首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 78 毫秒
1.
This article employs Support Vector Machine (SVM) and Relevance Vector Machine (RVM) for prediction of Evaporation Losses (E) in reservoirs. SVM that is firmly based on the theory of statistical learning theory, uses regression technique by introducing ε‐insensitive loss function has been adopted. RVM is based on a Bayesian formulation of a linear model with an appropriate prior that results in a sparse representation. The input of SVM and RVM models are mean air temperature (T) ( °C), average wind speed (WS) (m/sec), sunshine hours (SH)(hrs/day), and mean relative humidity (RH) (%). Equations have been also developed for prediction of E. The developed RVM model gives variance of the predicted E. A comparative study has also been presented between SVM, RVM and ANN models. The results indicate that the developed SVM and RVM can be used as a practical tool for prediction of E. Copyright © 2011 John Wiley & Sons, Ltd.  相似文献   

2.
This paper proposes to use least square support vector machine (LSSVM) and relevance vector machine (RVM) for prediction of the magnitude (M) of induced earthquakes based on reservoir parameters. Comprehensive parameter (E) and maximum reservoir depth (H) are used as input variables of the LSSVM and RVM. The output of the LSSVM and RVM is M. Equations have been presented based on the developed LSSVM and RVM. The developed RVM also gives variance of the predicted M. A comparative study has been carried out between the developed LSSVM, RVM, artificial neural network (ANN), and linear regression models. Finally, the results demonstrate the effectiveness and efficiency of the LSSVM and RVM models.  相似文献   

3.
The forecasting of evaporative loss (E) is vital for water resource management and understanding of hydrological process for farming practices, ecosystem management and hydrologic engineering. This study has developed three machine learning algorithms, namely the relevance vector machine (RVM), extreme learning machine (ELM) and multivariate adaptive regression spline (MARS) for the prediction of E using five predictor variables, incident solar radiation (S), maximum temperature (T max), minimum temperature (T min), atmospheric vapor pressure (VP) and precipitation (P). The RVM model is based on the Bayesian formulation of a linear model with appropriate prior that results in sparse representations. The ELM model is computationally efficient algorithm based on Single Layer Feedforward Neural Network with hidden neurons that randomly choose input weights and the MARS model is built on flexible regression algorithm that generally divides solution space into intervals of predictor variables and fits splines (basis functions) to each interval. By utilizing random sampling process, the predictor data were partitioned into the training phase (70 % of data) and testing phase (remainder 30 %). The equations for the prediction of monthly E were formulated. The RVM model was devised using the radial basis function, while the ELM model comprised of 5 inputs and 10 hidden neurons and used the radial basis activation function, and the MARS model utilized 15 basis functions. The decomposition of variance among the predictor dataset of the MARS model yielded the largest magnitude of the Generalized Cross Validation statistic (≈0.03) when the T max was used as an input, followed by the relatively lower value (≈0.028, 0.019) for inputs defined by the S and VP. This confirmed that the prediction of E utilized the largest contributions of the predictive features from the T max, verified emphatically by sensitivity analysis test. The model performance statistics yielded correlation coefficients of 0.979 (RVM), 0.977 (ELM) and 0.974 (MARS), Root-Mean-Square-Errors of 9.306, 9.714 and 10.457 and Mean-Absolute-Error of 0.034, 0.035 and 0.038. Despite the small differences in the overall prediction skill, the RVM model appeared to be more accurate in prediction of E. It is therefore advocated that the RVM model can be employed as a promising machine learning tool for the prediction of evaporative loss.  相似文献   

