Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
10 results
Search Results
Item Hierarchical clustering algorithm for land cover mapping using satellite images(2012) Senthilnath, J.; Omkar, S.N.; Mani, V.; Tejovanth, N.; Diwakar, P.G.; Archana Shenoy, B.This paper presents hierarchical clustering algorithms for land cover mapping problem using multi-spectral satellite images. In unsupervised techniques, the automatic generation of number of clusters and its centers for a huge database is not exploited to their full potential. Hence, a hierarchical clustering algorithm that uses splitting and merging techniques is proposed. Initially, the splitting method is used to search for the best possible number of clusters and its centers using Mean Shift Clustering (MSC), Niche Particle Swarm Optimization (NPSO) and Glowworm Swarm Optimization (GSO). Using these clusters and its centers, the merging method is used to group the data points based on a parametric method (k-means algorithm). A performance comparison of the proposed hierarchical clustering algorithms (MSC, NPSO and GSO) is presented using two typical multi-spectral satellite images - Landsat 7 thematic mapper and QuickBird. From the results obtained, we conclude that the proposed GSO based hierarchical clustering algorithm is more accurate and robust. © 2012 IEEE.Item Integration of speckle de-noising and image segmentation using Synthetic Aperture Radar image for flood extent extraction(Indian Academy of Sciences, 2013) Senthilnath, J.; Handiru, H.V.; Rajendra, R.; Omkar, S.N.; Mani, V.; Diwakar, P.G.Flood is one of the detrimental hydro-meteorological threats to mankind. This compels very efficient flood assessment models. In this paper, we propose remote sensing based flood assessment using Synthetic Aperture Radar (SAR) image because of its imperviousness to unfavourable weather conditions. However, they suffer from the speckle noise. Hence, the processing of SAR image is applied in two stages: speckle removal filters and image segmentation methods for flood mapping. The speckle noise has been reduced with the help of Lee, Frost and Gamma MAP filters. A performance comparison of these speckle removal filters is presented. From the results obtained, we deduce that the Gamma MAP is reliable. The selected Gamma MAP filtered image is segmented using Gray Level Co-occurrence Matrix (GLCM) and Mean Shift Segmentation (MSS). The GLCM is a texture analysis method that separates the image pixels into water and non-water groups based on their spectral feature whereas MSS is a gradient ascent method, here segmentation is carried out using spectral and spatial information. As test case, Kosi river flood is considered in our study. From the segmentation result of both these methods are comprehensively analysed and concluded that the MSS is efficient for flood mapping. © Indian Academy of Sciences.Item Geo-statistical analysis of groundwater quality in an unconfined aquifer of Nethravathi and Gurpur river confluence, India(Springer Science and Business Media Deutschland GmbH, 2018) Sylus, K.J.; Ramesh, H.The groundwater quality plays a vital role in domestic, industrial and agricultural water supply. However, seawater intrusion was one of the major problems occur worldwide in the coastal aquifers due to excessive pumping of fresh groundwater. Thus, groundwater gets contaminated due to seawater intrusion, disposal of industrial waste etc. Due to this reason, it becomes necessary for regular monitoring of groundwater quality, in order to take proper measures for avoiding and reducing contamination. Hence, the present study was aimed to assess water quality in Nethravathi and Gurpur river confluence, located on the west coast of India. Groundwater samples were collected for the month of January 2013–May 2017, which was further analysed in the laboratory as per Bureau of Indian Standards (BIS) and World Health Organisation (WHO) standards. The water quality parameters considered for analysis are Potential Hydrogen (pH), Sodium (Na), Potassium (K), Electrical conductivity (EC), Chloride (Cl), Total Dissolved Solids (TDS), Calcium (Ca), Magnesium (Mg), Total Hardness (TH) and Bicarbonate (HCO3). The results of these parameters were further mapped using Geographical Information System (GIS) to visualize spatial distribution. The geo-statistical analysis was also carried out using SPSS tool to know the correlation of these parameters. The regression analysis was carried out with Factor of sea to the chemical parameters such as Bicarbonate (HCO3), Electrical Conductivity (EC), Total Dissolved Solids (TDS), Calcium (Ca), Magnesium (Mg) and Total