A Comparison of Machine Learning Techniques for Modeling River Flow Time Series: The Case of Upper Cauvery River Basin

Models of river flow time series are essential in efficient management of a river basin. It helps policy makers in developing efficient water utilization strategies to maximize the utility of scarce water resource. Time series analysis has been used extensively for modeling river flow data. The use of machine learning techniques such as support-vector regression and neural network models is gaining increasing popularity. In this paper we compare the performance of these techniques by applying it to a long-term time-series data of the inflows into the Krishnaraja Sagar reservoir (KRS) from three tributaries of the river Cauvery. In this study flow data over a period of 30 years from three different observation points established in upper Cauvery river sub-basin is analyzed to estimate their contribution to KRS. Specifically, ANN model uses a multi-layer feed forward network trained with a back-propagation algorithm and support vector regression with epsilon intensive-loss function is used. Auto-regressive moving average models are also applied to the same data. The performance of different techniques is compared using performance metrics such as root mean squared error (RMSE), correlation, normalized root mean squared error (NRMSE) and Nash-Sutcliffe Efficiency (NSE).

Probable maximum precipitation estimation for catchments in Mahanadi river basin

Probable maximum precipitation (PMP) is a theoretical concept that is widely used by hydrologists to arrive at estimates for probable maximum flood (PMF) that find use in planning, design and risk assessment of high-hazard hydrological structures such as flood control dams upstream of populated areas. The PMP represents the greatest depth of precipitation for a given duration that is meteorologically possible for a watershed or an area at a particular time of year, with no allowance made for long-term climatic trends. Various methods are in use for estimation of PMP over a target location corresponding to different durations. Moisture maximization method and Hershfield method are two widely used methods. The former method maximizes the observed storms assuming that the atmospheric moisture would rise up to a very high value estimated based on the maximum daily dew point temperature. On the other hand, the latter method is a statistical method based on a general frequency equation given by Chow. The present study provides one-day PMP estimates and PMP maps for Mahanadi river basin based on the aforementioned methods. There is a need for such estimates and maps, as the river basin is prone to frequent floods. Utility of the constructed PMP maps in computing PMP for various catchments in the river basin is demonstrated. The PMP estimates can eventually be used to arrive at PMF estimates for those catchments. (C) 2015 The Authors. Published by Elsevier B.V.

Use of Data Driven Techniques for Short Lead Time Streamflow Forecasting in Mahanadi basin

Streamflow forecasts at daily time scale are necessary for effective management of water resources systems. Typical applications include flood control, water quality management, water supply to multiple stakeholders, hydropower and irrigation systems. Conventionally physically based conceptual models and data-driven models are used for forecasting streamflows. Conceptual models require detailed understanding of physical processes governing the system being modeled. Major constraints in developing effective conceptual models are sparse hydrometric gauge network and short historical records that limit our understanding of physical processes. On the other hand, data-driven models rely solely on previous hydrological and meteorological data without directly taking into account the underlying physical processes. Among various data driven models Auto Regressive Integrated Moving Average (ARIMA), Artificial Neural Networks (ANNs) are most widely used techniques. The present study assesses performance of ARIMA and ANNs methods in arriving at one-to seven-day ahead forecast of daily streamflows at Basantpur streamgauge site that is situated at upstream of Hirakud Dam in Mahanadi river basin, India. The ANNs considered include Feed-Forward back propagation Neural Network (FFNN) and Radial Basis Neural Network (RBNN). Daily streamflow forecasts at Basantpur site find use in management of water from Hirakud reservoir. (C) 2015 The Authors. Published by Elsevier B.V.

Wear Behavior of Cooling Slope Rheocast A356 Al Alloy

In the present study, the dry sliding wear behavior of rheocast A356 Al alloys, cast using a cooling slope, as well as gravity cast A356 Al alloy have been investigated at a low sliding speed of 1ms(-1), against a hardened EN 31 disk at different loads. The wear mechanism involves microcutting-abrasion and adhesion at lower load for all of the alloys studied in the present work. On the other hand, at higher load, mainly adhesive wear along with oxide formation is observed for gravity cast A356 Al alloy and rheocast A356 Al alloy, cast using a 45 degrees slope angle. Unlike other alloys, 60 degrees slope rheocast A356 Al alloy is found to undergo mainly abrasive wear at higher load. Accordingly, the rheocast sample, cast using a 60 degrees cooling slope, exhibits a remarkably lower wear rate at higher load compared to gravity cast and 45 degrees slope rheocast samples. This is attributed to the dominance of abrasive wear at higher load in the case of rheocast A356 Al alloy cast using a 60 degrees slope. The presence of finer and more spherical primary Al grain morphology is found to resist adhesive wear in case of 60 degrees cooling slope processed rheocast alloy and thereby delay the transition of the wear regime from normal wear to severe wear.

