Application of Discriminant Analysis and Support Vector Machine in Mapping Gold Potential Areas for Further Drilling in the Sari-Gunay Gold Deposit,NW Iran

In this contribution, we used discriminant analysis (DA) and support vector machine (SVM) to model subsurface gold mineralization by using a combination of the surface soil geochemical anomalies and earlier bore data for further drilling at the Sari-Gunay gold deposit, NW Iran. Seventy percent of the data were used as the training data and the remaining 30 % were used as the testing data. Sum of the block grades, obtained by kriging, above the cutoff grade (0.5 g/t) was multiplied by the thickness of the blocks and used as productivity index (PI). Then, the PI variable was classified into three classes of background, medium, and high by using fractal method. Four classification functions of SVM and DA methods were calculated by the training soil geochemical data. Also, by using all the geochemical data and classification functions, the general extension of the gold mineralized zones was predicted. The mineral prediction models at the Sari-Gunay hill were used to locate high and moderate potential areas for further infill systematic and reconnaissance drilling, respectively. These models at Agh-Dagh hill and the area between Sari-Gunay and Agh-Dagh hills were used to define the moderate and high potential areas for further reconnaissance drilling. The results showed that the nu-SVM method with 73.8 % accuracy and c-SVM with 72.3 % accuracy worked better than DA methods.     

2D probabilistic prediction of sparsely measured earth properties constrained by geophysical imaging fully accounting for tomographic reconstruction ambiguity

Many hydrological, environmental, or engineering exploration tasks require predicting spatially continuous scenarios of sparsely measured borehole logging data. We present a methodology to probabilistically predict such scenarios constrained by ill-posed geophysical tomography. Our approach allows for transducing tomographic reconstruction ambiguity into the probabilistic prediction of spatially continuous target parameter scenarios. It is even applicable to data sets where petrophysical relations in the survey area are non-unique, i.e., different facies related petrophysical relations may be present. We employ static two-layer artificial neural networks (ANNs) for prediction and additionally evaluate, whether the training performance of the ANNs can be used to rank geophysical tomograms, which are mathematically equal reconstructions of physical parameter distributions in the ground. We illustrate our methodology using a realistic synthetic database for maximal control about the prediction performance and ranking potential of the approach. For doing so, we try to link geophysical radar and seismic tomography as input parameters to porosity of the ground as target parameter of ANN. However, the approach is flexible and can cope with any combination of geophysical tomograms and hydrologic, environmental or engineering target parameters. Ranking of equivalent geophysical tomograms based on additional borehole logging data is found to be generally possible, but risks remain that the ranking based on the ANN training performance does not fully coincide with the closeness of geophysical tomograms to ground truth. Since geophysical field data sets do usually not offer control options similar to those used in our synthetic database, we do not recommend the utilization of recurrent ANNs to learn weights for the individual geophysical tomograms used in the prediction procedure.     

Hydrogeological assessment of the Tabarteh fault zone by physicochemical analysis and multivariate statistical methods

Hydrogeologically, faults may impede, conduit, exert no influence, or may play a combination of these roles on groundwater flow. The object of this paper is to study the hydrogeological role of the Tabarteh fault, which is located on the border of Zagros and Central Iran tectonic zones in an alluvial aquifer. The recorded data of water table levels, chemical parameters, and discharge rate of wells, in addition to geological maps and geophysical results, were collected and evaluated. The outcrop of travertine in limited areas and the emergence of a few small springs within the alluvium show a barrier role of the fault in the groundwater flow. The spatial analysis of chemical components, head time series, and groundwater flow direction assessment demonstrated that the fault acts as both a barrier and a non-barrier in different sections. The multivariate statistical methods of cluster and discriminant analyses also confirm the dual role of the fault.     

Local site effect of a clay site in Shiraz based on seismic hazard of Shiraz Plain

Propagation of seismic waves through soil layers would drastically change the frequency content and amplitude-based features of ground motions at the surface. These alterations are known as seismic site effects. Computation of site effects of high-populated areas such as large cities is of great importance (e.g., it is used in development of seismic microzonation of a region). Shiraz is one of the most populous cities of Iran and is located in a high seismic hazardous region. A representative clay site in this city is selected to assess local site effects. The time series and random vibration theory procedure in the frequency domain are implemented to analyze the aforementioned site. Furthermore, the nonlinear dynamic soil behavior is simulated by the equivalent linear method and the nonlinear method via DEEPSOIL program. Three types of soil column uncertainties such as shear wave velocity, modulus reduction, and damping ratio of soil layers as well as depth of underlying rock half-space (D _bed) are considered herein. The mean amplification and standard deviation of natural logarithm of amplification factors are computed for a variety of analysis types. The results of the current study show that the computed mean and standard deviation of amplification factor in ln units by considering only V _S uncertainty are in good agreement with the corresponding ones by considering V _S and modulus reduction and damping ratio variabilities simultaneously for the studied site. Furthermore, it seems that the effect of bedrock depth in definition of spectral shapes of the Iranian seismic building code should be taken into account.     

