Search

In this paper, the problem of site characterization is treated as a task of function approximation of the large existing data from standard penetration tests (SPTs) in three-dimensional subsurface of Bangalore, India. More than 2,700 field SPT values (N) has been collected from 766 boreholes spread over an area of 220-km2 area in Bangalore, India. To get N corrected value (Nc), N values have been corrected for different parameters such as overburden stress, size of borehole, type of sampler, length of connected rod. In three-dimensional analysis, the function Nc=Nc(X,Y,Z), where X, Y, and Z are the coordinates of a point corresponds to Nc value, is to be approximated with which Nc value at any half-space point in Bangalore, India can be determined. An attempt has been made to develop artificial neural network (ANN) model using multilayer perceptrons that are trained with Levenberg-Marquardt back-propagation algorithm. Also, a geostatistical model based on ordinary kriging technique has been adopted. The knowledge of the semivariogram of the Nc values is used in the ordinary kriging method to predict the Nc values at any point in the subsurface of Bangalore, India where field measurements are not available. The results obtained show that ANN model is fairly accurate in predicting Nc values. In case of ordinary kriging, a new type of cross-validation analysis shows that it is a robust model for prediction of Nc values. A comparison between the ANN and geostatistical model demonstrates that the ANN model is superior to Geostatistical model in predicting Nc values in the subsurface of Bangalore, India. [ABSTRACT FROM AUTHOR]

Treating the occurrence and severity of droughts as random, a hybrid model, combining a linear stochastic model and a nonlinear artificial neural network (ANN) model, is developed for drought forecasting. The hybrid model combines the advantages of both stochastic and ANN models. Using the Standardized Precipitation Index series, the hybrid model as well as the individual stochastic and ANN models were applied to forecast droughts in the Kansabati River basin in India, and their performances were compared. The hybrid model was found to forecast droughts with greater accuracy. [ABSTRACT FROM AUTHOR]

Evaporation in reservoirs plays a prominent role in water resources planning, operation, and management because a considerable amount of water is lost through evaporation, especially in large reservoirs. Estimating evaporation from surface water usually requires ample data that are not easily measurable. At present, in India, reservoir evaporation is estimated from the pan evaporation and average water spread area. Because reservoir evaporation exhibits a nonlinear relationship with the reservoir storage and other meteorological parameters, accurate prediction of evaporation by the conventional method is a cumbersome process. Recently evolved data-driven techniques will excel in nonlinear processes modeling. In this study, reservoir evaporation is predicted using three different data-driven techniques-artificial neural network (ANN), model tree (MT), and genetic programming (GP)-by time-series modeling. The daily Koyna reservoir evaporation prediction models are developed using 49 years of daily evaporation data. Approximately 70% of the data set is used for training the model, and the remaining 30% is used for testing. From this study, all of the data-driven techniques predicted the reservoir evaporation very accurately, with better performance and a correlation of approximately 0.99. This shows that if the input data series exhibits a good pattern with less noise, the data-driven techniques result in better performances. Among the data-driven techniques used in this study, GP predicts the reservoir evaporation slightly better than ANN and MT models. [ABSTRACT FROM AUTHOR]

All reservoirs are subjected to sediment inflow and deposition to a certain extent resulting in reduction of their capacity. Trap efficiency (Te), a most important parameter for reservoir sedimentation studies, is being estimated using conventional empirical methods till today. A limited research has been carried out on estimating the variation of Te with time. In the present study, an attempt has been made to incorporate the age of the reservoir to estimate the Te. This study investigates the suitability of conventional empirical approaches along with soft computing data-driven techniques to estimate the reservoir Te. The incorporation of reservoir age, in empirical model, has resulted in a better Te estimation. Further, to estimate Te at different time steps, soft computing approaches such as artificial neural networks (ANNs) and genetic programming (GP) have been attempted. Based on correlation analysis, it was found that ANN model (4-4-1) resulted better than conventional empirical methods but inferior to GP. The results show that the GP model is parsimonious and understandable and is well suited to estimate Te of a large reservoir. [ABSTRACT FROM AUTHOR]

Conventional methods and models available for estimation of reservoir sedimentation process differ greatly in terms of complexity, inputs, and other requirements. An artificial neural network (ANN) model was used to estimate the volume of sediment retained in a reservoir. Annual rainfall, annual inflow, and capacity of the reservoir were chosen as inputs. Thirty Two years of data pertaining to Gobindsagar Reservoir on the Satluj River in India, were used in this study (23 years for training and 9 years for testing). The pattern of the sediment volume retained in this reservoir was well captured by the Multi-Layer Perceptron (3–5-1) ANN model using the back propagation algorithm. Based on several performance indices, it was found that the ANN model estimated the volume of sediment retained in the reservoir with better accuracy and less effort as compared to conventional regression analysis. [ABSTRACT FROM AUTHOR]