Theses

Browse

Search Results

Now showing 1 - 9 of 23

Open Access
Forecasting of daily reference evapotranspiration using artificial neural network, adaptive neuro-fuzzy inference system and multiple linear regression
(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-07) Sah, Namrata; Kashyap, P.S.
Open Access
Analysis of spatio-temporal trends of rainfall in Jodhpur and Kota zones of Rajasthan
(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-06) Yogesh Kumar; Anil Kumar
The trend is one of the deterministic components of a time series. The trend component is described as long term or regular fluctuation in a time series, on an average basis, which could either be increasing or decreasing in nature. The anthropogenic and climatic activities influence many hydrometeorological processes in a persistent manner, whose effect emerges in form of trends in rainfall, temperature, evapo-transpiration, stream flows, etc. These trends may be with respect to time (temporal trend) and space (spatial trend). These trends in rainfall are of paramount importance for carrying out studies related to climate change aspects. The knowledge of trends in rainfall is extremely important for agricultural engineers, hydrologists, water scientists etc. Without studying trends it may sometimes lead to overestimation or underestimation of the parameters for the design and operation of water infrastructures, water stresses, water shortages and agricultural failures. Rajasthan is a state which covers north-western and western parts of Indian sub-continent. The state has always been under the threat of droughts and planning and management of water resources and agriculture becomes a crucial issue in the state. There should be proper management of water resources and agricultural operations to prevent such extreme events. Hence it is very important to study the nature of rainfall in form of trends both temporally and spatially. This study was conducted to analyze the temporal and spatial trends of annual and monsoonal rainfall, and annual rainy days in Jodhpur and Kota zones of Rajasthan. Non- Parametric statistical methods namely Mann-Kendall (MK) and Modified Mann-Kendall (MMK) test were employed for detection of temporal trends. The magnitude of the identified trends was assessed by using Theil-Sen slope estimator test. A recently proposed Innovative trend analysis (ITA) method was also used for detection of temporal trends. The turning point of potential trends was identified using Sequential Mann-Kendall (SQMK) test. The spatial analysis of trends was done using Inverse Distance Weighing (IDW) technique in GIS environment. On the basis of application of above methods, fluctuating trends of different magnitudes in both Jodhpur and Kota zones were identified, which could be possible due to climatic and anthropogenic activities taking place in the study area over the years. This could be a sign of climate change in the study area.
Open Access
Monthly rainfall modelling using ANN for central Telangana region
(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-06) Kota Spandana; Devendra Kumar
In the present study, artificial neural network technique has been employed to predict monthly rainfall for Medak, Khammam and Warangal stations of Central Telangana, India. Eighty five years of rainfall data (January, 1901 to December, 1985) were used for training of models and twenty eight years of rainfall data (January, 1986 to December, 2014) were used for testing of models. Gamma test, autocorrelation function and cross correlation function were used for selection of appropriate input variables. The ANN models were trained using multilayer perceptron with two learning rules i.e. Levenberg-Marquardt and Delta-bar-delta and two transfer functions viz. sigmoid axon and Tanh axon. The performance of the models was evaluated qualitatively by visual observation and quantitatively by using different performance indices viz. Root Mean Square Error, Correlation Coefficient, Coefficient of Efficiency, Percent Bias and Integral Square Error. It was observed that the better results of monthly rainfall prediction of developed models were observed when the rainfall data of adjoining stations were used as the input variable as compared the lagged rainfall of the same station. The higher value of Correlation Coefficient and Coefficient of Efficiency and lower value of Integral Square Error, Percent Bias and Root Mean Square Error suggest that the M-8 model, K-7 model and W-5 may be used to predict monthly rainfall of Medak, Khammam and Warangal stations respectively for Central Telangana region.
Open Access
Drought assessment based on standardized precipitation index and its forecasting using neural networks
(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-06) Rai, Priya; Singh, Praveen Vikram