Hardness (TH). The significant groundwater quality chemical parameters were found by correlation analysis. The significant groundwater quality chemical parameters were further given as input for mapping, prediction and modelling of groundwater quality. The prediction of significant parameters carried out using the monthly groundwater quality data for the year 2013 and 2014. The result of spatial mapping and statistical analysis provides the spatial and temporal variation of groundwater quality in the study area. The results showed that only Panganimuguru and Kunjatbail region is affected by seawater. The modelling results of Cl and TDS shows the spatial occurrence of contamination in the study area of Netravathi and Gurpur river confluence at the various time period. Further, the results of the modelling also show that the contamination occurs up to a distance of 519 m towards the freshwater zone of the study area. © 2018, Springer International Publishing AG, part of Springer Nature.Item Modeling of surface soil moisture using C-band SAR data over bare fields in the tropical semi-arid region of India(Springer Science and Business Media Deutschland GmbH, 2021) Gururaj, P.; Umesh, P.; Shetty, A.Spatial variability of surface soil moisture is a prime factor in modeling many environmental and meteorological processes. This study aims to model surface soil moisture in bare fields using Sentinel-1A SAR data at a regional scale. The site/plot selected for the study falls in the tropical semi-arid region of Malavalli, Karnataka, India. The study site is divided into 43 grids to collect soil moisture samples from bare field plots synchronized with Sentinel-1A pass. Sentinel-1A, dual-polarized (VV and VH) data with 5.405-GHz frequency and central incidence angle of 33° are used. Six SAR imageries were procured from ESA, out of which five were used to model field soil moisture and one for validation. Processing of the SAR imageries is carried out using SNAP 7.0 software’s standard tools, and the backscattered energy of each sample grid is extracted using R software. The relation between SAR backscatter energy with soil parameters like moisture, dielectric constant, and roughness was used to model soil moisture. Results revealed that Sentinel-1A has a high potential to record the soil moisture spatial variation at the plot scale. Volumetric soil moisture and backscattered energy showed a positive correlation with R2 of 0.59 and 0.51 for VV and VH polarization. Dielectric constant also showed a positive correlation with backscattered energy having R2 of 0.54 and 0.48 for VV and VH polarization. With this knowledge, surface soil moisture is modeled over bare fields and mapped. Soil moisture modeled is validated using field data, which has R2 of 0.88 and RMSE of 1.93. The developed model and surface soil moisture map are helpful in regional hydrological studies and crop water requirement assessment. © 2021, Società Italiana di Fotogrammetria e Topografia (SIFET).Item Seismic Hazard Assessment and Landslide Vulnerability Mapping for Ladakh, and Jammu & Kashmir Using GIS Technique(Springer, 2023) Bhagyaraj, U.; Kolathayar, S.In the present study, earthquake-induced landslide susceptibility mapping of the two newly formed union territories of India namely Ladakh, and Jammu & Kashmir has been done based on Newmark’s methodology using GIS techniques. The vulnerability of the study area against induced seismic acceleration was estimated in terms of static safety factor (FSc). Terrain slope and Peak Horizontal acceleration (PHA) were taken as the major input for the study. Deterministic Seismic Hazard Analysis (DSHA) was carried out by considering linear seismic source model to obtain PHA at the bedrock level using a MATLAB code developed by authors. The PHA was amplified to the ground surface using appropriate site correction factors considering the B-type site class. GIS technique was employed to get slope value from Digital Elevation Models (DEM). The two union territories were divided into 30m×30m grids and the static factor of safety values required to prevent the landslide for each grid were estimated. It is observed that both Ladakh, Jammu & Kashmir are at risk of landslides caused by earthquakes, as many spots demand a critical safety factor (FSc) of greater than 1.0. It is apparent that the upper western sections of Jammu & Kashmir, which include Muzaffarabad district and parts of Punch district, are severely prone to landslides since they require FSc greater than 2.0. In comparison to other regions, the lower western region of Ladakh, near India’s political border, is demanding a high value of FSc. The