Loading...
Theses
Browse
10 results
Search Results
ThesisItem Open Access Predicting the Bhimtal lake water level fluctuations by using different machine learning techniques(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-11) Tripathi, Vaibhav; Kashyap, P.S.Lake water level forecasting at various time intervals using the records of past time series is an important issue in water resources planning, engineering, etc.. Variations in lake level are complex outcomes of many environmental factors, such as precipitations, direct and indirect runoffs. The future planning, management and prediction of water demand and usage should be preceded by long-term variation analysis for related parameters in order to enhance the process of developing new scenarios whether for surface-water or ground-water resources. Water level plays an important part in the community’s well-being and economic livelihoods. This study investigated the fluctuations in the water level of Bhimtal Lake in the Nainital district (India) by using different machine learning techniques. Different soft computing such as MLP based ANN, Support Vector Machine, Random Forest, Multilinear Regression and CatBoost were used to predict the daily stage. The following data required for the study spanned over 12 years (2009-2020). By using Gamma test, the best input combination of variables (rainfall and stage lagged by two days, rainfall and stage lagged by one day and present day rainfall) were determined. The performance of the calibrated models was assessed qualitatively by visual interpretation and quantitatively using statistical indicators such as coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE). The MLR and CatBoost models were found as the best models compared to ANN, SVR and RF models for prediction of daily stage of the study area.ThesisItem Open Access Modelling of standardized groundwater index using integrated remote sensing and machine learning techniques(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-11) Shomya Kumari; Deepak KumarGroundwater is an important natural freshwater reserve on which billions of habitants depend for their diverse utilization. Global water demand has far exceeded the total available water resources which in turn have put a serious concern on food security. India is one of the largest agricultural user of groundwater in the world where there has been a large scale revolutionary shift from surface water management to a widespread groundwater abstraction. Increased industrialization, rapid population growth, climate change, changes in the land use and land cover, has influenced the extensive use of groundwater which simultaneously affects the groundwater level. Groundwater drought occurs when this groundwater level falls below the critical level. In the present study, analysis of groundwater drought of the state of Bihar, India, has been carried using a drought index called Standardized Groundwater Index (SGI) and the spatial and temporal distribution of SGI has been reflected using Remote sensing and GIS approach. The rainfall and groundwater data of 38 districts of Bihar from 2002-2019 has been used and was divided seasonally into pre- monsoon, monsoon, post- monsoon and winter seasons. Further, SGI was modelled using Artificial Neural Network and Random Forest machine learning techniques with different input models. GRACE satellite water equivalent data along with rainfall and below groundwater level was used to predict SGI. Finally, the trend analysis of groundwater level data of 38 districts of Bihar for all the four seasons was studied using Mann- Kendall test statistics and Thein Sen's slope estimator. The results of SGI spatial and temporal distribution showed that districts like Aurangabad, Gaya, Buxar, Bhojpur, Kishanganj, Katihar, Kaimur, Rohtas, Nawada, Saran Chappra, Siwan, Samastipur, Supaul are prone to the critical groundwater drought condition. On comparing the performance of the two models to predict, SGI it was found that RF models performs superior than the ANN model with correlation coefficient value of (r) as 0.95. The trend analysis results showed that 45% of the districts are showing decline in the groundwater level particularly in pre-monsoon season.ThesisItem Open Access Application of machine learning techniques for rainfall-runoff modelling of Gola watershed(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-11) Singh, Abhinav Kumar; Pankaj KumarThe prediction of runoff has a significant role in water resource planning and management. There is a great need for good soil and water management system to overcome challenges of water scarcity and other natural adverse events like- floods, landslides, etc. Rainfall-runoff modelling is an appropriate approach for runoff prediction, which makes it possible to take preventive measures to avoid damage caused by natural hazards. In the present