排序方式： 共有23条查询结果，搜索用时 15 毫秒
1.
This paper evaluates the feasibility of using an artificial neural network (ANN) methodology for estimating the groundwater levels in some piezometers placed in an aquifer in north‐western Iran. This aquifer is multilayer and has a high groundwater level in urban areas. Spatiotemporal groundwater level simulation in a multilayer aquifer is regarded as difficult in hydrogeology due to the complexity of the different aquifer materials. In the present research the performance of different neural networks for groundwater level forecasting is examined in order to identify an optimal ANN architecture that can simulate the piezometers water levels. Six different types of network architectures and training algorithms are investigated and compared in terms of model prediction efficiency and accuracy. The results of different experiments show that accurate predictions can be achieved with a standard feedforward neural network trained usung the Levenberg–Marquardt algorithm. The structure and spatial regressions of the ANN parameters (weights and biases) are then used for spatiotemporal model presentation. The efficiency of the spatio‐temporal ANN (STANN) model is compared with two hybrid neural‐geostatistics (NG) and multivariate time series‐geostatistics (TSG) models. It is found in this study that the ANNs provide the most accurate predictions in comparison with the other models. Based on the nonlinear intrinsic ANN approach, the developed STANN model gives acceptable results for the Tabriz multilayer aquifer. Copyright © 2008 John Wiley & Sons, Ltd. 相似文献
2.
3.
4.
5.
Anisotropic emission of gravitational waves during the merger of black holes induces a recoil velocity on the centre of mass of the binary and the final merger product can then be ejected from its host galaxy. We consider ejected black holes which stay on bound orbits around their host haloes. A recoiled black hole which moves on an almost radial orbit outside the virial radius of its central galaxy, in the cold dark matter background, reaches its apapsis in a finite time. Due to small dark matter velocity dispersion at high redshifts and also the small black hole velocity near the apapsis passage a high-density wake forms around these black hole. Gamma-ray emission can result from the enhancement of dark matter annihilation in these wakes. The diffuse high-energy gamma-ray background from the ensemble of such black holes in the Hubble volume is also evaluated. 相似文献
6.
大歧口凹陷位于渤海湾盆地黄骅坳陷中北部,是中新生代叠合盆地中新生界沉积最厚的凹陷。本文基于大量二维、三维地震剖面和钻井资料,从凹陷主控断裂活动性、沉积沉降中心分布和构造格架等方面,侧重对大歧口凹陷新生代构造演化过程和原型盆地类型进行研究。认为:1)大歧口凹陷构造单元有4级,凹陷具有"东西分带、南北分块"的平面构造格局和北断南超箕状断陷的剖面结构。2)凹陷内断裂有4级,主要断裂的规模、活动期次和断裂活动具有演化的阶段性和空间的迁移性,典型构造带活动性具有由北往南迁移的特点。3)新生代期间整个大歧口凹陷的沉积沉降中心均在东部海域的歧口主凹内,但整体具有往南迁移的趋势。4)凹陷经历了拓展裂谷、拉分断陷、箕状断陷和碟状坳陷4个构造演化阶段,断陷阶段在整个构造演化时期意义重大,且具有走滑拉分特点。故认为大歧口凹陷原型盆地是一种"板内拉分盆地"。 相似文献
7.
Groundwater vulnerability modeling is an alternative approach to evaluate groundwater contamination especially in areas affected by intensive anthropogenic activities. However, the DRASTIC model as a well-known method to assess groundwater vulnerability suffers from the inherent uncertainty associated with its seven essential parameters. In this study, three different fuzzy logic (FL) models (Sugeno fuzzy logic, Mamdani fuzzy logic, and Larsen fuzzy logic) are adopted to improve the DRASTIC system to be more realistic. The vulnerability map of groundwater from multiple aquifer systems (i.e., karstic, alluvium, and complex) in Basara basin, Iraq, was created using the FL models. Validation of the FL models results using NO3-N concentration obtained from wells and springs of the study area indicating that all of the three FL models are applicable for improving the DRASTIC model. However, each of the FL models has its own advantages for groundwater vulnerability estimation in different types of aquifer systems in the Basara basin. Therefore, this study proposes the supervised committee fuzzy logic (SCFL) as a multimodel method to combine the advantages of individual FL models. The SCFL method confirms that no water well with high NO3-N levels would be classified as low risk and vice versa. The study suggests that this approach has provided a convenient estimation of pollution risk in the study area and therefore, a more accurate prediction of the intrinsic vulnerability to pollution in the multiple aquifer system can be achieved through SCFL method. 相似文献
8.
9.
It is expected that episodic tremors and slips (ETS) as a type of slow earthquakes with periodic property will be detected using harmonic estimation techniques. The principal goal of this paper is the detection of these kinds of earthquakes using least squares harmonic estimation (LSHE). To accomplish this, the raw time series of 38 permanent GPS stations of the Pacific Northwest Geodetic Array have been analyzed. Previously, some independent techniques could confirm the occurrences of the aforementioned quakes at these stations. However, the current research intends to evaluate the spectrum of each of the de-trended time series using the LS-HE method. In each station, the period of the detected harmonic with the maximum power spectrum is equivalent to the average period previously reported for these events. According to the obtained results, the recurrence interval of these events ranges from 9 months to 3 years. In sum, the study confirms this method being efficient for investigating the occurrences of ETSs when the length of the GPS time series is sufficiently large. 相似文献
10.
Modelling time series of groundwater levels is investigated by three fuzzy logic (FL) models, Sugeno (SFL), Mamdani (MFL) and Larsen (LFL), using data from observation wells. One novelty in the study is the re-use of these three models as multiple models through the following strategies: (a) simple averaging, (b) weighted averaging and (c) committee machine techniques; these are implemented using artificial neural networks (ANN). These strategies provide some evidence that (i) multiple models improve on the performance of individual models and those using committee machines perform better than the other two options; and (ii) committee machine models produce defensible modelling results to develop management scenarios. The study investigates water table declines through management scenarios and shows that in this aquifer water use has higher impacts on water table variations than climatic variations. This provides evidence of the need for planned management in the study area. 相似文献