Shashi Mathur

Streamflow forecasting by SVM with quantum behaved particle swarm optimization

Accurate forecasting of streamflows has been one of the most important issues as it plays a key role in allotment of water resources. However, the information of streamflow presents a challenging situation; the streamflow forecasting involves a rather complex nonlinear data pattern. In the recent years, the support vector machine has been used widely to solve nonlinear regression and time series problems. This study investigates the accuracy of the hybrid SVM-QPSO model (support vector machine-quantum behaved particle swarm optimization) in predicting monthly streamflows. The proposed SVM-QPSO model is employed in forecasting the streamflow values of Vijayawada station and Polavaram station of Andhra Pradesh in India. The SVM model with various input structures is constructed and the best structure is determined using normalized mean square error (NMSE) and correlation coefficient (R). Further quantum behaved particle swarm optimization function is adapted in this study to determine the optimal values of SVM parameters by minimizing NMSE. Later, the performance of the SVM-QPSO model is compared thoroughly with the popular forecasting models. The results indicate that SVM-QPSO is a far better technique for predicting monthly streamflows as it provides a high degree of accuracy and reliability.

A hybrid SVM-PSO model for forecasting monthly streamflow

The long-term streamflow forecasts are very significant in planing and reservoir operations. The streamflow forecasts have to deal with a complex and highly nonlinear data patterns. This study employs support vector machines (SVMs) in predicting monthly streamflows. SVMs are proved to be a good tool for forecasting the nonlinear time series. But the performance of the SVM depends solely upon the appropriate choice of parameters. Hence, particle swarm optimization technique is employed in tuning SVM parameters. The proposed SVM-PSO model is used in forecasting the streamflow values of Swan River near Bigfork and St. Regis River near Clark Fork of Montana, United States. Further SVM model with various input structures is constructed, and the best structure is determined using various statistical performances. Later, the performance of the SVM model is compared with the autoregressive moving average model (ARMA) and artificial neural networks (ANNs). The results indicate that SVM could be a better alternative for predicting monthly streamflows as it provides a high degree of accuracy and reliability.

Soil Moisture Dynamics Modeling Considering the Root Compensation Mechanism for Water Uptake by Plants

A numerical model is developed in this study for simulating soil moisture flow in layered soil profile with plant growth. A dynamic root compensation mechanism (RCM) is used for a nonuniform root distribution pattern to compute water uptake by plants in a moisture scarce environment. The governing soil moisture flow equation integrated with the roots water uptake function is solved numerically by the implicit finite difference method coupled with the Picard iteration technique. The model is first tested for a barren layered soil profile using numerical simulation data available in the literature. A nonlinear function for water uptake by roots is then incorporated in the flow equation and the rate of water removal is simulated with and without considering the RCM for a characteristic example under optimal and water scare conditions. The model is finally applied to a rain-fed wheat (Triticum aestivum) field using a dynamic root growth model. The simulation considering the RCM shows better agreement with the...

Soil moisture flow modeling with water uptake by plants (wheat) under varying soil and moisture conditions.

A variably saturated soil moisture flow model is developed for planted soils with depth varying properties by incorporating a nonuniform macroscopic root water uptake function. The model includes spatial and temporal variation of the root density with dynamic root growth for simulating water uptake by plants along with the impact of soil moisture availability. The governing partial differential moisture flow equation integrated over the depth with a plant water uptake term is solved numerically by the implicit finite difference method using an iterative scheme. The model is first tested for barren soils for two profiles considering constant and depth varying soil characteristics under constant inflow condition. The results obtained are later tested with experimental data available in the literature. A nonuniform plant water uptake term is subsequently incorporated in the model and water uptake by wheat plants under different soil moisture availability conditions is studied. Finally, the moisture flow model is validated with field data of rain fed wheat Triticum aestivum using a dynamic root growth model for a layered root zone soil profile. The simulated soil moisture regime of the layered root zone shows a reasonably good agreement with the observed data.

Optimal design of an in-situ bioremediation system using support vector machine and particle swarm optimization

A methodology based on support vector machine and particle swarm optimization techniques (SVM-PSO) was used in this study to determine an optimal pumping rate and well location to achieve an optimal cost of an in-situ bioremediation system. In the first stage of the two stage methodology suggested for optimal in-situ bioremediation design, the optimal number of wells and their locations was determined from preselected candidate well locations. The pumping rate and well location in the first stage were subsequently optimized in the second stage of the methodology. The highly nonlinear system of equations governing in-situ bioremediation comprises the equations of flow and solute transport coupled with relevant biodegradation kinetics. A finite difference model was developed to simulate the process of in-situ bioremediation using an Alternate-Direction Implicit technique. This developed model (BIOFDM) yields the spatial and temporal distribution of contaminant concentration for predefined initial and boundary conditions. BIOFDM was later validated by comparing the simulated results with those obtained using BIOPLUME III for the case study of Shieh and Peralta (2005). The results were found to be in close agreement. Moreover, since the solution of the highly nonlinear equation otherwise requires significant computational effort, the computational burden in this study was managed within a practical time frame by replacing the BIOFDM model with a trained SVM model. Support Vector Machine which generates fast solutions in real time was considered to be a universal function approximator in the study. Apart from reducing the computational burden, this technique generates a set of near optimal solutions (instead of a single optimal solution) and creates a re-usable data base that could be used to address many other management problems. Besides this, the search for an optimal pumping pattern was directed by a simple PSO technique and a penalty parameter approach was adopted to handle the constraints in the PSO. The results showed that the costs involved in the proposed management solution were consistent with that resulting from other nontraditional optimization techniques which use embedded/linked bioremediation simulation models. Moreover, an optimal transient pumping strategy resulted in an overall reduction in pumping cost by almost 20% when compared to cases where a steady state pumping strategy was adopted. A considerable reduction in the number of simulations was achieved using the SVM approach.

