as layered accretions in the subparallel clayey lenses of sandstone saprolite, preserving its structure. Iron contents varied according to different soil fabrics. Higher concentrations of iron are found in the massive ferricrete or in pisolites in the mottled horizon. Kaolinite is a dominant clay mineral and shows two micro-organizations: (1) massive fabric intrinsic to the sedimentary rock, and (2) reworked in pisolites and illuviated features. The pisolites are relicts of ferricrete in the soft bioturbated topsoil. The continuous sequence of ferricrete from saprolite to the Ferralsol indicates that the regolith is autochthonous, developed directly from sandstones of Marília Formation, through a long and intense process of laterization.

Insights in Fault Flow Behaviour from Onshore Nigeria Petroleum System Modelling

Faults are complex geological features acting either as permeability barrier, baffle or drain to fluid flow in sedimentary basins. Their role can be crucial for over-pressure building and hydrocarbon migration, therefore they have to be properly integrated in basin modelling. The ArcTem basin simulator included in the TemisFlow software has been specifically designed to improve the modelling of faulted geological settings and to get a numerical representation of fault zones closer to the geological description. Here we present new developments in the simulator to compute fault properties through time as a function of available geological parameters, for single-phase 2D simulations. We have used this new prototype to model pressure evolution on a siliciclastic 2D section located onshore in the Niger Delta. The section is crossed by several normal growth faults which subdivide the basin into several sedimentary units and appear to be lateral limits of strong over-pressured zones. Faults are also thought to play a crucial role in hydrocarbons migration from the deep source rocks to shallow reservoirs. We automatically compute the Shale Gouge Ratio (SGR) along the fault planes through time, as well as the fault displacement velocity. The fault core permeability is then computed as a function of the SGR, including threshold values to account for shale smear formation. Longitudinal fault fluid flow is enhanced during periods of high fault slip velocity. The method allows us to simulate both along-fault drainages during the basin history as well as overpressure building at present-day. The simulated pressures are at first order within the range of observed pressures we had at our disposal.

Two-phase flow pipe network method for simulation of CO2 sequestration in fractured saline aquifers

A two-phase flow unified pipe network method is developed to simulate CO2 evolution in fractured saline aquifers. Fractures are explicitly represented in the proposed method. The two-phase flow in both rock matrix and fractures is considered by using different equivalent pipe flow models respectively, namely the two-phase matrix pipe flow model and the two-phase fracture pipe flow model. The equivalent flow coefficients of the pipe flow models are derived based on flow rate equivalence. The coupling of the fracture pipe flow and matrix pipe flow is treated by applying the extended capillary pressure conditions. Brooks-Corey relative permeability model and capillary model are adopted to simulate CO2 (non-wetting phase) invasion into the brine (wetting phase) saturated formation, which is a typical drainage process. Accurate Equations of State for calculating density and viscosity of CO2 are incorporated to reflect its change in hydraulic characteristics during the injection processes. The proposed method is simple yet robust and not sensitive to the mesh quality. The complex geological and topological features of fracture networks can, therefore, be well retained in the proposed method. The anisotropy and heterogeneity characteristics of the fractured rock mass caused by the fracture networks can be accurately represented. The proposed method is verified by comparing to other numerical methods. Both 2D and 3D models with complex fracture networks are presented to demonstrate the feasibility of proposed method. Numerical examples show that fractures can significantly affect the distribution and evolution of CO2 in aquifers and the differences of entry capillary pressures for fractures and matrix rock should be accurately simulated.

Wedge Instability on the Abutment of a Gravity Dam in Italy

This paper describes a wedge instability occurred during excavation of the right abutment slope in a granite rock mass at the Cumbidanovu dam site in Italy. The dam is a 72.7 m high concrete gravity dam, presently under construction. The slopes are characterized by the presence of a granite rock mass, rather complex geologic features (shear/fault zones), multiple rock joint sets, and significant differences in rock mass quality. The rock mass conditions are briefly illustrated based on systematic geological and discontinuity mapping during excavation of the abutment slopes, from the top down. Also briefly described are the rock mass characterization studies, including the results of laboratory and in situ testing. The results of three-dimensional stability studies with limit equilibrium and finite element analyses are illustrated. The main purpose has been to back-analyze the rock wedge instability based on the available data and the geological mapping performed, in view of the stabilization measures to be adopted, including a reshaping of the abutment slope.

Multiscale model reduction for shale gas transport in a coupled discrete fracture and dual-continuum porous media

Natural gas production from shale formations involves highly complex geological features consisting of fractures that are embedded spatially-distributed in a matrix made of organic and inorganic materials. In this paper, we develop a coupled multiscale and multi-continuum approach for simulating gas transport in the shale formation. The multiscale method allowed us to capture detailed interactions between the fractures and the background. For the fine-scale heterogeneities involving organic and inorganic materials distribution in the matrix, we use a dual-continuum approach. The matrix is coupled to the fractures by use of the Generalized Multiscale Finite Element Method (GMsFEM). In our previous work (Akkutlu et al., 2016), we used a single-continuum background coupled to the fracture network. This paper presents a significant extension and considers dual-continuum media as a background. GMsFEM systematically identifies the fracture networks by constructing corresponding multiscale basis functions. GMsFEM also accurately represents the fractures interacting with the background media. Moreover, GMsFEM can handle any spatial fracture distributions and thus, it avoids the limitations of the multi-continuum approaches. Results show that the proposed numerical approach can accurately capture the interactions between the fractures and the multi-continuum model using a few multiscale basis functions.