4.
The complexity of the evapotranspiration process and its variability in time and space have imposed some limitations on previously developed evapotranspiration models. In this study, two data‐driven models: genetic programming (GP) and artificial neural networks (ANNs), and statistical regression models were developed and compared for estimating the hourly eddy covariance (EC)‐measured actual evapotranspiration (AET) using meteorological variables. The utility of the investigated data‐driven models was also compared with that of HYDRUS‐1D model, which makes use of conventional Penman–Monteith (PM) model for the prediction of AET. The latent heat (LE), which is measured using the EC method, is modelled as a function of five climatic variables: net radiation, ground temperature, air temperature, relative humidity, and wind speed in a reconstructed landscape located in Northern Alberta, Canada. Several ANN models were evaluated using two training algorithms of Levenberg–Marquardt and Bayesian regularization. The GP technique was used to generate mathematical equations correlating AET to the five climatic variables. Furthermore, the climatic variables, as well as their two‐factor interactions, were statistically analysed to obtain a regression equation and to indicate the climatic factors having significant effect on the evapotranspiration process. HYDRUS‐1D model as an available physically based model was examined for estimating AET using climatic variables, leaf area index (LAI), and soil moisture information. The results indicated that all three proposed data‐driven models were able to approximate the AET reasonably well; however, GP and regression models had better generalization ability than the ANN model. The results of HYDRUS‐1D model exhibited that a physically based model, such as HYDRUS‐1D, might be comparable or even inferior to the data‐driven models in terms of the overall prediction accuracy. Based on the developed GP and regression models, net radiation and ground temperature had larger contribution to the AET process than other variables. Copyright © 2010 John Wiley & Sons, Ltd.  相似文献   

5.
This paper discusses the evaluation of liquefaction potential of soil based on standard penetration test (SPT) dataset using evolutionary artificial intelligence technique, multi-gene genetic programming (MGGP). The liquefaction classification accuracy (94.19%) of the developed liquefaction index (LI) model is found to be better than that of available artificial neural network (ANN) model (88.37%) and at par with the available support vector machine (SVM) model (94.19%) on the basis of the testing data. Further, an empirical equation is presented using MGGP to approximate the unknown limit state function representing the cyclic resistance ratio (CRR) of soil based on developed LI model. Using an independent database of 227 cases, the overall rates of successful prediction of occurrence of liquefaction and non-liquefaction are found to be 87, 86, and 84% by the developed MGGP based model, available ANN and the statistical models, respectively, on the basis of calculated factor of safety (F s ) against the liquefaction occurrence.  相似文献   

6.
Seismic site coefficients (F s ) for Imphal city have been estimated based on 700 synthetically generated earthquake time histories through stochastic finite fault method, considering various combinations of magnitudes and fault distances that may affect Imphal city. Seismic hazard curves and Uniform Hazard Response Spectra (UHRS) are presented for Imphal city. F s have been estimated based on site response analyses through SHAKE-91 for a period range of engineering interest (PGA to 3.0 s), for 5% damping. F s were multiplied by UHRS values to obtain surface level spectral acceleration with 2 and 10% probability of exceedance in 50 year (～2500 and ～500 year) return period. Comparison between predicted mean surface level response spectra and IS-1893 code shows that spectral acceleration value is higher for longer periods (i.e., >1.0 s), for ～500 year return period, and lower for periods shorter than 0.2 s for ～2500 year return period.  相似文献   

7.
This paper presented trend analysis of droughts in Kerala, Telangana, and Orissa meteorological subdivisions in India and proposed a framework for drought prediction by employing the Empirical Mode Decomposition (EMD)‐based prediction models. The study used 3‐month standardized precipitation index (SPI3) for drought analysis. The trend analysis of SPI3 series for the period 1871–2012 using Mann–Kendall method showed statistically significant increasing trend in Kerala and Telangana subdivisions and a decreasing trend in Orissa subdivision. In addition, the non‐linear trend component extracted from EMD showed statistically significant changes in all the three subdivisions. Then, the study proposed a hybrid approach for prediction of short‐term droughts by coupling multivariate extension of EMD (MEMD) with stepwise linear regression (SLR) and genetic programming (GP) methods. First, the multivariate dataset comprising the SPI3 series of current and lagged time steps are decomposed using the MEMD. Then, SLR/GP models are developed to predict each subseries of SPI3 of desired time step considering the subseries of predictor variables at the corresponding timescales as inputs. The resulting models at different timescales are recombined to obtain the SPI3 values of the desired time step. The method is applied for prediction of short‐term droughts in the three subdivisions. The results obtained by the hybrid models are compared with that obtained by conventional prediction models using M5 Model Trees and GP. The rigorous performance evaluation based on multiple statistical criteria clearly exhibited the superiority of the hybrid approaches (i.e., prediction models with MEMD‐based decomposition over models without decomposition) for prediction of SPI3 in three subdivisions. Further, the study found that MEMD‐GP model performs marginally better than the MEMD‐SLR model due to its efficacy in modelling high frequency modes.  相似文献   

