In this paper, an approach is presented to analyze the stability risk of rock slopes based on a new rating system. Three factors are used to estimate the risk level of rock slopes: (1) failure probability, (2) element at risk rating, and (3) vulnerability rating. Element at risk and vulnerability ratings are both given a range from 0 to 10, and the probability of failure is varied between 0 and 1, so the risk rating ranges between 0 and 100. This risk rating can be used to determine both the quantitative and qualitative risk levels of slopes at the same time. The method is tested on the western sector of the slopes facing Songun copper plant phase III, Iran, to clarify its procedures and assess its validity. Deterministic kinematic analyses showed that the slope has a potential for circular failure. Risk assessments revealed that the risk levels of the slope in both static and pseudo-static conditions are “very low” and “high,” respectively.
The longitudinal dispersion coefficient is a key element in determining the distribution and transmission of pollution, especially when cross-sectional mixing is completed. However, the existing predictive techniques for this purpose exhibit great amounts of uncertainty. The main objective of this study is to present a more accurate model for predicting longitudinal dispersion coefficient in natural rivers and streams. Bayesian network (BN) approach was considered in the modeling procedure. Two forms of input variables including dimensional and dimensionless parameters were examined to find the best model structure. In order to increase the performance of the model, the clustering method as a preprocessing data technique was applied to categorize the data in separate groups with similar characteristics. An expansive data set consisting of 149 field measurements was used for training and testing steps of the developed models. Three performance evaluation criteria were adopted for comparison of the results of the different models. Comparison of the present results with the artificial neural network (ANN) model and also well-known existing equations showed the efficiency of the present model. The performance of dimensionless BN model 30% is more than dimensional ones in terms of the root mean square error. The accuracy criterion was increased from 70 to 83% by performing clustering analysis on the BN model. The BN-cluster model 43% is more accurate than ANN model in terms of the accuracy criterion. The results indicate that the BN-cluster model give 16% better results than the best available considered model in terms of the accuracy criterion. The developed model provides a suitable approach for predicting pollutant transport in natural rivers. 相似文献
Landslides every year impose extensive damages to human beings in various parts of the world; therefore, identifying prone areas to landslides for preventive measures is essential. The main purpose of this research is applying different scenarios for landslide susceptibility mapping by means of combination of bivariate statistical (frequency ratio) and computational intelligence methods (random forest and support vector machine) in landslide polygon and point formats. For this purpose, in the first step, a total of 294 landslide locations were determined from various sources such as aerial photographs, satellite images, and field surveys. Landslide inventory was randomly split into a testing dataset 70% (206 landslide locations) for training the different scenarios, and the remaining 30% (88 landslides locations) was used for validation purposes. To providing landslide susceptibility maps, 13 conditioning factors including altitude, slope angle, plan curvature, slope aspect, topographic wetness index, lithology, land use/land cover, distance from rivers, drainage density, distance from fault, distance from roads, convergence index, and annual rainfall are used. Tolerance and the variance inflation factor indices were used for considering multi-collinearity of conditioning factors. Results indicated that the smallest tolerance and highest variance inflation factor were 0.31 and 3.20, respectively. Subsequently, spatial relationship between classes of each landslide conditioning factor and landslides was obtained by frequency ratio (FR) model. Also, importance of the mentioned factors was obtained by random forest (RF) as a machine learning technique. The results showed that according to mean decrease accuracy, factors of altitude, aspect, drainage density, and distance from rivers had the greatest effect on the occurrence of landslide in the study area. Finally, the landslide susceptibility maps were produced by ten scenarios according to different ensembles. The receiver operating characteristics, including the area under the curve (AUC), were used to assess the accuracy of the models. Results of validation of scenarios showed that AUC was varying from 0.668 to 0.749. Also, FR and seed cell area index indicators show a high correlation between the susceptibility classes with the landslide pixels and field observations in all scenarios except scenarios 10RF and 10SVM. The results of this study can be used for landslides management and mitigation and development activities such as construction of settlements and infrastructure in the future. 相似文献
