Forecasting Copper Prices Using Hybrid Adaptive Neuro-Fuzzy Inference System and Genetic Algorithms Abstract An accurate forecasting model for the price volatility of minerals plays a vital role in future investments and decisions for mining projects and related companies. In this paper, a hybrid model is proposed to provide an accurate model for forecasting the volatility of copper prices. The proposed model combines the adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm (GA). Genetic algorithms are used for estimating the ANFIS model parameters. The results of the proposed model are compared to other models, including ANFIS, support vector machine (SVM), generalized autoregressive conditional heteroscedasticity (GARCH), and autoregressive integrated moving average (ARIMA) models. The empirical results confirm the superiority of the hybrid GA–ANFIS model over other models. The proposed model also improves the forecasting accuracy obtained from the ANFIS, SVM, GARCH, and ARIMA models by a 62.92%, 36.38%, 91.72%, and 42.19% decrease in mean square error, respectively.

ANN-Based Prediction of Laboratory-Scale Performance of CO 2 -Foam Flooding for Improving Oil Recovery Abstract Improving oil recovery by CO2 injection continues to gain momentum in mature oil fields due to its favorable industrial and environmental benefits. One remediation for the poor sweep efficiency of CO2 is co-injection of surfactants to generate CO2-foams in reservoirs. However, it is essential to minimize the expensive and time-consuming experiments required during the laboratory screening of this EOR process for a given reservoir. In this regard, methods to predict RF and Q from reservoir characteristics based on existing laboratory test data are worthwhile. In this paper, we develop the RF and Q prediction models involving optimized multi-layer perceptron (MLP) and radial basis function (RBF) neural networks. These models are applied to a compiled dataset of 214 data records of published CO2-foam injection tests into oil-reservoir cores. The RF and Q prediction derived applying these two models to the compiled dataset are compared. Statistical accuracy measures of the predictions achieved for an independent testing subset (20% of the data records) indicate for RF (MLP: RMSE = 0.0236, R2 = 0.9988; for RBF: RMSE = 0.0197, R2 = 0.9991) and for Q (MLP: RMSE = 0.0283, R2 = 0.9971; for RBF: RMSE = 0.0092, R2 = 0.9991) the excellent prediction performance of the developed networks.

Untapped Economic Resource Potential of the Neoproterozoic to Early Paleozoic Volta Basin, Ghana: A Review Abstract The ~ 115,000 km2 Volta Basin of Ghana is one of the most studied geological terrains. However, unlike the Birimian and Tarkwaian which have been targeted due to their gold potential, the Volta Basin has been studied largely only toward resolving its lithostratigraphic-related issues. The Volta Basin, however, has economic resource potentials that are worth exploring for the economic benefit of the country. This study seeks to highlight some of the economic resources of the Volta Basin that can be harnessed through further exploration and evaluation. Synthesis of the available literature on the economic resources of the Basin and some few field relations by the authors helped in unraveling the economic resource potential of the Basin. Previous mineral prospectivity maps for various identified minerals in the Basin were merged into a single large-scale map and overlaid on the geology of the area using GIS-based kriging interpolation method to outline the complete mineral resource potential of the Volta Basin. The study reveals that the northeastern, central, and southeastern fringes of the Basin have extensive exposures of sandstones that can be extracted and quarried for construction purposes. The Oti/Pendjari Group with a large areal extent coupled with a great thickness could be evaluated for brick and tiles production. The Group also has a wealth of limestones in the Mamprusi areas that could serve as a hub for cement production to serve all the northern parts of the country if exploited. The Basin could be hosting gold deposits via late hydrothermal fluids evidenced by quartz veins and the presence of extensive continuation of the Birimian structures into the overlying Volta Basin which are the main controlling features of the Birimian gold deposits. The Basin hosts phosphate, bauxite, diamond and iron ore deposits in some localities. Out of these, only iron ore discovered in the Sheini area is currently under exploration but is being constrained by several geological factors. Although Premuasi 1 well has not given promising results on the hydrocarbon potential of the Basin, the lithostratigraphic succession of the basin supports a complete hydrocarbon system just like the Taodeni Basin.