Flash flood susceptibility mapping using a novel deep learning model based on deep belief network,back propagation and genetic algorithm

Flash floods are responsible for loss of life and considerable property damage in many countries.Flood susceptibility maps contribute to flood risk reduction in areas that are prone to this hazard if appropriately used by landuse planners and emergency managers.The main objective of this study is to prepare an accurate flood susceptibility map for the Haraz watershed in Iran using a novel modeling approach(DBPGA) based on Deep Belief Network(DBN) with Back Propagation(BP) algorithm optimized by the Genetic Algorithm(GA).For this task, a database comprising ten conditioning factors and 194 flood locations was created using the One-R Attribute Evaluation(ORAE) technique.Various well-known machine learning and optimization algorithms were used as benchmarks to compare the prediction accuracy of the proposed model.Statistical metrics include sensitivity,specificity accuracy, root mean square error(RMSE), and area under the receiver operatic characteristic curve(AUC) were used to assess the validity of the proposed model.The result shows that the proposed model has the highest goodness-of-fit(AUC = 0.989) and prediction accuracy(AUC = 0.985), and based on the validation dataset it outperforms benchmark models including LR(0.885), LMT(0.934), BLR(0.936), ADT(0.976), NBT(0.974), REPTree(0.811), ANFIS-BAT(0.944), ANFIS-CA(0.921), ANFIS-IWO(0.939), ANFIS-ICA(0.947), and ANFIS-FA(0.917).We conclude that the DBPGA model is an excellent alternative tool for predicting flash flood susceptibility for other regions prone to flash floods.     

Extraction of velocity pulses of pulse-like ground motions using empirical Fourier decomposition

Journal of Seismology - Pulse-like ground motions may have only a distinct strong pulse or multiple pulses within the velocity time-history. These intrinsic pulses are hidden in low-frequency...     

Probabilistic analysis of soil‐structure interaction effects on the seismic performance of structures

This paper revisits the phenomenon of dynamic soil‐structure interaction (SSI) with a probabilistic approach. For this purpose, a twofold objective is pursued. First, the effect of SSI on inelastic response of the structure is studied considering the prevailing uncertainties. Second, the consequence of practicing SSI provisions of the current seismic design codes on the structural performance is investigated in a probabilistic framework. The soil‐structure system is modeled by the sub‐structure method. The uncertainty in the properties of the soil and the structure is described by random variables that are input to this model. Monte Carlo sampling analysis is employed to compute the probability distribution of the ductility demand of the structure, which is selected as the metrics for the structural performance. In each sample, a randomly generated soil‐structure system is subjected to a randomly selected and scaled ground motion. To comprehensively model the uncertainty in the ground motion, a suite of 3269 records is employed. An extensive parametric study is conducted to cover a wide range of soil‐structure systems. The results reveal the probability that SSI increases the ductility demand of structures designed based on the conventional fixed‐based assumption but built on flexible soil in reality. The results also show it is highly probable that practicing SSI provisions of modern seismic codes increase the ductility demand of the structure. Copyright © 2016 John Wiley & Sons, Ltd.     

Artificial recharge efficiency assessment by soil water balance and modelling approaches in a multi-layered vadose zone in a dry region

To assess recharge through floodwater spreading, three wells, approx. 30 m deep, were dug in a 35-year-old basin in southern Iran. Hydraulic parameters of the layers were measured. One well was equipped with pre-calibrated time domain reflectometry (TDR) sensors. The soil moisture was measured continuously before and after events. Rainfall, ponding depth and the duration of the flooding events were also measured. Recharge was assessed by the soil water balance method, and by calibrated (inverse solution) HYDRUS-1D. The results show that the 15 wetting front was interrupted at a layer with fine soil accumulation over a coarse layer at the depth of approx. 4 m. This seemed to occur due to fingering flow. Estimation of recharge by the soil water balance and modelling approaches showed a downward water flux of 55 and 57% of impounded floodwater, respectively.     

Comparing grain size distribution of sediment and original soil under raindrop detachment and raindrop-induced and flow transport mechanism

The grain size distribution (GSD) of sediment in comparison with the original soil GSD is discussed under different slopes (5, 15 and 25%) and rainfall intensities (30, 60 and 90 mm h^–1 with respective duration of 30, 15 and 10 min) but identical runoff (15 mm). The sediment quantification was carried out by raindrop-induced flow transport (RIFT) or/and transport by flow (FT) using a rainfall simulator and a 6 × 1 m² erosion plot and a silt loam. The results show a high degree of enrichment for size classes of 2–4 and 4–8 μm and a high degree of depletion for size classes of >63 μm under different slopes and rainfall intensities. In addition, the results show that the experimental enrichment ratio (ER) for particle size <16 μm under different slopes and rainfall intensities was greater than 1, while the ER for particle size >32 μm was less than 1.