排序方式： 共有8条查询结果，搜索用时 15 毫秒
1
1.
Artificial neural networks have a wide application in many areas of science and engineering and, particularly, in geotechnical
problems with some degree of success due to the fact that the mechanical behavior of rocks are not salient. They are highly
nonlinear, quite complex and complicated. While applying neural network in such complicated problems, epoch determination
is based on hit-and-trail basis mainly. In this paper, the effect of different number of epochs is shown on the network and
a method is proposed to determine the optimum number of epoch with the help of self-organized map (SOM) to avoid overtraining
of the network. Data distribution is also done with the help of SOM and a statistical analysis is made to show consistency
between training and testing dataset for ensuring the optimal model performance. 相似文献
2.
Shivam?Raj?Singh Atma?Prakash Budhaditya?Hazra Ajit?Sarmah Ankit?Garg Hong-Hu?ZhuEmail author 《Stochastic Environmental Research and Risk Assessment (SERRA)》2018,32(12):3541-3559
Vegetation is known to influence the hydrological state variables, suction \( \left( \psi \right) \) and volumetric water content (\( \theta_{w} \)) of soil. In addition, vegetation induces heterogeneity in the soil porous structure and consequently the relative permeability (\( k_{r} \)) of water under unsaturated conditions. The indirect method of utilising the soil water characteristic curve (SWCC) is commonly adopted for the determination of \( k_{r} \). In such cases, it is essential to address the stochastic behaviour of SWCC, in order to conduct a robust analysis on the \( k_{r} \) of vegetative cover. The main aim of this study is to address the uncertainties associated with \( k_{r} \), using probabilistic analysis, for vegetative covers (i.e., grass and tree species) with bare cover as control treatment. We propose two approaches to accomplish the aforesaid objective. The univariate suction approach predicts the probability distribution functions of \( {\text{k}}_{\text{r}} \), on the basis of identified best probability distribution of suction. The bivariate suction and water content approach deals with the bivariate modelling of the water content and suction (SWCC), in order to capture the randomness in the permeability curves, due to presence of vegetation. For this purpose, the dependence structure of \( \psi \) and \( \theta_{w} \) is established via copula theory, and the \( k_{r} \) curves are predicted with respect to varying levels of \( \psi - \theta_{w} \) correlation. The results showed that the \( k_{r} \) of vegetative covers is substantially lower than that in bare covers. The reduction in \( k_{r} \) with drying is more in tree cover than grassed cover, since tree roots induce higher levels of suction. Moreover, the air entry value of the soil depends on the magnitude of \( \psi - \theta_{w} \) correlation, which in turn, is influenced by the type of vegetation in the soil. \( k_{r} \) is found to be highly uncertain in the desaturation zone of the relative permeability curve. The stochastic behaviour of \( k_{r} \) is found to be most significant in tree covers. Finally, a simplified case study is also presented in order to demonstrate the impact of the uncertainty in \( k_{r} \), on the stability of vegetates slopes. With an increment in the parameter \( \alpha \), factor of safety (FS) is found to decrease. The trend of FS is reverse of this with parameter \( n \). Overall FS is found to vary around 4–5%, for both bare and vegetative slopes. 相似文献
3.
H. K. Pandey Shivam Dwivedi Kamlesh Kumar 《Journal of the Geological Society of India》2018,92(3):286-290
Flood is common phenomena worldwide since time immemorial. Recently the change in climatic parameters has drastically affected the pattern and magnitude of flood. India being one of the tropical country face flood and drought situations every year, therefore it needs accurate assessment and forecast of flood for proper management of natural resources.An attempt has been made through the present study which consists frequency analysis on maximum daily discharge data in Betwa river at Basoda, Mohana and Shahijina gauging stations in Madhya Pradesh state using Gumbel’s Extreme value distribution and Log Pearson Type-3 distribution for 20 years period (1993-2012).The result shows that Log Pearson Type-3 distribution is better suited for Betwa basin. The results can be used by civil engineers for deciding the dimensions of hydraulic structures such as spillways, dams, bridges etc. Floods are forecasted for the different return periods for Betwa river. 相似文献
4.