Present active tectonics is affecting central Alborz and created various dynamic landforms in Buin Zahra-Avaj area, northern Iran. The area, located between the southern central Alborz and the edge of northwestern central Iran, is the result of both the Arabian–Eurasian convergence and clockwise rotation of the south Caspian Basin with respect to Eurasia in which most of the steep fault planes have a left lateral strike-slip component and most of the dip-slip faults are reverse, dipping SW. Since this region consists of several residential and industrial areas and includes several fault zones, the assessment of the structures of the present activity is vital. Six significant morphometric indices have been applied for this evaluation including stream length–gradient (SL), drainage basin asymmetry factor (Af), hypsometric integral (Hi), ratio of valley floor width to valley height (Vf), drainage basin shape (Bs), and mountain front sinuosity (Smf). The combined analyzed indices, represented through the relative tectonic activity (Iat), were used. The study area was divided into four regions according to the values of Iat. These classes include class 1 (very high activity,18%), class 2 (high, 20%), class 3 (moderate, 44%), and class 4 (low, 18%). The results of these indices are consistent with field observations on landforms and the deformation of Quaternary deposits. 相似文献
Local scour around piers is one of the main causes of bridge failures. In this study, three robust techniques, artificial neural networks (ANNs), M5-Tree, and Gene Expression Programming (GEP), were employed for prediction of scour depth around complex piers. The clear water condition was chosen for all experimental tests. The results indicated that pier diameter (bc) and foundation level (Y) are the main parameters for local scour. Furthermore, the minimum scour depth occurs in range of Y/bc = 1.1~1.3. In next step, to evaluate the mentioned techniques, a wide range of dataset was collected from the present study and literature. The radial base function (RBF) with R2 = 0.945 and RMSE = 0.031 provides better prediction in comparison with conventional equations, M5-Tree (R2 = 0.883, RMSE = 0.292) and the GEP techniques (R2 = 0.811 and RMSE = 0.263). The equations developed by M5-Tree and GEP are more useful for practical purposes and can be easily employed to predict the depth of scour at complex piers. 相似文献
In the present research, effect of silica fume as an additive and oil polluted sands as aggregates on compressive strength of concrete were investigated experimentally. The amount of oil in the designed mixtures was assumed to be constant and equal to 2% of the sand weight. Silica fume accounting for 10%, 15% and 20% of the weight is added to the designed mixture. After preparation and curing, concrete specimens were placed into the three different conditions: fresh, brackish and saltwater environments (submerged in fresh water, alternation of exposed in air & submerged in sea water and submerged in sea water). The result of compressive strength tests shows that the compressive strength of the specimens consisting of silica fume increases significantly in comparison with the control specimens in all three environments. The compressive strength of the concrete with 15% silica fume content was about 30% to 50% higher than that of control specimens in all tested environments under the condition of using polluted aggregates in the designed mixture. 相似文献
Natural Hazards - Vehicles can be easily swept away by floodwaters once the flow velocity and depth reach certain critical limits, with probabilities toward fatality reported to be nearly 50%.... 相似文献
Reservoir simulators model the highly nonlinear partial differential equations that represent flows in heterogeneous porous media. The system is made up of conservation equations for each thermodynamic species, flash equilibrium equations and some constraints. With advances in Field Development Planning (FDP) strategies, clients need to model highly complex Improved Oil Recovery processes such as gas re-injection and CO2 injection, which requires multi-component simulation models. The operating range of these simulation models is usually around the mixture critical point and this can be very difficult to simulate due to phase mislabeling and poor nonlinear convergence. We present a Machine Learning (ML) based approach that significantly accelerates such simulation models. One of the most important physical parameters required in order to simulate complex fluids in the subsurface is the critical temperature (Tcrit). There are advanced iterative methods to compute the critical point such as the algorithm proposed by Heidemann and Khalil (AIChE J 26,769–799, 1980) but, because these methods are too expensive, they are usually replaced by cheaper and less accurate methods such as the Li-correlation (Reid and Sherwood 1966). In this work we use a ML workflow that is based on two interacting fully connected neural networks, one a classifier and the other a regressor, that are used to replace physical algorithms for single phase labelling and improve the convergence of the simulator. We generate real time compositional training data using a linear mixing rule between the injected and the in-situ fluid compositions that can exhibit temporal evolution. In many complicated scenarios, a physical critical temperature does not exist and the iterative sequence fails to converge. We train the classifier to identify, a-priori, if a sequence of iterations will diverge. The regressor is then trained to predict an accurate value of Tcrit. A framework is developed inside the simulator based on TensorFlow that aids real time machine learning applications. The training data is generated within the simulator at the beginning of the simulation run and the ML models are trained on this data while the simulator is running. All the run-times presented in this paper include the time taken to generate the training data and train the models. Applying this ML workflow to real field gas re-injection cases suffering from severe convergence issues has resulted in a 10-fold reduction of the nonlinear iterations in the examples shown in this paper, with the overall run time reduced 2- to 10-fold, thus making complex FDP workflows several times faster. Such models are usually run many times in history matching and optimization workflows, which results in compounded computational savings. The workflow also results in more accurate prediction of the oil in place due to better single phase labelling.