8.
Soil detachment in concentrated flow is due to the dislodging of soil particles from the soil matrix by surface runoff. Both aggregate stability and shear strength of the topsoil reflect the erosion resistance of soil to concentrated runoff, and are important input parameters in predicting soil detachment models. This study was conducted to develop a formula to predict soil detachment rate in concentrated flow by using the aggregate stability index (As), root density (Rd) and saturated soil strength (σs) in the subtropical Ultisols region of China. The detachment rates of undisturbed topsoil samples collected from eight cultivated soil plots were measured in a 3.8 m long, 0.2 m wide hydraulic flume under five different flow shear stresses (τ = 4.54, 9.38, 15.01, 17.49 and 22.54 Pa). The results indicated that the stability index (As) was well related with soil detachment rate, particularly for results obtained with high flow shear stress (22.54 Pa), and the stability index (As) has a good linear relationship with concentrated flow erodibility factors (Kc). There was a positive linear relationship between saturated soil strength (σs) and critical flow shear stress (τc) for different soils. A significant negative exponential relationship between erodibility factors (Kc) and root density (Rd) was detected. This study yielded two prediction equations that allowed comparison of their efficiency in assessing soil detachment rate in concentrated flow. The equation including the root density (Rd) may have a better correlation coefficient (R2 = 0.95). It was concluded that the formula based on the stability index (As), saturated soil strength (σs) and root density (Rd) has the potential to improve methodology for assessing soil detachment rate in concentrated flow for the subtropical Chinese Ultisols. Copyright © 2012 John Wiley & Sons, Ltd.  相似文献   

9.
Lasaga's model [Lasaga, A.C., 1983. Geospeedometry: an extension of geothermometry. In: Saxena, S.K. (Ed.), Kinetics and Equilibrium in Mineral Reactions. Spring, New York, pp. 82–114.] to estimate cooling rate (s=dT/dt), as other analytical formulations available in the literature for instance the work of Dodson, M.H., 1976 [Dodson, M.H., 1976. Kinetic processes and thermal history of slowly cooling solids. Nature, 259, 551–553; Dodson, M.H., 1986. Closure profiles in cooling systems. Mat. Sci. Forum 7, 145–154.] can be difficult to apply to natural rocks for two reasons: (i) heavy numerical computations; (ii) the choice of the appropriate set of diffusion data. We propose a new formulation of Lasaga's equation which is simpler to use and less tight in the choice of a particular experimental data set. It is based on `frozen in' diffusion profiles in mineral pairs which are chemically isolated from the rest of the host rock. In this model, ions are exchanged by solid-state diffusion through the common surface of coexisting minerals. Our method approximates the shape of the elemental concentration profiles after cooling to an error function (with an effective diffusion coefficient Deff), as most of the variation of C(x) from rim (x=0) to core (x=d) occurs over a distance 0<x<a (a is the `characteristic diffusion length' of the profile: a≈3√(Defft)). Our analytical formula to calculate s is straightforward to use. It allows excellent estimates of s as long as 2a<d when the grain size is large compared to diffusion distances. For small grain sizes, we give another analytical formula that evaluates s at the value strial. We show by how much strial underestimates s. Expressing cooling rates s requires diffusion parameters Do and E (the pre-exponential factor and activation energy of diffusion). Available experimental data of (Do,E) are scattered due to different experimental conditions (T, fO2, mineral compositions). Therefore geospeedometric results range widely. It had been long noticed that the (Do,E) pairs are linearly correlated. This correlation can be expressed as the `compensation law' [Hart, S.R., 1981. Diffusion compensation in natural silicates. Geochim. Cosmochim. Acta 45, 200–215.]. We give the compensation law for Fe/Mg interdiffusion in two minerals used in geospeedometry, olivines and garnets. We show that implementing the `compensation law' into the analytical expression of cooling rate gives final s value consistent with all the (Do,E) experimental data sets and consequently greatly reduces the uncertainty on cooling rate (s or strial).  相似文献   