Prospecting for Clinoptilolite-Type Zeolite in a Volcano-Sedimentary Terrain Using ASTER Data: A Case Study from Alborz Mountains, Northern Iran Abstract Zeolites are hydrated alumino-silicates of alkali metals and alkaline earth cations which occur in sedimentary and volcano-sedimentary terrains. In this study, visible–near-infrared and shortwave infrared data of ASTER were evaluated in prospecting for zeolite in part of the green tuff belt of the Alborz Mountains, northern Iran. The study area is dominantly covered by sedimentary and volcano-sedimentary rocks, in which zeolite minerals occur only in the Late Eocene vitric tuff. Principal components (PC) analysis and spectral information divergence (SID) were used to discriminate and map the sedimentary and volcano-sedimentary units and the zeolite-rich areas, respectively. The X-ray diffraction and reflectance spectroscopy results indicated that clinoptilolite is the major type of zeolite mineral in this area. Comparing a color composite image, produced from PC images 1–3–5 as R–G–B, with the published geological map and the field investigations indicated that major sedimentary and volcano-sedimentary units as well as their alluvial deposits were discriminated efficiently. Results of the SID method, using an image-derived spectrum of clinoptilolite as a reference, showed good agreements with the field observations. The results of this study indicated that ASTER data are useful for discriminating various sedimentary and volcano-sedimentary units as well as clinoptilolite-type zeolite-rich areas in arid and semiarid terrains.

Geochemical Characteristics of Oil from Oligocene Lower Ganchaigou Formation Oil Sand in Northern Qaidam Basin, China Abstract Oil from the Oligocene oil sands of the Lower Ganchaigou Formation in the Northern Qaidam Basin and the related asphaltenes was analyzed using bulk and organic geochemical methods to assess the organic matter source input, thermal maturity, paleo-environmental conditions, kerogen type, hydrocarbon quality, and the correlation between this oil and its potential source rock in the basin. The extracted oil samples are characterized by very high contents of saturated hydrocarbons (average 62.76%), low contents of aromatic hydrocarbons (average 16.11%), and moderate amounts of nitrogen–sulfur–oxygen or resin compounds (average 21.57%), suggesting that the fluid petroleum extracted from the Oligocene oil sands is of high quality. However, a variety of biomarker parameters obtained from the hydrocarbon fractions (saturated and aromatic) indicate that the extracted oil was generated from source rocks with a wide range of thermal maturity conditions, ranging from the early to peak oil window stages, which are generally consistent with the biomarker maturity parameters, vitrinite reflectance (approximately 0.6%), and Tmax values of the Middle Jurassic carbonaceous mudstones and organic-rich mudstone source rocks of the Dameigou Formation, as reported in the literature. These findings suggest that the studied oil is derived from Dameigou Formation source rocks. Furthermore, the source- and environment-related biomarker parameters of the studied oil are characterized by relatively high pristane/phytane ratios, the presence of tricyclic terpanes, low abundances of C27 regular steranes, low C27/C29 regular sterane ratios, and very low sterane/hopane ratios. These data suggest that the oil was generated from source rocks containing plankton/land plant matter that was mainly deposited in a lacustrine environment and preserved under sub-oxic to oxic conditions, and the data also indicate a potential relationship between the studied oil and the associated potential source rocks. The distribution of pristane, phytane, tricyclic terpanes, regular steranes and hopane shows an affinity with the studied Oligocene Lower Ganchaigou Formation oil to previously published Dameigou Formation source rocks. In support of this finding, the pyrolysis–gas chromatography results of the analyzed oil asphaltene indicate that the oil was primarily derived from type II organic matter, which is also consistent with the organic matter of the Middle Jurassic source rocks. Thus, the Middle Jurassic carbonaceous mudstones and organic rock mudstones of the Dameigou Formation could be significantly contributing source rocks to the Oligocene Lower Ganchaigou Formation oil sand and other oil reservoirs in the Northern Qaidam Basin.

Unconventional Energy Resources: 2017 Review Abstract This review presents six summaries for energy resource commodities including coal and unconventional resources, and an analysis of energy economics and technology for the different commodities, as prepared by the Energy Minerals Division of the American Association of Petroleum Geologists. Unconventional energy resources, as defined in this report, are those energy resources that do not occur in discrete oil or gas reservoirs held within stratigraphic and/or structural traps of sedimentary basins. As defined, such energy resources include coal, coalbed methane (CBM), tight gas and liquids, bitumen and heavy oil, uranium (U), thorium (Th), and associated rare earth elements of interest to industry, and geothermal. Current North American and global research and development activities are summarized for each of the unconventional energy resource commodities in separate topical sections of this report.

Mapping Geochemical Anomalies Through Integrating Random Forest and Metric Learning Methods Abstract Extracting geochemical anomalies from geochemical exploration data is one of the most important activities in mineral exploration. Geochemical anomaly detection can be regarded as a binary classification problem. The similarity between geochemical samples can be measured by their distance. The key issue of this classification is to find the intrinsic relationship and distance between geochemical samples to separate geochemical anomalies from background. In this paper, a hybrid method that integrates random forest and metric learning (RFML) is used to identify geochemical anomalies related to Fe-polymetallic mineralization in Southwest Fujian Province of China. RFML does not require any specific statistical assumption on geochemical data, nor does it depend on sufficient known mineral occurrences as the prior knowledge. The geochemical anomaly map obtained by the RFML method showed that the known Fe deposits and the generated geochemical anomaly area have strong spatial association. Meanwhile, the receiver operating characteristic curves for the results of RFML and another method, namely maximum margin metric learning, indicated that the RFML method exhibited better performance, suggesting that RFML can be effectively applied to recognize geochemical anomalies.