study, machine learning techniques namely: Multiple linear regression (MLR), Multiple adaptive regression splines (MARS), Support vector machine (SVM), and Random forest (RF) were used for runoff prediction of the Gola watershed, located in the south-eastern part of the Uttarakhand. The rainfall data for 12 years (2009-2020) of three rain-gauge stations (Nainital, Bhimtal & Kathgodam) and runoff data at the outlet of watershed i.e. Kathgodam were obtained from their respective irrigation departments for the analysis. Thiessen polygon method was used for the calculation of mean areal rainfall of the watershed. Gamma test was conducted to obtain the best inputs for the models. The complete dataset has been divided into training and testing datasets, where 80% of data was used in training and rest 20% was used for the testing period. The goodness of fit for the models was evaluated by root mean square error (RMSE), coefficient of determination (R2), Nash- Sutcliffe coefficient of efficiency (NSE), and percent bias (PBIAS). For runoff prediction, the overall performance-wise rankings of models were RF, MARS, SVM, and MLR. Among all four models, the RF model outperformed in training and testing periods. It can be summarized that the RF model is best-in-class and delivers a strong potential for runoff prediction of the Gola watershed.ThesisItem Open Access Effect of rainfall dynamics on solute transport and groundwater recharge for rainfed semi-arid regions(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-09) Vijay Kumar, P.; Deepak KumarIndia was the world's second largest fertilizer producer after China, and it also ranks first in fertilizer imports. Reducing fertilizer use cannot be considered a viable option in India since optimizing food output was the highest priority for the population's food and nutritional protection. Improving fertilizer usage quality by maintaining steps such as balanced nutrient distribution, good planning, and water conservation will significantly reduce fertilizer leaching beyond the root zone of crops. A detailed explanation of both water and solute flow through the vadose zone was expected to reliably forecast environmental impacts associated with human activities such as overuse of fertilizer and irrigation. This study investigated the effect of variation of climate change on solute transport and groundwater recharge for rainfed Cotton Crop using HYDRUS-1d and HYDRUS-2d in Semi-arid Region of Gopalapur in the Raichur district (India). The solute transport and reaction parameters were assessed using HYDRUS-2d at the depths of 50, 100 and 150 cm of soil horizon. while the potential groundwater recharge and cumulative bottom fluxes as well as soil water content were assessed using the HYDRUS-1D. the following input data required are Metrological data from 2015-2020, Soil data, Crop data, Soil hydraulic parameters, and Solute data respectively. The results pertaining to HYDRUS-1d showed that the potential groundwater recharge for average precipitation, 20% decreased precipitation and 20% increased precipitation were 16.66 cm, 4.33 cm, and 30.35 cm respectively. There was huge difference of groundwater recharge between 20% increased and decreased precipitation due to availability of water to percolate. Similarly HYDRUS-2d showed that solute transport for average precipitation, 20% decreased precipitation and 20% increased precipitation at 150cm depth of soil horizon was that for N is 3.21*10-5, 1.33*10-7, 6.969*10-4mmolcm-3, P is 0, 0, 2.9*10-7mmolcm-3 and K is 0, 0, 6.25*10-8 mmolcm-3 respectively. From this it can be infer that increased precipitation caused solute to move faster than at usual rate. Therefore, it is concluded that the HYDRUS model would aid in reducing fertilizer losses, improving groundwater efficiency, and ultimately lowering production costs.ThesisItem Open Access Trend analysis of climatic variables for Rajkot (Gujarat)(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-02) Mainwal, Shivani; Singh, Praveen VikramClimatic variability, particularly rainfall, air temperature, wind, relative humidity and solar radiation, has received a great deal of attention worldwide. The magnitude of the variability or fluctuations of these variables varies according to location. In the present study the variability and trend of these climate variables have been examined for Rajkot (Gujarat) during the period of 35 years from 1979 to 2013. The variability of these climatic variables has been analyzed using statistical parameters while trend analysis has been studied using non-parametric approaches such as Mann- Kendall and Sen’s slope estimator test. Statistical and trend analysis has been done for various time scale i.e. monthly, seasonal (pre-monsoon, monsoon, post-monsoon and winter) and annual basis. The average minimum and maximum value of daily rainfall, maximum temperature, minimum