Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
10 results
Search Results
Item Multi-spectral satellite image classification using Glowworm Swarm Optimization(2011) Senthilnath, J.; Omkar, S.N.; Mani, V.; Tejovanth, N.; Diwakar, P.G.; Shenoy B, A.This paper investigates a new Glowworm Swarm Optimization (GSO) clustering algorithm for hierarchical splitting and merging of automatic multi-spectral satellite image classification (land cover mapping problem). Amongst the multiple benefits and uses of remote sensing, one of the most important has been its use in solving the problem of land cover mapping. Image classification forms the core of the solution to the land cover mapping problem. No single classifier can prove to classify all the basic land cover classes of an urban region in a satisfactory manner. In unsupervised classification methods, the automatic generation of clusters to classify a huge database is not exploited to their full potential. The proposed methodology searches for the best possible number of clusters and its center using Glowworm Swarm Optimization (GSO). Using these clusters, we classify by merging based on parametric method (k-means technique). The performance of the proposed unsupervised classification technique is evaluated for Landsat 7 thematic mapper image. Results are evaluated in terms of the classification efficiency - individual, average and overall. © 2011 IEEE.Item Analysis of Land Use Land Cover Change Detection Using Remotely Sensed Data for Kali River Basin(Springer Science and Business Media Deutschland GmbH, 2024) Sreejith, K.S.; Kumar, G.P.; Dwarakish, G.S.For the last two centuries, the Earth's land cover has undergone fast change, and all indications indicate that this trend will continue. This shift is being driven by economic development and population expansion. For the management of natural resources and the observation of environmental changes, land use and land cover (LULC) change has become a key element. Natural landscapes have undergone significant change as a result of anthropogenic activity, particularly in areas where population increase and climate change have a significant impact. To effectively manage the environment, especially water management, it is essential to understand how trends in land use and land cover (LULC) change. This study used remote sensing and geographic information systems (GIS) to examine changes in LULC patterns during a 20-year period in the Kali River Basin. LULC changes were mapped using multitemporal Landsat series satellite images. Landsat-5 image of 2002 and Landsat-8 image of 2022 were obtained for the purpose of the study. Maximum likely hood algorithm was used to detect areas of change with supervised classification, performed in ERDAS Imagine 2014 and took minimum of 100 samples and maximum of 250 samples of ground truth data for each class. The supervised classification produced good results with overall accuracies of 91.58% and 89.47% for the 2002 and 2022, respectively. The results of the change detection analysis conducted between 2002 and 2022 demonstrate the extent of LULC changes that have taken place in various LULC classes, while the majority of the river basin's grassland, barren land, and open forest have undergone intensive conversion to cultivated land and built-up areas. These modifications show that population growth was responsible for the rise in cultivated land and built-up areas. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.Item Land-use land-cover changes in east singbhum mineralized zone: A case study(2011) Kashinath, P.; Deb, D.; Vardhan, H.; Mangalpady, M.; Samanta, B.Remote sensing images and techniques are widely used for environmental monitoring, climate changes, forest management and for water resource management. In the present work, identification of land-use land-cover (LULC) changes was studied based on Landsat Satellite (MSS) and IRS Satellite (LISS-III) images by Maximum Likelihood Classification (MLC) method. The study finds that the areas of water bodies and dense forest have decreased by more than 11 % and 6 %, respectively, while area covered by vegetation and habitats have increased by 16 % and 5 %, respectively. It was also found that dense forest was increased by 30 % around Norwapahar mine site area.Item Comparison of various pan-sharpening methods using Quickbird-2 and Landsat-8 imagery(Springer Verlag service@springer.de, 2017) Pushparaj, J.; Hegde, A.V.Pan-sharpening is the process of transferring the spatial resolution of panchromatic (PAN) image to a multispectral (MS) image for producing a single image with high spatial detail and rich spectral information. In this study, PAN and MS imagery of Quickbird-2 and Landsat-8 are fused separately, using ten different pan-sharpening methods such as principal component analysis (PCA), modified-intensity hue saturation (M-IHS), multiplicative, brovey transform (BT), wavelet-principal component analysis (W-PCA), hyperspectral color space (HCS), high-pass filter (HPF), Gram-Schmidt (GS), Fuze Go, and non-subsampled contourlet transform (NSCT). The effectiveness of these techniques is assessed and compared by qualitative analysis and 14 quantitative analysis