10.
Near-surface soil CO2 gas-phase concentration (C) and concomitant incident rainfall (Pi) and through-fall (Pt) depths were collected at different locations in a temperate pine forest every 30 min during the 2005 and 2006 growing seasons (and then averaged to the daily timescale). At the daily scale, C temporal variations were well described by a sequence of monotonically decreasing functions interrupted by large positive jumps induced by rainfall events. A stochastic model was developed to link rainfall statistics responsible for these jumps to near-surface C dynamics. The model accounted for the effect of daily rainfall variability, both in terms of timing and amount of water, and permitted an analytical derivation of the C probability density function (pdf) using the parameters of the rainfall pdf. Given the observed positive correlation between daily C and soil CO2 fluxes to the atmosphere (Fs), the effects of various rainfall regimes on the statistics of Fs can be deduced from the behavior of C under different climatic conditions. The predictions from this analytical model are consistent with flux measurements reported in manipulative experiments that varied rainfall amount and frequency.  相似文献   

11.
In recognition of the non‐linear relationship between storage and discharge existing in most river systems, non‐linear forms of the Muskingum model have been proposed, together with methods to calibrate the model parameters. However, most studies have focused only on routing a typical hypothetical flood hydrograph characterized by a single peak. In this study, we demonstrate that the storage–discharge relationship adopted for the non‐linear Muskingum model is not adequate for routing flood hydrographs in natural channels, which are often characterized by multiple peaks. As an alternative, an evolutionary algorithm‐based modelling approach, i.e. genetic programming (GP), is proposed, which is found to route complex flood hydrographs accurately. The proposed method is applied for constructing a routing model for a channel reach along the Walla Walla River, USA. The GP model performs extremely well with a root‐mean‐square error (RMSE) of 0·73 m3 s?1 as against an RMSE of 3·26 m3 s?1 for routing the multi‐peaked hydrograph. The advantage of GP lies in the fact that, unlike other models, it establishes the routing relationship in an easy and simple mathematical form. Copyright © 2007 John Wiley & Sons, Ltd.  相似文献   

12.
The various useful source-parameter relations between seismic moment and common use magnitude lg(M 0) andM s,M L,m b; between magnitudesMs andM L,M s andm b,M L andm b; and between magnitudeM s and lg(L) (fault length), lg (W) (fault width), lg(S) (fault area), lg(D) (average dislocation);M L and lg(f c) (corner frequency) have been derived from the scaling law which is based on an “average” two-dimensional faulting model of a rectangular fault. A set of source-parameters can be estimated from only one magnitude by using these relations. The average rupture velocity of the faultV r=2.65 km/s, the total time of ruptureT(s)=0.35L (km) and the average dislocation slip rateD=11.4 m/s are also obtained. There are four strong points to measure earthquake size with the seismic moment magnitudeM w.
  1. The seismic moment magnitude shows the strain and rupture size. It is the best scale for the measurement of earthquake size.
  2. It is a quantity of absolute mechanics, and has clear physical meaning. Any size of earthquake can be measured. There is no saturation. It can be used to quantify both shallow and deep earthquakes on the basis of the waves radiated.
  3. It can link up the previous magnitude scales.
  4. It is a uniform scale of measurement of earthquake size. It is suitable for statistics covering a broad range of magnitudes. So the seismic moment magnitude is a promising magnitude and worth popularization.
  相似文献   