temperature, wind, relative humidity and solar radiation were found as 0.00mm and 22.77mm, 26.60 0C to 43.61 0C, 11.370C to 27.630C, 1.98 m/s to 5.68 m/s, 0.19 to 0.90 and 9.89 MJ/m2 to 28.03 MJ/m2. For rainfall there was an increasing trend from February to June and December and decreasing trend for the month January and July to November on monthly basis. The seasonal rainfall shows an increasing trend for winter and pre-monsoon season and decreasing trend for post-monsoon and monsoon season while it shows an increasing trend on annual basis. For maximum temperature there was an increasing trend from January to March, July, August and December and decreasing trend for April to June and September to November on monthly basis. The seasonal maximum temperature shows an increasing trend for winter and annual season while there was a decreasing trend for pre-monsoon, monsoon and post-monsoon. The minimum temperature showed an increasing trend from January to April and December and decreasing trend for May to November on monthly basis. The seasonal minimum temperature shows an increasing trend for pre-monsoon, winter and annual season while there was a decreasing trend for monsoon and post-monsoon. For wind showed an increasing trend from January to March and September to December and decreasing trend for April to august on monthly basis. The seasonal wind showed an increasing trend for pre monsoon, post monsoon and winter season while there was a decreasing trend for monsoon and annual season. The relative humidity shows increasing trend from February to June, and decreasing trend for the month of January and July to December. The seasonal relative humidity shows an increasing trend for pre monsoon, winter and annual season and decreasing trend for monsoon and post monsoon season. The solar radiation shows an increasing trend from January to March, July, August, November and December and decreasing trend for April to June, September and October on monthly basis. The seasonal solar radiation shows an increasing trend for monsoon, post monsoon, winter and annual season and decreasing trend for pre monsoon.ThesisItem Open Access Stage-discharge modelling at Gaula barrage site using different soft computing techniques(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-02) Shukla, Ravi; Pravendra KumarDevelopment of stage-discharge relationship is extremely important issue in hydrological modelling. Due to complexity of stage-discharge relationship, the discharge prediction plays an important role for planning and management of water resources. Considering these facts, a study has been carried out for modelling of discharge at Gaula barrage site. The Gaula barrage site is located in Uttarakhand, India and it is 578km long river. In the present study, artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and wavelet based artificial neural system (WANN) based models were used to estimate the discharge for study area. The daily data for monsoon period (1st June to 30th September) of 1024 days and 440 days were used to train and test the models, respectively. The Gamma test was carried out to identify the best model for discharge prediction. The input data having stage with one day lag and discharge with one and two days lag and current day discharge as output were used for discharge modelling. In case of ANN models, back-propagation algorithm and hyperbolic tangent sigmoid activation function were used. WANN used Haar a trous based wavelet function while in ANFIS models, triangular, psig, generalized bell and gaussian membership functions were used to train and test the models. The performance of the models was evaluated qualitatively by visual observation and quantitatively using correlation coefficient, root mean square error, Willmott index and coefficient of efficiency. It was found that ANFIS based model performed better than ANN and WANN based models for discharge prediction at Gaula barrage site.ThesisItem Open Access Reference evapotranspiration prediction using Heuristic approach with gamma test based on climate data(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-02) Gupta, Sanjeev; Pravendra KumarAccurate estimation of reference evapotranspiration (ETo) is critically significant in crop modelling, hydrological water simulation, irrigation scheduling and sustainable management because it accounts for more than two-thirds of global precipitation losses. Therefore, ETo based estimation is a key issue in the hydrological cycle. In this study, FAO-56 based Penman-Monteith (PM) method was used to estimate daily ETo which was considered as output to calibrate the models. Different soft computing and statistical techniques such as ANN, wavelet coupled ANN (WANN), ANFIS and MNLR were used to predict daily reference evapotranspiration in area of GKVK, Bengaluru. By using Gamma test, the best input combination of