Drought is one of the most important environmental problems affecting the planet. Drought means scarcity of water, which disturbs the entire ecosystem and adversely affects various sectors of society, e.g. agriculture, hydropower generation, water supply and industry. Occurrence of drought and its forecasting are critical components of hydrology which play a major role in risk management, drought preparedness and mitigation. The identification, characterization and monitoring of droughts are of great importance in water resources planning and management. Based on its nature, drought may be divided into four different categories, viz., metrological, agricultural, hydrological and socioeconomical. Of these, the meteorological drought signifies the paucity of rainfall over a region for a considerable period of time. Drought occurs in nearly all climatic zones of the world at one time or other, but this creeping phenomenon mostly affects tropics and adjoining regions. This study was conducted using the rainfall data for 44 years (1971-2014) of Parbhani district of Marathwada region with specific objectives to find the best fit probability distribution, determine occurrence of meteorological drought based on Standardized Precipitation Index (SPI) for different time scales, develop Multilayer Perceptron Neural Network (MLPNN) models and assess the performance of these models for meteorological drought forecasting. The data were used to determine best fit probability distribution among Normal, log Normal, Gamma distribution and Weibull distribution based on KS goodness of fit statistic at 1% and 5% level of significance. The rainfall data were used to calculate drought and wet conditions in the region based on SPI values considering time scales of 1-, 3-, 6-, 9-, 12- and 24-month for the best fit distribution. The forecasting of the occurrence of the drought based on SPI was done at considered time scales using Multilayer Perceptron Neural Network (MLPNN) models. The lag found for different time scales i.e., SPI-1, SPI-3, SPI-6, SPI-12 and SPI-24 were 1, 2, 4, 7, 8 and 12 respectively. The NeuroSolutions Software was used with Levenberg-Marquardt learning rule and activation function was hyperbolic tangent with range -1 to 1. The performance of developed models was assessed using statistical indices such as root mean squared error (RMSE), Coefficient of determination (R2) and Coefficient of efficiency (CE). The Normal and Gamma distribution were found to be the best fitted on the rainfall data, however, Gamma distribution had an edge over the Normal distribution. During the total period of 528 months (1971-2014), 32 extreme drought, 69 severe drought, 82 extreme wet and 160 severe wet events occurred. The multilayer perceptron neural network models can be used only for forecasting of long duration SPI. The network architecture 7-8-1, 8-11-1 and 12-9-1 can be used for SPI-9, -12 and -24 months respectively for the study area.
Open Access
Daily and weekly rainfall modelling using Artificial Neural Network
(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-08) Joshi, Neeraj; Devendra Kumar
Artificial Neural Network technique has been employed to predict daily and weekly rainfall for Nainital station of Uttarakhand, India. The meteorological data from year (2003 to 2013) were used for training of daily and weekly rainfall prediction models and meteorological data from (2014 to 2018) were used for testing of daily and weekly rainfall prediction models. Gamma test was used for the selection of appropriate input variables of daily and weekly rainfall prediction models. The ANN models were trained using multilayer perceptron with one learning rule i.e. Levenberg - Marquardt and two transfer functions viz. Tanh Axon and Sigmoid Axon. The performance of the models was evaluated qualitatively by visual observation and quantitatively using different performance indices viz. Root Mean Square Error, Correlation Coefficient, Coefficient of Efficiency, Percent Bias and Integral Square Error. It was observed that both Tahn Axon and Sigmoid Axon activation functions are capable of predicting the daily and weekly rainfall with almost equal prediction efficiency, for daily rainfall model structure of 5 – 8 – 8 - 1 with L evenberg – M arquardt and Tahn Axon, and model structure 5 -10 - 10-1 with Levenberg –M arquardt and Sigmoid Axon performed well. And, in case of weekly rainfall the model structure of 5 -10-10-1 was found to be working well in both the cases for Nainital station of Uttarakhand, India.
Open Access
Daily monsoon rainfall prediction using Artificial Neural Network (ANN) and Wavelet Based Artificial Neural Network (WANN) models
(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-07) Rawat, Amit; Pravendra Kumar
Rainfall is the most complex and difficult elements of hydrologic cycle to understand and to model due to the complexity of atmospheric processes. Long term Rainfall prediction is very important for countries whose economy depends mainly on agriculture. It is widely used in the energy industry for efficient resource planning and management including famine and disease control, rainwater catchment and ground water management. Considering these facts, a study has been carried out to assess the monsoon rainfall prediction in Parbhani Maharastara, India. The daily monsoon meteorological data of 30 years (1st June, 1985 – 30th Sept, 2014) were collected from meteorological observatory located at Vasantrao Naik Marathwada Krishi Vidyapeeth, Parbhani of Maharastra State, India. In the present study, Artificial Neural Network (ANN) and wavelet based Artificial Neural Network (WANN) techniques were used to predict the daily monsoon rainfall. The daily data for monsoon period (1st June to 30th September) of years 1985-2008 and 2008-2014 were used to train and test models, respectively. The best combination of input variables was selected on the basis of Gamma statistic. In case of ANN and WANN, back-propagation algorithm and tan sigmoid activation function were used to train and test the models. The performance of the models were evaluated qualitatively by visual observations and quantitatively using various performances indices Viz. RMSE, correlation coefficient, MSE, coefficient of efficiency and pooled average relative error. Finally, it can be concluded from the results that the performance of the WANN model is better than the ANN model.