13.
  相似文献   

14.
The current paper deals with the evaluation of the BANCS erosion prediction model and its two componentsethe Bank Erosion Hazard Index(BEHI)and Near-Bank Stress(NBS)indices.To construct the erosion prediction curves,18 experimental sections were established on the Kubrica Stream,district of Trencín,Slovakia.Each section was assessed through the NBS index and BEHI index and real annual bank erosion was measured using erosion toe pins.Subsequently,the relations between the BEHI and real annual bank erosion was assessed through regression and correlation analyses.The relation proved to be moderately strong,with the correlation coefficient(R)reaching 0.47.Further,the relation between the NBS index and real annual bank erosion was evaluated,which was also moderately strong,with R=0.65.Based on the measured data,two erosion prediction curves were constructed,the first for moderate BEHI,with R=0.69 and coefficient of determination(R2)of 0.47 and the second for high BEHI with R=0.74 and R2=0.55.The prediction curves were based on data from one year of measurements and can,therefore,be used only for discharges that occurred within that year and in the region where the model was developed.In the current case,according to runoff Curve Numbers(CN),the real culmination discharge was Q=1.88 m3/s,which is roughly equivalent to 1.5-year recurrence interval flow(Q1.5).  相似文献   

15.
—Northeastern Venezuela has been studied in terms of coda wave attenuation using seismograms from local earthquakes recorded by a temporary short-period seismic network. The studied area has been separated into two subregions in order to investigate lateral variations in the attenuation parameters. Coda-Q ?1 (Q c ?1) has been obtained using the single-scattering theory. The contribution of the intrinsic absorption (Q i ?1) and scattering (Q s ?1) to total attenuation (Q t ?1) has been estimated by means of a multiple lapse time window method, based on the hypothesis of multiple isotropic scattering with uniform distribution of scatterers. Results show significant spatial variations of attenuation the estimates for intermediate depth events and for shallow events present major differences. This fact may be related to different tectonic characteristics that may be due to the presence of the Lesser Antilles subduction zone, because the intermediate depth seismic zone may be coincident with the southern continuation of the subducting slab under the arc.  相似文献   

16.
Assessment of potential climate change impacts on stream water temperature (Ts) across large scales remains challenging for resource managers because energy exchange processes between the atmosphere and the stream environment are complex and uncertain, and few long‐term datasets are available to evaluate changes over time. In this study, we demonstrate how simple monthly linear regression models based on short‐term historical Ts observations and readily available interpolated air temperature (Ta) estimates can be used for rapid assessment of historical and future changes in Ts. Models were developed for 61 sites in the southeastern USA using ≥18 months of observations and were validated at sites with longer periods of record. The Ts models were then used to estimate temporal changes in Ts at each site using both historical estimates and future Ta projections. Results suggested that the linear regression models adequately explained the variability in Ts across sites, and the relationships between Ts and Ta remained consistent over 37 years. We estimated that most sites had increases in historical annual mean Ts between 1961 and 2010 (mean of +0.11 °C decade?1). All 61 sites were projected to experience increases in Ts from 2011 to 2060 under the three climate projections evaluated (mean of +0.41 °C decade?1). Several of the sites with the largest historical and future Ts changes were located in ecoregions home to temperature‐sensitive fish species. This methodology can be used by resource managers for rapid assessment of potential climate change impacts on stream water temperature. Copyright © 2014 John Wiley & Sons, Ltd.  相似文献   

