Thumbnail Image

Theses

Browse

2013 - 20195
Reset filters
Author: Amit Kumar × End date: 2019 × Start date: 2010 ×
Reset filters

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    ThesisItemOpen Access
    Comparison of MLP-ANN and W-ANN for SPI forecasting to assess meteorological drought
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2019-07) Amit Kumar; Singh, Pravin Vikram
    The accurate assessment of drought is an essential component for effective water resource management planning to mitigate adverse consequences of drought. The Standardized Precipitation Index (SPI) is a widely used index to characterize meteorological drought on a varying time scale. Information about Standardized Precipitation Index (SPI) at a place is vital for the assessment of drought. In this study, an approach to forecast Standardized Precipitation Index (SPI) has been attempted to assess meteorological drought in drought prone area of the country at different time scales. This approach involved application of Multi-Layer Perceptron Artificial Neural Networks (MLP-ANN) and Wavelet Artificial Neural Network (W-ANN) to generate Standardized Precipitation Index values for different scales and denoted as, SPI-1, SPI-3, SPI-6, SPI-9, SPI-12 and SPI-24. To generate SPI values using these two models, the data set of Prabhani district in the state of Maharashtra was considered. The total data set of calculated values of SPI during 1971 to 2014 at various time scales was divided into three sets; (i) a training set, consisting of first 36 years data from January, 1971 to December, 2006; and (ii) a testing set, consisting of 4 years data from January, 2007 to December, 2010; and (ⅲ) a validation set, consisting of remaining 4 years data from January, 2011 to December 2014 for both the approaches. The SPI values at previous six-month lag were used to forecast current month SPI values and gamma test was used to decide the best combination of inputs for SPI forecasting. Both MLP-ANN and W-ANN models trained with the Levenberg Marquardt (LM) back propagation algorithm were developed using single hidden layer. The Root Mean Square Error (RMSE), Correlation Coefficient (r) and Coefficient of Efficiency (CE) statistical indices were adopted to evaluate the performance of these models. The SPI values generated by using best developed MLP-ANN and W-ANN models were compared with calculated values of SPI. The forecasted results indicate that for SPI-1, the performance of both MLP-ANN and WANN models was not satisfactory, however, MLP-ANN based model performed better than W-ANN model. For SPI-3, 6 and 9, the performance of W-ANN model was found to be better than MLP-ANN based model. In case of SPI-12 hand SPI-24, both the models were found to be performing satisfactorily, however, WANN model has a little bit edge over MLP-ANN. Interestingly, it was observed that the performance of both these models was found to be improving with increasing SPI time scale.
  • Thumbnail Image
    ThesisItemOpen Access
    Optimization of MIG welding parameters of dissimilar metals using Artificial Neural Network (ANN) and Genetic Algorithm (GA)
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2013-07) Amit Kumar; Jadoun
    Welding is a process by which we can join two similar or dissimilar metals very efficiently. With the help of welding, success of the weld can be achieved up to 100%. Welding is more useful because it is less costly as compared to other fabrication process like casting, forming, machining. In this study dissimilar metals of stainless steel of grade 304 and stainless steel of grade 316 are used in this study. We make 27 samples at different levels. Metal inert gas (MIG) welding is used in this study for welding because MIG welding is automatic machine and even less skill worker can operate it. Phoenix 301 MIG welding machine is used for welding. Joint strength is determined using the universal testing machine (UTM). In this study Artificial neural Network is a very important tool which relates input and output.. For classification Artificial Neural Network was built which shows some inter relationship between Input and Output parameter. ANN work similarly as biological neuron does work. GA is used to optimize selected MIG welding parameters input parameter (voltage, welding speed and current) and output parameter (tensile strength). Artificial neural network and Genetic Algorithm is used to design the experiment. The results were analysed using Artificial Neural Network (ANN) which is a part of MATLAB for the optimal parameters GA tool used which also a part of MATLAB. MIG welding is also known as metal inert gas welding and gas metal-arc welding (GMAW). Gas metal arc welding (GMAW) is widely used in industry due to its high metal deposition and ease of automation with better weld quality.
  • Thumbnail Image
    ThesisItemOpen Access
    Efficacy assesment of bio-based nano materials of gypsum and rock phosphate in wheat (Triticum aestivum)
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2014-08) Amit Kumar; Rajeew Kumar
    Three field experiments were conducted during rabi season of 2013-14 at N. E. Bourlag Crop Research Centre of Govind Ballabh Pant University of Agriculture & Technology, Pantnagar, (Uttarakhand), to study the effect bio based nano materials of gypsum and rock phosphate on phenology, morphology, physiology and yield of wheat and on soil microbes. The experimental site was sandy clay loam, and had organic carbon (0.72%), available nitrogen (216 kg/ha), available phosphorus (22 kg/ha) and available potassium (133 kg/ha). The soil reaction was slightly alkaline (pH 7.3). The wheat variety UP-2526 was used as test crop. Three sets of experiment having six, twelve and twelve treatments were laid down in randomized block design with three replications. In, first set of experiment the treatments were control, 50% RDF, 100% RDF, 125% RDF, 50 & 100% RDF applied with bio based nano materials. In second and third set of experiment RDF @ 50 % and 100 % were tested