This study challenges the use of three nature‐inspired algorithms as learning frameworks of the adaptive‐neuro‐fuzzy inference system (ANFIS) machine learning model for short‐term modeling of dissolved oxygen (DO) concentrations. Particle swarm optimization (PSO), butterfly optimization algorithm (BOA), and biogeography‐based optimization (BBO) are employed for developing predictive ANFIS models using seasonal 15 min data collected from the Rock Creek River in Washington, DC. Four independent variables are used as model inputs including water temperature (T), river discharge (Q), specific conductance (SC), and pH. The Mallow's Cp and R2 parameters are used for choosing the best input parameters for the models. The models are assessed by several statistics such as the coefficient of determination (R2), root‐mean‐square error (RMSE), Nash–Sutcliffe efficiency, mean absolute error, and the percent bias. The results indicate that the performance of all‐nature‐inspired algorithms is close to each other. However, based on the calculated RMSE, they enhance the accuracy of standard ANFIS in the spring, summer, fall, and winter around 13.79%, 15.94%, 6.25%, and 12.74%, respectively. Overall, the ANFIS‐PSO and ANFIS‐BOA provide slightly better results than the other ANFIS models. 相似文献
One of the crucial components in seismic hazard analysis is the estimation of the maximum earthquake magnitude and associated uncertainty. In the present study, the uncertainty related to the maximum expected magnitude μ is determined in terms of confidence intervals for an imposed level of confidence. Previous work by Salamat et al. (Pure Appl Geophys 174:763-777, 2017) shows the divergence of the confidence interval of the maximum possible magnitude mmax for high levels of confidence in six seismotectonic zones of Iran. In this work, the maximum expected earthquake magnitude μ is calculated in a predefined finite time interval and imposed level of confidence. For this, we use a conceptual model based on a doubly truncated Gutenberg-Richter law for magnitudes with constant b-value and calculate the posterior distribution of μ for the time interval Tf in future. We assume a stationary Poisson process in time and a Gutenberg-Richter relation for magnitudes. The upper bound of the magnitude confidence interval is calculated for different time intervals of 30, 50, and 100 years and imposed levels of confidence α?=?0.5, 0.1, 0.05, and 0.01. The posterior distribution of waiting times Tf to the next earthquake with a given magnitude equal to 6.5, 7.0, and 7.5 are calculated in each zone. In order to find the influence of declustering, we use the original and declustered version of the catalog. The earthquake catalog of the territory of Iran and surroundings are subdivided into six seismotectonic zones Alborz, Azerbaijan, Central Iran, Zagros, Kopet Dagh, and Makran. We assume the maximum possible magnitude mmax?=?8.5 and calculate the upper bound of the confidence interval of μ in each zone. The results indicate that for short time intervals equal to 30 and 50 years and imposed levels of confidence 1???α?=?0.95 and 0.90, the probability distribution of μ is around μ?=?7.16???8.23 in all seismic zones. 相似文献
A review and analysis of post-stack time-lapse time-shifts has been carried out that covers published literature supplemented by in-house datasets available to the authors. Time-shift data are classified into those originating from geomechanical effects and those due to fluid saturation changes. From these data, conclusions are drawn regarding the effectiveness of post-stack time-shifts for overburden and reservoir monitoring purposes. A variety of field examples are shown that display the range and magnitude of variation for each class of application. The underlying physical mechanisms creating these time-shifts are then described, and linked to a series of generic and field-specific rock physics calculations that predict their magnitudes. These calculations serve as a guide for practitioners wishing to utilize this information on their own datasets. Conclusions are drawn regarding the reliability of this attribute for monitoring purposes, and the extent to which further development is required and how it should be reported by authors. 相似文献
River confluences (RCs) are important features within river systems where the three dimensional (3D) flow structures and the downstream mixing of flows can cause deep scour holes. Despite this, few methods have been proposed to control scouring at RCs. In this study, application of a collar was experimentally examined for local scour control at the point where two rivers flow together. In parti-cular, experimental tests were done with and without collar application at three different locations. The results reveal that the scour depth is directly proportional to the discharge ratio, i.e. the ratio of lateral discharge to that in the channel downstream of the confluence, and the densimetric Froude number (Frg). In addition, installation of a collar at RCs can decrease the scour depth up to 100%, thus completely avoiding the scour process. The results also show that by increasing the Frg the optimal installation location for a collar changes and moves towards the river bed level. Using a collar can also reduce the height of the point bar formed downstream of the confluence. The outcomes of the study allow deri-vation of an equation for predicting scour depth when a collar is applied as a countermeasure. The analysis of this equation shows that the estimates are mostly affected by the Frg. 相似文献