Evaluation of Precipitation Retrievals From Orbital Data Products of TRMM Over a Subtropical Basin in India

The spatial error structure of daily precipitation derived from the latest version 7 (v7) tropical rainfall measuring mission (TRMM) level 2 data products are studied through comparison with the Asian precipitation highly resolved observational data integration toward evaluation of the water resources (APHRODITE) data over a subtropical region of the Indian subcontinent for the seasonal rainfall over 6 years from June 2002 to September 2007. The data products examined include v7 data from the TRMM radiometer Microwave Imager (TMI) and radar precipitation radar (PR), namely, 2A12, 2A25, and 2B31 (combined data from PR and TMI). The spatial distribution of uncertainty from these data products were quantified based on performance metrics derived from the contingency table. For the seasonal daily precipitation over a subtropical basin in India, the data product of 2A12 showed greater skill in detecting and quantifying the volume of rainfall when compared with the 2A25 and 2B31 data products. Error characterization using various error models revealed that random errors from multiplicative error models were homoscedastic and that they better represented rainfall estimates from 2A12 algorithm. Error decomposition techniques performed to disentangle systematic and random errors verify that the multiplicative error model representing rainfall from 2A12 algorithm successfully estimated a greater percentage of systematic error than 2A25 or 2B31 algorithms. Results verify that although the radiometer derived 2A12 rainfall data is known to suffer from many sources of uncertainties, spatial analysis over the case study region of India testifies that the 2A12 rainfall estimates are in a very good agreement with the reference estimates for the data period considered.

Numerical Analysis of Rainfall Infiltration in the Slope with a Fracture

With the finite volume method, a 2D numerical model for seepage in unsaturated soil has been established to study the rainfall infiltration in the fractured slope.The result shows that more rain may infiltrate into the slope due to existing fracture and then the pore pressure rises correspondingly. Very probably, it is one of the crucial factors accounting for slope failure. Furthermore a preliminary study has been conducted to investigate the influence of various fracture and rainfall factors such as the depth, width and location of a crack, surface condition, rainfall intensity and duration. Pore pressure and water volumetric content during the transient seepage are carefully examined to reveal the intrinsic mechanism.

Effect of Rock Mass Structure and Block Size on the Slope Stability-Physical Modeling and Discrete Element Simulation

This paper studies the stability of jointed rock slopes by using our improved three-dimensional discrete element methods (DEM) and physical modeling. Results show that the DEM can simulate all failure modes of rock slopes with different joint configurations. The stress in each rock block is not homogeneous and blocks rotate in failure development. Failure modes depend on the configuration of joints. Toppling failure is observed for the slope with straight joints and sliding failure is observed for the slope with staged joints. The DEM results are also compared with those of limit equilibrium method (LEM). Without considering the joints in rock masses, the LEM predicts much higher factor of safety than physical modeling and DEM. The failure mode and factor of safety predicted by the DEM are in good agreement with laboratory tests for any jointed rock slope.

三峡永久船闸高边坡开挖三维离散元数值模拟:3-D Simulation of the Excavation of High Steep Slope of Three-Gorges Permanent Lock by Distinct Element Method

采用面一面接触的三维离散元刚性块体模型,从实测节理面中取出其中的三组,按照其倾向、倾角和节理间距将三峡永久船闸未开挖的区域划分为10~5个离散单元,通过施加力边界条件,给出了与实测初始地应力场接近的数值模拟结果；然后,分4步模拟了永久船闸的开挖过程。计算结果表明：开挖过程会引起节理面出现张开趋势,个别岩体还会沿着节理面滑移。岩体位移的不对称现象较为自然地说明了由节理引起的岩体各向异性特征。

Effect of Microtopography, Slope Length and Gradient, and Vegetative Cover on Overland Flow Through Simulation

Overland flow on a hillslope is significantly influenced by its microtopography, slope length and gradient, and vegetative cover. A 1D kinematic wave model in conjunction with a revised form of the Green-Ampt infiltration equation was employed to evaluate the effect of these surface conditions. The effect of these conditions was treated through the resistance parameter in the kinematic wave model. The resistance in this paper was considered to be made up of grain resistance, form resistance, and wave resistance. It was found that irregular slopes with microtopography eroded more easily than did regular slopes. The effect of the slope gradient on flow velocity and flow shear stress could be negative or positive. With increasing slope gradient, the flow velocity and shear stress first increased to a peak value, then decreased again, suggesting that there exists a critical slope gradient for flow velocity and shear stress. The vegetative cover was found to protect soil from erosion primarily by enhancing erosion-resisting capacity rather than by decreasing the eroding capability of overland flow.