map thus developed is an excellent guide to researchers for detailed study and to policymakers for taking remedial actions. © 2023, Geological Society of India, Bengaluru, India.Item Surface soil moisture modeling using C-band SAR observations at different stages of agricultural crops(Springer Science and Business Media Deutschland GmbH, 2023) Gururaj, P.; Shetty, A.; Umesh, P.Surface soil moisture (SSM) can be helpful in irrigation monitoring, water conservation, and a variety of other hydrological modeling applications. The majority of previous researches concentrated on the applicability or development of soil moisture models at only one stage of agricultural crop. The goal of this research is to model SSM of agricultural crops at different crop stages using C-band SAR data. The SSM of agricultural crops modeled include Paddy, Tomato, Sugarcane, and Maize fields. The whole crop cycle of these crops are divided into vegetative, maturity and yield stage. Field data like soil moisture, roughness, and Vegetation Water Content (VWC) were gathered in synchronization with the satellite pass over the study area. SEM’s for each crop stage is developed and compared to existing models like Oh 2004 and WCM. From the study, it is observed temporal variation of SSM is almost uniform for the whole crop cycle of sugarcane (~ 5%). But in case of other crops, SSM is high during the seedling/vegetative stage and comparatively less during the yield stage. Developed SSM models using SAR data is performing well in vegetative and maturity stage of all crops whereas in yield formation stage of maize and paddy error is comparatively high. On the hand, both developed and existing models did not perform well in case of sugarcane crop at maturity and yield stage. To the best of our knowledge, this is the only study that deals with surface soil moisture modeling of different crops and their stages at the plot scale in the semi-arid tropics. © 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.Item Spatial Mapping of Flood Susceptibility Using Decision Tree-Based Machine Learning Models for the Vembanad Lake System in Kerala, India(American Society of Civil Engineers (ASCE), 2023) Kulithalai Shiyam Sundar, P.; Kundapura, S.Floods have claimed the lives of countless people and caused significant property damage in many countries, putting their livelihoods in the jeopardy. The Vembanad lake system (VLS) in Kerala, India, has faced adverse mishappening during 2018, 2019, and 2021 floods in the state due to torrential rainfall. The goal of this research is to construct effective decision tree-based machine learning models such as adaptive boosting (AdaBoost), random forest (RF), gradient boosting machines (GBMs), and extreme gradient boosting (XGBoost) for integrating data, processing, and generating flood susceptibility maps. There are 18 conditioning parameters considered, which include seven categories and 11 numerical data. These seven categorical data were converted to numerical data, bringing the total amount of input data to 61. The recursive feature elimination (RFE) was utilized as the feature selection technique, and a total of 22 layers were chosen to feed into the machine learning models to generate the flood susceptibility maps. The efficiencies of the models were evaluated using receiver operating characteristic (ROC)-area under the ROC curve (AUC), F1 score, accuracy, and kappa. According to the results, the performance of all four models demonstrated their practical application; however, XGBoost fared well in terms of the model's metrics. For the testing data set, the ROC-AUC values of XGBoost, GBM, and AdaBoost are 0.90, whereas it was 0.89 for RF. The accuracy varied significantly among the four models, with XGBoost scoring 0.92, followed by GBM (0.88), RF (0.87), and AdaBoost (0.87). As a result, this map may be utilized for early mitigation actions during future floods, as well as for land-use planners and emergency managers, assisting in the reduction of flood risk in regions prone to this hazard. © 2023 American Society of Civil Engineers.Item Flood hazard map of the Becho floodplain, Ethiopia, using nonstationary frequency model(Springer Science and Business Media Deutschland GmbH, 2024) Tola, S.Y.; Shetty, A.Flood estimates based on stationary flood frequency models are commonly used as inputs to flood hazard mapping. However, changing flood characteristics caused by climate change necessitate more accurate assessments of the probabilities of rare flood events. This study aims to develop a flood hazard map based on the nonstationary flood frequency using a generalized extreme value distribution