Experimental Study of Adsorption Effects on Shale Permeability Abstract CH4 adsorption plays an important role in the permeability evolution of unconventional gas reservoirs. In this paper, an experimental method for simultaneous measurement of rock adsorption and permeability has been developed. For this experimental method, the CH4 adsorption amounts were obtained using a volumetric method. The permeability was measured by considering gas diffusion from the reference chamber to the core sample, under the pressure difference. A set of adsorption-permeability experiments were conducted on shale samples from lower Silurian Longmaxi Formation in the Sichuan Basin. The experimental results show that both the adsorption and swelling behavior of shale can be well described by the Langmuir equation. The effects of adsorption on permeability are influenced by two factors: (1) adsorption-induced storage, which causes an incremental in apparent porosity, leading to a significant error in permeability measurement if true porosity is used; and (2) adsorption-induced swelling, which potentially closes the existing natural fractures and reduces the intrinsic permeability. The adsorption storage effects are more significant at low pressure and are influenced by the experimental configurations (ratio of chamber volume to pore volume). With the increase in adsorption-induced swelling strain, the permeability declines by a cubic function during the adsorption process. Since swelling strain is linearly proportional to the amount of CH4 adsorbed, the behaviors of permeability and the amount of adsorbing gas follow similar trends.

An Improved Data-Driven Multiple Criteria Decision-Making Procedure for Spatial Modeling of Mineral Prospectivity: Adaption of Prediction–Area Plot and Logistic Functions Abstract Assigning realistic weights to targeting criteria in order to synthesize various geo-spatial datasets is one of the most important challenging tasks for mineral prospectivity modeling (MPM). Techniques for multiple criteria decision-making (MCDM), like MPM, are deeply concerned with combining a large-scale exploration dataset into a single evaluation model for localizing prospects of a certain deposit type. In this paper, we develop the data-driven TOPSIS procedure, as a GIS-based MCDM technique for MPM. Because weighting and integrating various exploration evidence layers are influenced by intricacy and vagueness of ore mineralization process, imprecise selection of targeting criteria may reduce the possibility of exploration success. To address this problem, we applied prediction–area plot for prioritizing, recognizing and weighting efficient and inefficient targeting criteria. In addition, normalized density (Nd) index was then used for assigning significant weights to fractal-based discretized classes of each targeting criterion. After recognition of efficient and inefficient targeting criteria, data-driven TOPSIS procedure was adapted based on participation of only efficient targeting criteria as well as all targeting criteria for porphyry-Cu prospectivity in Varzaghan district, NW Iran. For quantitative assessment, a success rate curve for each of the two prospectivity models generated in this study was drawn. The results prove the superiority of the predictive model based on using efficient targeting criteria.

Direct Formation of Burkeite in the Geothermal Waters at Vranjska Banja, Serbia Abstract There are no available data about direct burkeite formation on the geothermal waters pipelines in Europe. Data about accompanying minerals of burkeite are also scarce. This mineral has been found in the scale on pipelines of VG-2 and VG-3 boreholes at Vranjska Banja, Serbia. Geothermal waters from these boreholes have temperatures in the range of 103 and 105 °C which classifies them to the warmest waters in the continental Europe. Based on physicochemical and geochemical data, VG-2 and VG-3 geothermal waters can be classified as Na–Alk–SO4Cl type of waters. According to their temperatures, total hardness and pH values, these waters belong to hyperthermal, very soft and moderately alkaline. Calculated LSI (0.4 and 1.7) and RSI (6.5 and 4.8) values indicate their scale formation tendency. Results of the spectrometric scale examination from the pipe deposits provide a clear qualitative and quantitative burkeite characterization with its accompanying minerals. FTIR analysis points to the presence of carbonate (1766, 1458, 877 and 705 cm−1) and sulfate bands (1139, 1116 and 617 cm−1). Apart from the qualitative analysis, XRD also shows the burkeite mass part in the scale. VG-2 geothermal water contains about 50% of burkeite, which is associated with trona mineral (40%) and smaller amount of halite of about 10%. Burkeite is a dominant phase (> 60%) in VG-3 water, with the presence of a significant halite quantity (> 35%) and a minor calcite quantity (2%).