Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item Land use scenario analysis and prediction of runoff using SCS-CN method: A case study from the Gudgudi tank, Haveri district, Karnataka, India(2011) Bhagwat, N.B.; Shetty, A.; Hegde, V.S.Runoff from the Gudgudi tank catchment (209 ha) near Hangal in the Northern Karnataka is estimated employing Soil Conservation Services(SCS) model based on the hydrological data and land use/ land cover data. Rainfall measured for 2006 using a tipping bucket indicated annual rainfall of 887.7mm in the tank catchment. Textural characteristics of the soil indicate sandy-clayey type which corresponds to hydrological soil group "C and D". Average Soil infiltration rate of 0.18 cm/hour for the forest-land and 0.21 cm/hour for agriculture land has been observed. Weighted curve number is arrived based on the antecedent moisture conditions, and runoff is estimated for the existing land-use. Areastorage curve is constructed using the tank bed contours. Considering the hypothetical changes in the agriculture and forest area coverage, optimum conditions for maximizing the runoff and storage in the tank is arrived. The analysis suggests land use pattern of 15% of forest cover and 85% of agriculture land coverage in this region provide maximum runoff and storage in the tank for sustainable development. © 2011 CAFET-INNOVA TECHNICAL SOCIETY.Item Application of remote sensing and GIS for identification of potential ground water recharge sites in Semi-arid regions of Hard-rock terrain, in north Karnataka, South India(Springer Science and Business Media Deutschland GmbH, 2018) Bhagwat, T.N.; Hegde, V.S.; Shetty, A.Hydro-geomorphological characteristics, together with soil, slope, lineament density and Land use Land cover are signatures of potential ground water recharge areas, and are vital for water harvesting. In the present paper, Fifth order sub-basins in Semi-arid regions of the Varada River basin in South India is studied for selection of suitable area for recharge and prioritize the sub-basins using Indian Remote Sensing satellite (IRS) P6; Linear Imaging Self Scanning Sensor (LISS III) and ArcGIS 9.2. The Fifth order sub-basins of the Varada River spread in Hard-rock terrain and of different agro-climatic zones. The study shows that there are significant spatial variations in the fifth order basins with respect to their morphometric characteristics such as the basin area, drainage density, bifurcation ratio, and circularity ratio, constant of channel maintenance and slope of the basin. These variations reflect the differences in the hydrological process in the different Sub-basins. Based on the variations in the linear, aerial, relief as well as the slope, lineament density, and precipitation pattern rankings are assigned for each parameter with respect to ground water recharge within the Subbasins. Weighted sum overlay for precipitation, Land use, soil and Water table fluctuation are used to select the suitable areas of recharge within the sub-basins. Buffers created for lineaments and drainage networks were intersected with the suitable area of recharge for the probable tank's locations for recharge. The tank locations identified after intersection and having higher stream orders are further filtered for the identification of potential sites for ground water recharge. In the prioritized sub-basins SB-8, SB-10, SB-11 locations have been selected for recharge. © 2018, Springer International Publishing AG, part of Springer Nature.Item Assessment of surface soil moisture from ALOS PALSAR-2 in small-scale maize fields using polarimetric decomposition technique(Springer Science and Business Media Deutschland GmbH, 2021) Gururaj, P.; Umesh, P.; Shetty, A.Surface soil moisture knowledge is important, especially in agriculture and irrigation management. Properties of microwave remote sensing like penetration power and longer wavelength facilitate retrieval of surface soil moisture. ALOS PALSAR-2, quad polarized data are used to retrieve surface soil moisture using polarization decomposition techniques in a marginal farmer small-scale maize field. The focus of the study is to explore the utility of ALOS PALSAR-2 in retrieving surface soil moisture using the polarization decomposition technique. The demonstration of the study is carried out in Malavalli village, southern India, an agricultural predominant area. The study involves field soil moisture sampling in synchronous with satellite pass, measuring soil properties, preprocessing of SAR data, polarization decomposition, proportional analysis, regression analysis, model calibration and validation. Van Zyl decomposition gave the highest surface scattering component (43%) and reduced volumetric scattering component compared to Yamaguchi and Freeman–Durden decomposition. Surface scattering component of Yamaguchi decomposition gave a good coefficient of determination (R2 = 0.8029) with field-measured surface soil moisture. The semi-empirical model (SEM) was developed using surface scattering component and depolarization ratio with adjusted R2 = 0.75 at 95% confidence interval. On its comparison with existing soil moisture models, it is observed that the developed model is performing well with RMSE and AEmax of 1.81 and 2.88, respectively. Implying the applicability of ALOS PALSAR-2 in soil moisture retrieval in marginal farmer small-scale maize fields gave satisfactory results of accuracy. © 2021, Institute of Geophysics, Polish Academy of Sciences & Polish Academy of Sciences.Item Knowledge distillation: A novel approach for deep feature selection(Elsevier B.V., 2023) C, D.; Shetty, A.; Narasimhadhan, A.V.High dimensional data in hyperspectral remote sensing leads to computational, analytical, and storage complexities. Dimensionality reduction serves as an efficient tool to remove redundant, irrelevant, and highly correlated features. Recently, deep learning approaches have received remarkable progress in hyperspectral data analysis. In this paper, a new end-to-end deep learning framework based on a teacher-student network inspired by knowledge distillation is proposed for deep feature selection. Initially, a complicated teacher deep neural network is employed on complex high dimensional data to learn its corresponding best low dimensional representation. Then, the knowledge from the network is transferred to a simple student network that performs feature selection. Hence, it eventually leads to deep neural network compression which is of prime concern in hyperspectral remote sensing. Limited studies have been carried out to explore the benefits of knowledge distillation on hyperspectral data. The proposed method could be employed to choose deep features for both supervised and unsupervised tasks. Experimental results reveal the performance of the proposed scheme using limited features. In comparison to 1D and simple autoencoder models, the 2D model based on convolutional autoencoder delivers greater classification accuracies, with a classification accuracy value of 96.15% for the Indian Pines dataset and 97.82% for the Pavia University dataset. A similar trend is reported with unsupervised learning as well. Furthermore, the proposed model has a low degree of sensitivity to parameter selection. © 2022 National Authority of Remote Sensing & Space Science