Postclosure Long-Term Settlement for MSW Landfills

AbstractA mathematical model is developed to estimate the settlement attributable to biodegradation for municipal solid waste (MSW) landfills incorporating the effects of pH, temperature, and moisture content. The post closure long-term settlement is determined by combining mechanical compression and settlement attributable to biodegradation. The coefficient of mechanical compression was observed to be highly sensitive in the mechanical compression compared with temperature, pH, and moisture content in the biodegradation-induced settlement model. The developed model was validated with the field data. The biodegradation-induced settlement model was found to be a better result than the existing model.

Assessing the suitability of extreme learning machines (ELM) for groundwater level prediction

Abstract Fluctuation of groundwater levels around the world is an important theme in hydrological research. Rising water demand, faulty irrigation practices, mismanagement of soil and uncontrolled exploitation of aquifers are some of the reasons why groundwater levels are fluctuating. In order to effectively manage groundwater resources, it is important to have accurate readings and forecasts of groundwater levels. Due to the uncertain and complex nature of groundwater systems, the development of soft computing techniques (data-driven models) in the field of hydrology has significant potential. This study employs two soft computing techniques, namely, extreme learning machine (ELM) and support vector machine (SVM) to forecast groundwater levels at two observation wells located in Canada. A monthly data set of eight years from 2006 to 2014 consisting of both hydrological and meteorological parameters (rainfall, temperature, evapotranspiration and groundwater level) was used for the comparative study of the models. These variables were used in various combinations for univariate and multivariate analysis of the models. The study demonstrates that the proposed ELM model has better forecasting ability compared to the SVM model for monthly groundwater level forecasting.

Enhanced bioremediation of BTEX contaminated groundwater in pot-scale wetlands

Pot-scale wetlands were used to investigate the role of plants in enhancing the performance of engineered bioremediation techniques like biostimulation, bioaugmentation, and phytoremediation collectively. Canna generalis plants were grown hydroponically in BTEX contaminated groundwater supplied in wetland mesocosms. To quantify the contaminant uptake by the plants, wetlands with and without shoot biomass along with unplanted gravel bed were used under controlled conditions. The residual concentration of the selected BTEX compound, toluene, in the rhizosphere water was measured over the entire period of the experiment along with the water lost by evapotranspiration. The rate of biodegradation in all wetland mesocosms fitted best with the first-order kinetics. The total removal time of the BTEX compound was found to be highest in the unplanted gravel bed mesocosm followed by wetlands without and with shoot biomass. The cumulative uptake of toluene in shoot biomass of the wetland plants initially increased rapidly and started to decrease subsequently till it reached a peak value. Continuity equations integrated with biodegradation and plant uptake sink terms were developed to simulate residual concentration of toluene in rhizospheric water for comparison with the measured data for entire period of the experiments. The results of this research can be used to frame in situ plant-assisted bioremediation techniques for hydrocarbon-contaminated soil-water resources.

Groundwater level forecasting using SVM-PSO

The prediction of groundwater levels in a basin is of immense importance for the management of groundwater resources. In this study, support vector machines (SVMs) is used to construct a ground water level forecasting system. Further the proposed SVM-PSO model is employed in estimating the groundwater level of Rentachintala region of Andhra Pradesh in India. The SVM-PSO model with various input structures is constructed and the best structure is determined using the k-fold cross validation method. Further particle swarm optimisation function is adapted in this study to determine the optimal values of SVM parameters. Later, the performance of the SVM-PSO model is compared with the autoregressive moving average model (ARMA), artificial neural networks (ANN) and adaptive neuro fuzzy inference system (ANFIS). The results indicate that SVM-PSO is a far better technique for predicting groundwater levels as it provides a high degree of accuracy and reliability.

Groundwater level forecasting using SVM-QPSO

Forecasting the groundwater levels in a water basin plays a significant role in the the management of groundwater resources. In this study, Support Vector Machines (SVM) is used to construct a ground water level forecasting system. Further Quantum behaved Particle Swarm Optimization function is adapted in this study to determine the SVM parameters. Later, the proposed SVM-QPSO model is employed in estimating the groundwater level of Rentachintala region of Andhra Pradesh in India. The performance of the SVM-QPSO model is then compared with the ANN (Artificial Neural Networks). The results indicate that SVM-QPSO is a far better technique for predicting groundwater levels as it provides a high degree of accuracy and reliability.