A review of three geostatistical techniques for realistic geological reservoir modeling integrating multi-scale data

Abstract This paper discusses new methodologies and workflows developed to generate geological models (1) that look more realistic geologically speaking and (2) that respect the well and seismic data characterizing the studied area. Accounting simultaneously for these two constraints is challenging as they behave the opposite way. The more realistic the geological model, the more difficult the integration of data. A first powerful approach is based upon the non-stationary plurigaussian simulation method. In this case, the available geological and seismic data make it possible to compute the 3D probability distributions of facies proportions, which are then used to truncate the Gaussian functions. A second method is rooted in the Bayesian sequential simulation. Recent developments have been proposed to extend this method to media including distinct facies. We suggest an improved variant to better account for the resolution differences between sonic logs and seismic data. This yields a more robust framework to integrate seismic data. A third innovative approach reconciles geostatistical multipoint simulation with texture synthesis principles. Geostatistical multipoint methods provide models, which better reproduce complex geological features. However, they still call for significant computation times. On the other hand, texture synthesis has been developed for computer graphics: it can help reduce computation time, but it does not account for data. We then envision a hybrid multi-scale algorithm with improved computation performances and yet able to respect data

A local–global pattern matching method for subsurface stochastic inverse modeling

Inverse modeling is an essential step for reliable modeling of subsurface flow and transport, which is important for groundwater resource management and aquifer remediation. Multiple-point statistics (MPS) based reservoir modeling algorithms, beyond traditional two-point statistics-based methods, offer an alternative to simulate complex geological features and patterns, conditioning to observed conductivity data. Parameter estimation, within the framework of MPS, for the characterization of conductivity fields using measured dynamic data such as piezometric head data, remains one of the most challenging tasks in geologic modeling. We propose a new local–global pattern matching method to integrate dynamic data into geological models. The local pattern is composed of conductivity and head values that are sampled from joint training images comprising of geological models and the corresponding simulated piezometric heads. Subsequently, a global constraint is enforced on the simulated geologic models in order to match the measured head data. The method is sequential in time, and as new piezometric head become available, the training images are updated for the purpose of reducing the computational cost of pattern matching. As a result, the final suite of models preserve the geologic features as well as match the dynamic data. This local–global pattern matching method is demonstrated for simulating a two-dimensional, bimodally-distributed heterogeneous conductivity field. The results indicate that the characterization of conductivity as well as flow and transport predictions are improved when the piezometric head data are integrated into the geological modeling.

Capability of self-organizing map neural network in geophysical log data classification: Case study from the CCSD-MH

Well log interpretation is one of the prime sources of information for deep lithology in drilling research. Because of the complex geological features of the crystalline metamorphic rocks, more complex nonlinear functional behaviors exist for well log interpretation purposes. Hence, establishing a prediction technology that can accurately interpret/classify well log data in terms of lithology is of major significance. This study, for the first time, explores the application of self-organizing map neural network (SOM) in the classification of metamorphic rocks from Chinese Continental Scientific Drilling Main Hole (CCSD-MH) log data. For this purpose, a total of 33,326 data points derived from resistivity, P-wave velocity, bulk density, photoelectric absorption capture cross section, gamma ray, potassium content and neutron logs were used as an input pattern to a SOM to classify lithology in five categories: orthogneiss, paragneiss, eclogite, amphibolite and ultramafic rocks. Comparison of SOM results to those of feed-forward neural network (FFNN) was also carried out. The cross-validation method was used to investigate the robustness of the two neural networks in terms of classification accuracy in the context of lithology clustering tasks by sampling rotation. Statistical tests such as student paired samples t-test was carried out to guide in classification decision of the CCSD-MH data. The results of this study have proven that SOM appears to be comparable to FFNN in classifying lithology using geophysical log data from crystalline rocks. This proposed SOM approach can serve as practical alternative technology to be used in drilling research.

Prediction of porosity in crystalline rocks using artificial neural networks: An example from the Chinese Continental Scientific Drilling Main hole

Porosity plays an important part of understanding permeability and fluid flow within the continental, crystalline rocks. Geophysical well logs are presently the most consistent means of providing continuous information for porosity estimation. However, it is difficult to interpret geophysical well logs data in crystalline rocks due to their complex geological features and the difficulty in understanding and using the complex and intensive information content in these data. Motived by the successful prediction abilities of artificial neural networks (ANN) to solve different problems in geophysics, this study explore the applicability of using ANNs to predict porosity in continental, crystalline rocks. This ANN technique is calibrated on Chinese Continental Scientific Drilling Main Hole (CCSD-MH) data, which provides core porosity data combined with four geophysical well logs (density, neutron porosity, sonic and resistivity). The data from CCSD-MH is utilized to train feed-forward backpropagation (FFBP) neural network and radial basis function (RBF) neural network to derive a relationship between geophysical well logs and porosity, and hence predict porosity accurately. The findings demonstrate that ANNs provide better performances with sets of three geophysical well logs (density, sonic and resistivity) than regression technique. Comparison of FFBP to RBF showed that RBF reveals better stability and more accurate performances than FFBP. Based on the success achieved in this study, this intelligence artificial technique can be a very advantageous tool in facilitating the task of geophysicists in the framework of research drillings in continental crust.