climatic variables (mean relative humidity, wind speed, sunshine hour, saturated and actual vapour pressure and solar radiation) was determined. The performance of the calibrated models was assessed qualitatively by visual interpretation and quantitatively using statistical and hydrological indicators such as coefficient of determination (R2), root mean square error (RMSE), coefficient of efficiency (CE) and Willmott index (WI). Additionally, sensitivity analysis was performed for the best developed model to see the effect of each parameter on model performance. The WANN-11 model was found as the best model compared to ANN-10, ANFIS-06 and MNLR models for prediction of reference evapotranspiration of the study area.ThesisItem Open Access Comparative study of activated carbon derived from agricultural biomass for remediation of Chromium contaminated groundwater(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-02) Bhatt, Divyanshu; Deepak KumarGroundwater contamination is a vital challenge for 21st century as most of agricultural and industrial contamination generally percolate into subsurface. In the present study, activated carbon derived from agricultural and forestry biomass has been used to remediate chromium contaminated water. For the same, batch and Fix-Bed column experiments was conducted. Four different types of activated carbon namely; Rice husk activated carbon, Pine needle activated carbon, Rice straw activated carbon and Maize residue activated carbon were prepared from rice husk, pine needle, rice straw and maize residue biomass. Agricultural biomass was collected from agricultural and forestry waste of Crop Research Centre, G. B. Pant University of Agriculture and Technology, Uttarakhand, India. Activated carbon from these biomasses was extracted by chemical activation with H3PO4 impregnation (1:2) at 600oC for 30 minutes. Biochar and activated carbons were characterized by proximate analysis and FTIR analysis. Batch and Fixed-Bed Column sorption were carried out to investigate the potential of Cr (VI) adsorption on the surface of different type of activated carbon. Adsorption study has been conducted by fixing activated carbon dosage (1g/l), pH value (4 to 5) of Cr (VI) aqueous solution and variables such as initial concentration (50 mg/l, 100 mg/l, 150 mg/l), contact time and bed height (1cm, 0.5 cm, 0.25 cm) were varied. Effect of variable has been observed on Cr (VI) adsorption efficiency of activated carbon. Results divulged that among the all biomass, rice husk has maximum production yield of activated carbon followed by rice straw and pine needle. The production yield of activated carbon ranges from 33.7% to 46.25%. Further, highest percentage (64.9%) of fixed carbon was obtained for maize residue activated carbon. Adsorption results divulged that maximum Cr (VI) adsorption efficiency (76.218%) and adsorption capacity (106.58 mg/g) were achieved with maize residue activated carbon within 120 minutes. The efficiency of adsorption increased with an increase in contact time and decreased with an increase in initial Cr (VI) aqueous sample concentration. Pine needle activated carbon was used in Fixbed column study and highest 38.96% of initial concentration (50 mg/l Cr (VI)) has been removed using 1 cm bed height.ThesisItem Open Access Studies on the effects of industrial effluents on water sources of Siidcul region, Dehradun(G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2020-10) Baljinder Singh; Kashyap, P.S.Due to rapid industrialization on one side and increasing population on the other, the demand of water supply has been increasing tremendously. Moreover a major portion of this limited quality of water is polluted by sewage, industrial waste and a wide range of synthetic chemicals. Fresh water which is a precious and limited vital resource needs to be protected, conserved and used wisely by man. But unfortunately such has not been the case, as the polluted lakes, rivers and streams throughout the world testify. For our study, the sources selected are generally used for domestic, industrial and drinking purpose. A total of 10 groundwater sites which included 7 borewell sites apart from 3 handpump sites were studied and analyzed. For surface water evaluation, 5 designated locations which are approximately 5 km apart from one another were taken into consideration. In total 15 sites were studied for their physical and chemical properties. The samples from each site were collected during winter season, post winter rains and during the summer season in 2019-20. Post sample collection, the various physical and chemical parameters like pH, TDS, EC, Acidity, Alkalinity, CO2, TH, Ca2+ , Mg2+ , Na+ , K+ and Cl– were tested using standard APHA methodology and thereafter the results were compared with the standard guideline values recommended by Bureau of Indian Standard (BIS) for drinking purpose.