Open Access
Sediment particle movement for different packing patterns under varying channel slope and discharge conditions
(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-05) Kethavath, Ajaykumar; Akhilesh Kumar
Sediment particle movement depends on not only the discharge and surface topography but also on the inherent properties of sediment particle including its shape, size, specific weight apart from their orientation. The shear force exerted on a sediment particle by flowing water plays a dominant role in deciding the rate of movement. The movement of sediment particles starts only when the shear stress acting on the particle is more than the critical shear stress. A number of studies have been conducted to study initiation of particle known as the condition of incipient motion and critical shear stress. Mostly, these studies have been conducted considering sediment particle as uniform and spherical which are never met in practice. In case of non-spherical and irregular shaped particles their orientation becomes a deciding factor for the shear force acting on the particle as it varies with changing orientation under similar conditions. Similarly, in case of non-uniform sediment material, the packing pattern of the sediment particles also plays a dominant role in deciding the magnitude of acting shear force and their movement behaviour. This study was conducted to study the effect of sediment particle packing pattern on their movement speed under varying discharge and channel slope conditions. Laboratory experiments were conducted using 6 m long slope adjusting hydraulic tilting flume on artificially constructed regular shaped sediment particles. For this purpose, sediment particles of three different sizes were constructed in the laboratory and designated as P, Q and R. These particles were arranged in different packing patterns on the bed of the flume and particle movement speed were observed for selected packing patterns with five different discharges i.e.11.1 l/s/m, 15.3 l/s/m, 19 l/s/m, 23 l/s/m, and 26.7 l/s/m, and three different channel bottom slopes of 1%, 2% and 3%. In this way the experiment was conducted in total for 405 runs for different packing patterns, slope and discharge conditions. On the basis of the analysis of observed data, it was observed that in case of patterns 1R3, 2R3 and 3R3, the maximum movement of 78.61 cm/s was observed in 1R3 pattern at 3% land slope and the minimum movement was found to be 30.14 cm/s for 3R3 pattern at 1% channel slope. The maximum movement of Q particle was found to be 68.32 cm/s for 2Q3-2P3 pattern and 62.27 cm/s for 2P3-2Q3 pattern with a discharge of 26.7 l/s/m at 3% land slope. Similarly, the maximum movement speed of R particle was observed to be as 81.56 cm/s for 2 (1R3-1P3-1Q3) pattern which came down to 79.09 cm/s for 2P3-2Q3-2R3 and 78.14 cm/s for 2(1Q3-1R3-1P3) patterns at 3% channel bottom slope for a discharge of 26.7 l/s/m. In general, however, the magnitude of shear force, increased with increase in discharge for a particular packing pattern at a slope. Similarly, for a given discharge, the shear force increased with increase in channel slope. However, it was observed that for a given discharge by changing packing pattern of particles, the exposed area changed and the shear force and particle movement changed accordingly.
Open Access
Effect of additives on geotechnical properties of soil in relation to erosion under simulated rainfall conditions
(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2018-01) Joshi, Pranjay; Akhilesh Kumar
The vulnerability of soil erosion towards erosion may be reduced by having a good vegetative cover over the soil surface, slope improvement and improving soil properties so that it is not easily detached and transported. However, establishment of proper vegetative cover is time taking process as it takes time for a seed to germinate and attain maturity. As an alternative approach, if soil resistance is increased by increasing the shear strength of soil against erosive forces offered by eroding agents, the soil system will become capable of withstanding the detachment of its particles on the application of shear stress. Under this practice, an additive is mixed to the soil which increases the shear strength of soil. The additives range from biodegradable to non-biodegradable or partially biodegradable inert materials. Recently, the use of guargum polymer in agriculture has become quite popular. Some recent applications of Guar gum are in the field of drag reduction in pipes, evaporation control, soil stabilization and erosion control. Accordingly, in this study, additives namely jute fibre and guargum and their combinations were mixed with soil in different proportions to study various geo-technical properties such as dry density, optimum water content, California bearing ratio (CBR) and tri-axial shear parameters. Index properties like specific gravity, grain size distribution and consistency limits and geotechnical properties such as dry density and optimum moisture content of treated and untreated soils were determined. California bearing ratio (CBR) value was used to evaluate mechanical strength of soil. There were nine treatments for which