Shivam Goyal Manish Kumar Sarma Arup Kumar 《Theoretical and Applied Climatology》2017,129(3-4):1175-1187
This study focuses on changes in the maximum and minimum temperature over the Subansiri River basin for different climate change scenarios. For the study, dataset from Intergovernmental Panel on Climate Change (IPCC) fifth assessment report (AR5) (i.e., coupled model intercomparison project phase five (CMIP5) dataset with representative concentration pathway (RCP) scenarios) were utilized. Long-term (2011–2100) maximum temperature (T max) and minimum temperature (Tmin) time series were generated using the statistical downscaling technique for low emission scenario (RCP2.6), moderate emission scenario (RCP6.0), and extreme emission scenario (RCP8.5). Trends and change of magnitude in T max, T min, and diurnal temperature range (DTR) were analyzed for different interdecadal time scales (2011–2100, 2011–2040, 2041–2070, 2070–2100) using Mann-Kendall non-parametric test and Sen’s slope estimator, respectively. The temperature data series for the observed duration (1981–2000) has been found to show increasing trends in T max and T min at both annual and monthly scale. Trend analysis of downscaled temperature for the period 2011–2100 shows increase in annual maximum temperature and annual minimum temperature for all the selected RCP scenarios; however, on the monthly scale, T max and T min have been seen to have decreasing trends in some months.
相似文献5.
Natural Hazards - Regionalization on the basis of the properties of hydro-meteorological data helps in identifying the regions reflecting the similar characteristics which could be useful in... 相似文献
6.
Shivam Tripathi Rao S. Govindaraju 《Stochastic Environmental Research and Risk Assessment (SERRA)》2007,21(6):747-764
Recent advances in statistical learning theory have yielded tools that are improving our capabilities for analyzing large
and complex datasets. Among such tools, relevance vector machines (RVMs) are finding increasing applications in hydrology
because of (1) their excellent generalization properties, and (2) the probabilistic interpretation associated with this technique
that yields prediction uncertainty. RVMs combine the strengths of kernel-based methods and Bayesian theory to establish relationships
between a set of input vectors and a desired output. However, a bias–variance analysis of RVM estimates revealed that a careful
selection of kernel parameters is of paramount importance for achieving good performance from RVMs. In this study, several
analytic methods are presented for selection of kernel parameters. These methods rely on structural properties of the data
rather than expensive re-sampling approaches commonly used in RVM applications. An analytical expression for prediction risk
in leave-one-out cross validation is derived. For brevity, the effectiveness of the proposed methods is assessed first by
data generated from the benchmark sinc function, followed by an example involving estimation of hydraulic conductivity values
over a field based on observations. It is shown that a straightforward maximization of likelihood function can lead to misleading
results. The proposed methods are found to yield robust estimates of parameters for kernel functions. 相似文献
7.
Downscaling of precipitation for climate change scenarios: A support vector machine approach 总被引：7，自引：0，他引：7
The Climate impact studies in hydrology often rely on climate change information at fine spatial resolution. However, general circulation models (GCMs), which are among the most advanced tools for estimating future climate change scenarios, operate on a coarse scale. Therefore the output from a GCM has to be downscaled to obtain the information relevant to hydrologic studies. In this paper, a support vector machine (SVM) approach is proposed for statistical downscaling of precipitation at monthly time scale. The effectiveness of this approach is illustrated through its application to meteorological sub-divisions (MSDs) in India. First, climate variables affecting spatio-temporal variation of precipitation at each MSD in India are identified. Following this, the data pertaining to the identified climate variables (predictors) at each MSD are classified using cluster analysis to form two groups, representing wet and dry seasons. For each MSD, SVM- based downscaling model (DM) is developed for season(s) with significant rainfall using principal components extracted from the predictors as input and the contemporaneous precipitation observed at the MSD as an output. The proposed DM is shown to be superior to conventional downscaling using multi-layer back-propagation artificial neural networks. Subsequently, the SVM-based DM is applied to future climate predictions from the second generation Coupled Global Climate Model (CGCM2) to obtain future projections of precipitation for the MSDs. The results are then analyzed to assess the impact of climate change on precipitation over India. It is shown that SVMs provide a promising alternative to conventional artificial neural networks for statistical downscaling, and are suitable for conducting climate impact studies. 相似文献
8.
1