Active geological and young faulted zones have made Iran’s territory one of the most seismological active areas in the world according to recent historical earthquakes. Some of the deadliest earthquakes such as Gilan 1990 and Kermanshah 2018 caused tens of thousands fatalities. If such violent earthquakes affect strategical structures of a country, indirect losses would be more concerning than direct losses. Nowadays there is no doubt about the vital role of tunnels and underground structures in urban areas. These facilities serve as nonstop functional structures for human transportation, water and sewage systems and underground pedestrian ways. Any external hazard subjected to underground spaces, such as earthquake could directly affect passenger’s lives and significantly decrease whole system reliability of public transportation. Commonly two earthquake levels of intensities, Maximum Design Earthquake (MDE) and Operating Design Earthquake (ODE) were used in seismic design of underground structures. However, uncertain nature of earthquakes in terms of frequency content, duration of strong ground motion, and level of intensity indicate that only the two levels of earthquake (ODE and MDE) cannot cover the all range of possible seismic responses of structures during a probable earthquake. It is important to evaluate the behavior of tunnel under a wide range of earthquake intensities. For this purpose, a practical risk-based approach which is obtained using the total probability rule was used. This study illustrates a framework for evaluation seismic stability of tunnels. Urban railway tunnels of Tehran, Shiraz, Ahwaz, Mashhad, Isfahan and Tabriz were considered as study cases. Nominal value of seismic risk for three main damage states, including minor, moderate and major were calculated. 相似文献
We present an updated Lagrangian continuum particle method based on smoothed particle hydrodynamics (SPH) for simulating debris flow on an instrumented test slope. The site is a deforested area near the village of Ruedlingen, a community in the canton of Schaffhausen in Switzerland. Artificial rainfall experiments were conducted on the slope that led to failure of the sediment in the form of a debris flow. We develop a 3D mechanistic model for this test slope and conduct numerical simulations of the flow kinematics using an SPH formulation that captures large deformation, material nonlinearity, and the complex post-failure movement of the sediment. Two main simulations explore the impact of changes in the mechanical properties of the sediment on the ensuing kinematics of the flow. The first simulation models the sediment as a granular homogeneous material, while the second simulation models the sediment as a heterogeneous material with spatially varying cohesion. The variable cohesion is meant to represent the effects of root reinforcement from vegetation. By comparing the numerical solutions with the observed failure surfaces and final free-surface geometries of the debris deposit, as well as with the observed flow velocity, flow duration, and hot spots of strain concentration, we provide insights into the accuracy and robustness of the SPH framework for modeling debris flows.
Natural Hazards - One of the requirements for planning and decision-making to develop the infrastructures is to prepare the landslide occurrence hazard map. For this purpose, in this article, the... 相似文献
A simple displacement-type block model is proposed to compute the compression–load–time response of an idealized seismic buffer placed against a rigid wall and used to attenuate earthquake-induced dynamic loads. The seismic buffer is modelled as a linear elastic material and the soil wedge shear surface by a stress-dependent linear spring. The model is shown to capture the trends observed in four physical reduced-scale model shaking table tests carried out with similar boundary conditions up to a base excitation level of about 0.7g. In most cases, quantitative predictions are in reasonable agreement with physical test results. The model is simple and provides a possible framework for the development of advanced models that can accommodate more complex constitutive laws for the component materials and a wider range of problem geometry. 相似文献
Summary. Long-period tidal records from eight ports on the west coast of Great Britain are analysed, using both the harmonic method and the response function. Time series up to 9.5 yr were used so that fine structure of certain regions of high energy in the tidal residual spectrum may be examined. This also assisted in accurate separation of tides from surges. According to the currently accepted formulation of M1, its composition is not compatible with its actual composition in the real tide and, as such, has no useful purpose to serve in computation of predictions. Constituents Sa, Ssa, MA, and MB, are adversly affected by weather and long records are essential for their accurate separation. It has been observed that annual perturbations of S2, similar to those confirmed in recent years for M2, also exist but these are not readily recognisable because their speeds are the same as those of constituents T2 and R2. These perturbations, being highly sensitive to meteorological forces, are mainly responsible for cusps or humps in the vicinity of major tidal constituents in tidal residual spectra. The relationship of radiational and gravitational tides is found to be in very good agreement with theoretical results. In summer months non-predictable variance reduces to about half of the annual variance, reflecting the regional weather conditions of summer and winter. 相似文献