CBR values were determined. for two stages i.e., for the1st day of treatment and on the 4th day after the treatment. The tri-axial test was performed to obtain values of shear parameters at three confining pressures of 1kg/cm2, 1.5kg/cm2 and 2 kg/cm2 for a particular percentage of additives. Deviator stress was subjected from the top and the loading rate of 1.25 mm per minute was kept throughout the experiment. The unconsolidated undrained (UU) conditions were maintained throughout the experiment. For untreated soil, the value of cohesion was found to be 0.49 kg/cm2and angle of internal friction was found to be 28.66 degree on the1st day. The cohesion and angle of internal friction increased to 1.593kg/cm2and 55.35 degrees respectively on 7thday. Similarly, these values were obtained for all treatments applied to soil to determine shear parameters. To produce rainfall a small size portable rainfall simulation system was developed in the laboratory which was1m x1m in size and operated from a height of 5 meter. The simulator was calibrated for its rainfall generation capabilities which commensurate with natural rainfall conditions. The simulation system was calibrated for producing rainfall intensities of 12.8 cm/h t and 17.5 cm/h for water pressures of 0.4 kg/cm2 and 0.5 kg/cm2 which occurred almost uniformly over the entire test plot. The soil was treated with guargum having 0.3%, 0.5%, and 0.7% concentration by weight and with jute fiber having 0.3%, 0.5%, and 0.7% by weight and also with guargum and jute fiber combinations as 0.3%guargum and 0.3% Jute; 0.5% guargum and 0.5% jute; and 0.7% guargum and 0.7% jute mixture by weight. The recorded observations clearly revealed that as the value of shear strength of soil increased as the result of the applied treatments, the soil loss rate/ sediment outflow rate decreased for every combination of land slope and rainfall intensity. It was also found that for a particular value of cohesion and angle of internal friction, the runoff rate increased with rainfall intensity for every land slope while the sediment concentration and sediment outflow rate increased with rainfall intensity as well as land slope.
Open Access
Groundwater studies in lower part of Ganga-Ramganga interbasin using co-active neuro fuzzy inference system and fuzzy logic
(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2015-06) Pradhan, Sucharita; Shiv Kumar
The present study was undertaken in lower part of Ganga-Ramganga interbasin to investigate groundwater behavior, to prepare groundwater inventory for the assessment of groundwater utilization development stage and to study the comparative performance of Co-active Neuro Fuzzy Inference System and Fuzzy Logic rule based model to predict the seasonal depth to water table. Four groundwater models were developed using net groundwater recharge, net groundwater discharge and previous water table depth as input parameters in which model 1 andmodel 2 were developed using seasonal data and model 3 and model 4 were developed using annual data as input for both pre-monsoon as well as post-monsoon seasons. Neuro Solution 5.0 software with 71 % of total data having two to four Gaussian membership function was used for identification of most efficient network among 5 different CANFIS structure whereas Fuzzy Logic Toolbox with MATLAB R2010a was used to develop Fuzzy Logic rule based models. During the study period of 23 years, two hydrograph stations were on rising water table trend; eight hydrograph stations were neither on rising nor falling water table trend and nineteen hydrograph stations were found to be on falling water table trend during both pre-monsoon and post-monsoon seasons. The water table trend for rest hydrograph stations was not same during pre-monsoon and post-monsoon seasons. Numbers of minor irrigation structures like private tube wells and pump sets on bore wells along with area irrigated by different minor irrigation structures were increasing at an alarming rate. The cropping pattern revealed an increasing trend of area under high water demanding crops like rice and wheat while area under all minor crops except vegetables were found to be decreasing. The groundwater inventory indicated that during the study period, out of 25 blocks of study area, 22 blocks transformed from lower category to higher category of groundwater utilization development stage. The values of performance indicator such as R2, MAD, RMSE, CVRE, CE, r, APE and PI were calculated to evaluate the performance of CANFIS and Fuzzy Logic rule based models. Based on the values of performance indicator for CANFIS models, model 3 with CANFIS-2 structure and model 4 with CANFIS-1 structure were selected for prediction of depth to water table of pre-monsoon and post-monsoon seasons respectively. Further on the basis of values of performance indicator for Fuzzy Logic rule based models, model 3 and model 4 were selected for prediction of depth to water table of pre-monsoon and post-monsoon seasons respectively. By comparing CANFIS and Fuzzy Logic models on qualitative and quantitative basis, Fuzzy Logic rule based models were found to be better than CANFIS models. It was also concluded that, even though the results of CANFIS models were not as accurate as that of Fuzzy Logic rule base models, still CANFIS models confirmed its potential to recognize the trend of depth to water table during the period of study.

Theses

Browse

Thesis Type

Type

Author

Date

Subject

Search Results