model for the Becho floodplain in the upper Awash River basin. The distributional location parameter was modeled as a function of rainfall amount of different durations, annual total precipitation from wet days, yearly mean maximum temperature and time as covariates. The one-dimensional Hydrological Engineering Center River Analysis System (HEC-RAS) hydraulic model with steady flow analysis was used to generate flood hazard map input, depth and velocity, and inundation extent for different return periods. The result indicated that the model as a function of rainfall, such as monthly rainfall (August) and annual wet day precipitation, provided the best fit to the observed hydrological data. Rainfall as a covariate can explain the variation in the peak flood series. The developed hazard map based on depth alone and the combination of depth and velocity thresholds resulted in more than 70% of the floodplain area being classified as a high hazard zone under 2, 25, 50, and 100-years return periods. The current study assists water resource managers in considering changing environmental factors and an alternative flood frequency model for developing flood hazard management and mitigation strategies. © The Author(s) under exclusive licence to Institute of Geophysics, Polish Academy of Sciences & Polish Academy of Sciences 2023.Item MICAnet: A Deep Convolutional Neural Network for mineral identification on Martian surface(Elsevier B.V., 2024) Kumari, P.; Soor, S.; Shetty, A.; Koolagudi, S.G.Mineral identification plays a vital role in understanding the diversity and past habitability of the Martian surface. Mineral mapping by the traditional manual method is time-consuming and the unavailability of ground truth data limited the research on building supervised learning models. To address this issue an augmentation process is already proposed in the literature that generates training data replicating the spectra in the MICA (Minerals Identified in CRISM Analysis) spectral library while preserving absorption signatures and introducing variability. This study introduces MICAnet, a specialized Deep Convolutional Neural Network (DCNN) architecture for mineral identification using the CRISM (Compact Reconnaissance Imaging Spectrometer for Mars) hyperspectral data. MICAnet is inspired by the Inception-v3 and InceptionResNet-v1 architectures, but it is tailored with 1-dimensional convolutions for processing the spectra at the pixel level of a hyperspectral image. To the best of the authors’ knowledge, this is the first DCNN architecture solely dedicated to mineral identification on the Martian surface. The model is evaluated by its matching with a TRDR (Targeted Reduced Data Record) dataset obtained using a hierarchical Bayesian model. The results demonstrate an impressive f-score of at least .77 among different mineral groups in the MICA library, which is on par with or better than the unsupervised models previously applied to this objective. © 2024Item Multi-season rice mapping using deep learning models with multitemporal Sentinel-1 SAR data in the Kuttanad Delta, Kerala(Taylor and Francis Ltd., 2025) Aishwarya Hegde, A.; Nair, M.K.; Umesh, P.; Tahiliani, M.P.Timely and precise monitoring of rice paddies is essential for sustaining production, ensuring food security, and addressing climate challenges, as rice is a significant contributor to greenhouse gas emissions. Accurate rice mapping, facilitated by Sentinel-1 SAR, unaffected by weather is used in Machine learning (ML) and Deep learning (DL) models for multiclass classification of rice cropping seasons by analysing temporal backscatter patterns. A modified Dual-Branch BiLSTM model is developed to capture VH backscatter variations across the homogeneous and heterogeneous rice-growing landscapes. The study compares the performance of ML models, Random Forest (RF) and Support Vector Machine (SVM), with DL models, BiGRU and BiLSTM-BiGRU, for mapping Rabi, Kharif, double-cropping rice fields, and non-rice areas in the Kuttanad Delta region. A thorough evaluation of the proposed models was conducted using metrics like Precision, Recall, and F1 Score to assess their effectiveness. The results show that the Modified Dual-branch BiLSTM model attains F1 scores as high as 0.97 in homogeneous regions and 0.94 in heterogeneous rice-growing landscapes, highlighting its robustness and strong generalisation in mapping rice in varied landscape areas, particularly in the cloudy tropical and subtropical regions where optical data are often not consistently available during the rice cultivation season. © 2025 Informa UK Limited, trading as Taylor & Francis Group.