with different combinations of five biological based formulated nano minerals of gypsum (second experiment) and rock phosphate (third experiment) . The formulated nano minerals were clay based, parthenium based, FYM based, neem based, Vegetable peel based formulation of nano gypsum and nano rock phosphate. Results of first experiment revealed that plant height, dry matter accumulation, SPAD reading, green seeker value and grain yield obtained at 50% RDF with bio based nano materials, was statistically similar with 100% RDF. In experiment second, Tillers/m2, SPAD value, leaf area index, yield, and economics (gross return, net return, B: C ratio) observed highest under 50% RDF applied with clay based nano gypsum. In experiment third, Tillers/m2, dry matter accumulation, leaf area index, green seeker value, straw yield and bio logical yield observed highest under 50% RDF applied with vegetable peels based rock phosphate. From these experiments, it could be concluded that wheat crop performed better under 50% RDF applied with bio based nano materials, or 50% RDF applied with clay based nano gypsum or 50% RDF applied with vegetable peels based nano rock phosphate as compared to RDF without nano minerals. Therefore, we can save 50 % of our recommended fertilizer dose.
  • Thumbnail Image
    ThesisItemOpen Access
    Response of a new cultivar of Indian mustard (rgn-73) to fertility levels
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2015-06) Amit Kumar; Mahapatra, B.S.
    In order to evaluate the growth, yield and quality of Indian mustard cultivar RGN- 73 at varying fertility levels under tarai conditions of Uttarakhand, a field experiment was conducted at the N.E. Borlaug Crop Research Centre of the G.B Pant University of Agriculture and Technology, Pantnagar (Uttarakhand) during Rabi season of 2014-15. The experiment was conducted on a silty clay loam soil with moderate availability of nutrients with twelve fertility levels of NPK (N: 60, 80 and 100kg/ha, P2O5: 20 and 40 kg/ha, K2O: 0 and 30kg/ha) with three replications. Different fertility levels of NPK did not have any significant influence on plant height at different stages of crop growth. However, dry matter accumulation, number of primary and secondary branches, LAI, CGR ant RGR showed significant effect of fertility levels applied with maximum in case of (100:40:30 N:P2O5:K2O) and minimum at lowest fertility levels (60:20:0 N:P2O5:K2O) applied. Yield and yield attributing characters along with biological yield and harvest index were also showed significant differences with fertility levels and like growth characters, highest values were also recorded in case of highest fertility levels (100:40:30 N:P2O5:K2O). At higher level of N (100 kg/ha), an increased P by 20 kg/ha and K by 30 kg/ha, resulted significant increase in seed yield of Indian mustard over 60:20:0 (N:P2O5:K2O). The similar was the results for NP and K uptake, B:C ratio. From the above study it could be inferred that N:P2O5: K2O levels of 100:40:30 produced maximum yield and showed highest B:C ratio under tarai conditions of Uttarakhand for the mustard variety RGN-73.
  • Thumbnail Image
    ThesisItemOpen Access
    Effect of nutrient sources on nitrogen mineralization, carbon storage and yield of turmeric under harda (Terminalia chebula) based agroforestry system
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2017-06) Amit Kumar; Dwivedi, G.K.
    The present investigation was carried out for two years during 2015-2017 at Agroforestry Research Centre, G.B. Pant University of Agriculture and Technology (Haldi), Pantnagar. The experiment comprised of two farming systems (Harda open system) with eight treatments viz., Control, FYM, PM, WS, Vermicompost, NPK, Integrated 100 and 50%. The experiment was laid out in split plot design (SPD) with three replications, AF systems in the main plot and nutrient sources in sub plot treatments. The soil of the experiment site was silty clay loam having pH (7.15), EC (0.35 dSm-1), OC (0.80%) and available NPK 203.47, 16.68, 155.95 kg ha-1 respectively. The result of the experiment reveal that physical and chemical properties were significantly affected by farming systems as well as nutrient sources. The bulk density was recorded lower under AF system as compared to open one. Similarly, among nutrient sources the effect of organic sources was more pronounced as compared to NPK. SOC, available NPK status were also significantly increased due to nutrient sources as well as farming systems. SOC and available NPK increased by 28.6, 10.8, 42.7 and 13.6% respectively under harda AF system as compared to open system whereas increase of 27.0, 39.0, 52.0 and 20.1% of SOC, available NPK respectively were found under 100% integrated nutrient sources. The carbon stock (25%), CO2 evolution and carbon fractions were recorded higher under AF system than open system. The higher active and passive pools comprising of very labile, labile, less labile and non labile were recorded higher under farming system and NH4+ and NO3- fractions were also greatly influenced by farming system and nutrient sources. In turmeric crop, plant height, LAI, NPK content, uptake, rhizome yield, curcumin content and curing percentage were also greatly affected by the harda tree and nutrient sources. 100% integrated nutrient source recorded highest rhizome yield and was superior by 45.81 per cent over control. However, it decreased under harda tree. Curcumin content was also higher under harda tree system by 6.57%. There was an increment in tree height, DBH and crown width of harda tree by 9.42, 9.05 and 20.19 per cent respectively at the end of study period. It was also observed that harda tree produced 2.80 t ha-1 litter during the study. Therefore, it is concluded from the study that turmeric-harda tree system is a suitable agroforestry system where the overall yield of turmeric and harda as well as quality of the turmeric was greatly improved along with considerable improvement in the carbon stock and nitrogen mineralization.