17.
Predicting the geometry of channels and alluvial rivers is of primary importance in river engineering science. Appropriately designing channels and predicting stable river cross‐sections can decrease costs and prevent the destruction of installations and agricultural land by rivers. Consequently, researchers have applied different empirical and regression methods to achieve relations for predicting stable channel and river geometry. In this study, Group Method of Data Handling ]GMDH) models are used to predict three geometric variables of stable channels, namely width (w), depth (h) and slope (s). The effect of different input parameters, such discharge (Q), median grain size (d50) and the Shields parameter (τ*) on the GMDH models is assessed with regard to predicting stable channel geometry. The results indicate that the GMDH model with mean absolute percentage error (MAPE) of 5.53%, 4.05% and 4.89% for channel width, depth and slope prediction respectively, exhibits good accuracy. Moreover, a comparison of the GMDH models with previous theoretical equations (based on regression analysis) indicates the superiority of GMDH model performance, with error reductions of one‐fifth, one‐eighth and one‐sixth compared with the regression equations for channel width, depth and slope prediction, respectively. Copyright © 2016 John Wiley & Sons, Ltd.  相似文献   

18.
《Journal of Hydrology》2006,316(1-4):184-194
A semi-analytical model for the estimate of expected areal-average infiltration rate at hillslope scale is presented. It accounts for spatial heterogeneity of the saturated hydraulic conductivity, Ks, and rainfall rate, r. The Ks field is characterized by a lognormal probability density function while the rainfall rate r is represented by a uniform distribution between two extreme values. The model formulation relies upon the use of cumulative infiltration as the independent variable which is then expressed as a function of an expected time for use in practical applications. The solution is applicable for those ranges of r and Ks that allow for neglecting the infiltration of surface water running downslope into pervious soils (run-on process). The model was tested by comparisons with Monte Carlo simulations carried out for a variety of coefficients of variation of r and Ks over a clay loam soil and a sandy loam soil. The model was found to be very reliable both with coupled spatial variability of r and Ks and when only one variable is characterized by spatial heterogeneity while the other is uniform.  相似文献   

19.
In this study, foF2 data obtained from an equatorial station in West Africa were subjected to an occurrence probability distribution test. This was done on an hourly basis, for all the 24 h of the day. The results show that the probability (Np) of predicting foF2 within the range±of a standard deviation (σ) centered on the mean (μ) is ⩾0.68 is at least about 70% of the hourly set of data considered in this study irrespective of time of the day, season or solar cycle period. The distribution is not, however, perfectly symmetrically distributed around the mean. The seasonal hourly averages of foF2 were compared with those of IRI predictions. The IRI representation was found to be very good at low and moderate solar activity for both day and nighttime when the ITU-R coefficients are used. This is also true of the daytime at high solar activity. The night time prediction is only fairly good when the URSI coefficients are used for the prediction.  相似文献   

20.
A theoretical model of grain size variation of domain transitions in titanomagnetite (x = 0.6) as a function of oxidation (z) is presented. The superparamagnetic (SP) to single-domain (SD) transition ds, the SD to two-domain (TD) transition d0, the TD to three-domain (3D) transition and the pseudo-single domain (PSD) to multi-domain (MD) transition are calculated as a function of z. It is shown that all the transition grain sizes increase with z, except for the PSD-MD transition for z > 0.6. The calculations predict that ds increases from 0.044 to 0.197 μm, d0 increases from 0.54 to 13 μm, the TD-3D transition increases from 1.6 to 49 μm as z varies from 0 to 0.8. The PSD-MD transition increases from 42 μm at z = 0 to 150 μm at z = 0.6, whereas between z = 0.6 to z = 0.8, the PSD-MD transition decreases to 49 μm. Qualitatively, the model explains some of the trends in magnetic properties of submarine basalts with low-temperature oxidation. Quantitatively, the model does give reasonable estimates of the PSD-MD boundary and d0, which are close to the experimental values for x = 0.6 and z = 0. Furthermore, the model predicts that psarks or two-domain grains could be the major contributors to the remanence of oxidized submarine pillow basalts.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号