Mechanism on Progressive Failure of a Faulted Rock Slope Due to Slip-Weakening

Slip-weakening is one of the characteristics of geological materials under certain loadings. Non-uniform rock structure may exist in the vicinity of the slip surface for a rock slope. Some portion of the slip surface may be penetrated but the other not. For the latter case, the crack or the fault surface will undergo shear deformation before it becomes a successive surface under a certain loading. As the slipped portion advances,slip-weakening occurs over a distance behind the crack tip. In the weakening zone, the shear strength will decrease from its peak value to residual friction level. The stress will redistribute along the surface of crack and in the weakening zone. Thus the changed local stress concentration leads the crack to extend and the ratio of penetration of the slip surface to increase. From the view of large-scale for the whole slip surface, the shear strength will decrease due to the damage of interior rock structure, and the faulted rock behaves as a softening material. Such a kind of mechanism performs in a large number of practical landslides in the zones experienced strong earthquakes. It should be noted that the mechanism mentioned above is different from that of the breakage of structural clay,in which the geological material is regarded as a medium containing structural lumps and structural bands. In this paper, the softening behavior of a faulted rock should be regarded as a comprehensive result of the whole complicated process including slip-weakening, redistribution of stress, extension of crack tip, and the penetration of the slip surface. This process is accompanied by progressive failure and abrupt structural damage. The size of slip-weakening zone is related to the undergoing strain. Once the relative slide is initiated (local or integrated), the effect of slip-weakening will behave in a certain length behind the crack tip until the formation of the whole slip surface.

Experimental study on pore pressure in rock-soil slope during reservoir water level fluctuation

A test system was developed for measuring the pore pressure in porous media, and a new model was devised for the pore pressure testing in both saturated and unsaturated rock-soil. Laboratory experiments were carried out to determine the pore pressure during water level fluctuation. The variations of transient pore pressure vs. time at different locations of the simulated rock-soil system were acquired and processed, and meanwhile the deformation and failure of the model are observed. The experiment results show that whether the porous media are saturated or not, the transient pore pressure is mainly dependent on the water level fluctuation, and coupled with the variation of the stress field.

An Extension of 2D Janbu’s Generalized Procedure of Slices for 3D Slope Stability Analysis II—Numerical Method and Applications

This paper provides a numerical approach on achieving the limit equilibrium method for 3D slope stability analysis proposed in the theoretical part of the previous paper. Some programming techniques are presented to ensure the maneuverability of the method. Three examples are introduced to illustrate the use of this method. The results are given in detail such as the local factor of safety and local potential sliding direction for a slope. As the method is an extension of 2D Janbu's generalized procedure of slices (GPS), the results obtained by GPS for the longitudinal sections of a slope are also given for comparison with the 3D results. A practical landslide in Yunyang, the Three Gorges, of China, is also analyzed by the present method. Moreover, the proposed method has the advantages and disadvantages of GPS. The problem frequently encountered in calculation process is still about the convergency, especially in analyzing the stability of a cutting corner. Some advice on discretization is given to ensure convergence when the present method is used. However, the problem about convergency still needs to be further explored based on the rigorous theoretical background.

Numerical Analysis on Intermittent Flow in a Longitudinal Section of Bingham Fluid along a Slope

The transition process of intermittent flow in a longitudinal section of Bingham fluid from initial distribution to fully developed state was numerically investigated in this paper. The influences of slope dimensionless runoff Q* and viscosity μ0* on the dimensionless surge speed U* were also presented in a wide range of parameters. By one typical example, the intermittent flow possessed wave characteristics and showed a supercritical flow conformation for a fully developed flow. The distributions of gravity and bed drag along the flow path and the velocity distribution of flow field were also analyzed.

Evaluation of termination techniques for 4H-SiC PiN diodes and trench JFETs

An investigation concerning suitable termination techniques for 4H-SiC trench JFETs is presented. Field plates, p+ floating rings and junction termination extension techniques are used to terminate 1.2kV class PiN diodes. The fabricated PiN diodes evaluated here have a similar design to trench JFETs. Therefore, the conclusions for PiN diodes can be applied to JFET structures as well. Numerical simulations are also used to illustrate the effect of the terminations on the diodes' blocking mode behaviour.