methods including bias, correlation coefficient (CC), difference in variance (DIV), relative dimensionless global error in synthesis (ERGAS), universal image quality index (Q), relative average spectral error (RASE), root mean square error (RMSE), structural similarity index method (SSIM), signal-to-noise ratio (SNR), peak SNR (PSNR), spatial correlation coefficient (SCC), image entropy (E), and gradient and quality with no reference image (QNR). The results of both analysis types show that the Fuze Go and NSCT produced the best fused image with high spatial detail and rich spectral information followed by the HPF and GS. © 2017, Saudi Society for Geosciences.Item Estimation of daily actual evapotranspiration using vegetation coefficient method for clear and cloudy sky conditions(Institute of Electrical and Electronics Engineers, 2020) Shwetha, H.R.; Nagesh Kumar, D.N.Actual evapotranspiration (AET) can be studied and estimated using remote-sensing-based methods at multiple spatial and temporal scales. Reflectance and Land surface temperature are essential in these methods. However optical and thermal sensors fail to provide these data under overcast conditions and this creates gap in the AET product. Besides, there is a necessity of the AET method that requires less data and estimates AET with better accuracy. In this regard, AET was estimated for all-sky conditions using the vegetation coefficient (VI-Kv) method utilizing microwave, thermal, and optical data. Essential reference evapotranspiration (ET0) under cloudy conditions was estimated using LST-based Penman-Monteith temperature (PMT) and Hargreaves-Samani equations. Furthermore, LST predicted using the microwave polarization difference index (PLST) and LST of moderate resolution imaging spectroradiometer (MODIS) cloud product (MLST) were evaluated with in-situ air temperature (Ta) under cloudy sky conditions. Results revealed that the PLST correlated better with Ta than MLST with correlation coefficient (r) values of 0.71 and 0.81 for day and night times, respectively. Hence, PLST-based solar radiation (Rs) estimation yielded better accuracy with observed Rs with r and root mean square error values of 0.864 and 0.07 for Berambadi station under cloudy conditions, respectively. PMT-based ET0 values corresponded well with the observed ET0 under cloudy sky condition during this study. In addition, AET estimated using the VI-Kv method was compared with the simple two-source energy balance (TSEB) method under clear sky conditions. It was found that the improved VI-Kv method performed better than the TSEB method and could also fairly estimate AET even under cloudy sky conditions. © 2008-2012 IEEE.Item Exploring the relationship between LST and land cover of Bengaluru by concentric ring approach(Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2020) Govind, N.R.; Ramesh, H.The present study aims at investigating the impact of land cover features in enhancing or mitigating Land Surface Temperature (LST) in a semi-arid tropical metropolitan city of Bengaluru, India. Spatial distribution of LST and land cover types of the area were examined in the circumferential direction, and the contribution of land cover classes on LST was studied over 28 years. Urban growth and LST were modelled using Landsat and MODIS data for the years 1989, 2001, 2005 and 2017 based on the concentric ring approach. The study provides an efficient methodology for modelling and parameterisation of LST and urban growth by fitting an inverse S-curve into urban density (UD) and mean LST data. In addition, multiple linear regression models which could effectively predict the LST distribution based on land cover types were developed for both day and night time. Based on the analysis of remotely sensed data for LST, it is observed that over the years, urban core area has increased circumferentially from 5 to 10 km, and the urban growth has spread towards outskirts beyond 15 km from the city centre. As urban expansion occurs, the area under the study experiences an expansive cooling effect during day time; at night, an expansive heating effect is experienced in accordance with the growth in UD in the suburban area and outskirts. The regression models that were developed have relatively high accuracy with R2 value of more than 0.94 and could explain the relationship between LST and land cover types. The study also revealed that there exists a negative correlation between urban, vegetation, water body and LST during day time while a positive correlation is observed during night. Thus, this study could assist urban planners and policymakers in understanding the scientific basis for urban heating effect and predict LST for the future development for implementing green infrastructure. The proposed methodology could be applied to other urban areas for quantifying the distribution of LST and different land cover types and their interrelationships. © 2020, Springer Nature Switzerland AG.Item Inter comparison of post-fire burn severity indices of Landsat-8 and Sentinel-2 imagery using Google Earth Engine(Springer Science and Business Media Deutschland GmbH, 2021) Konkathi, P.; Shetty, A.Forest fires are significant catastrophic events that affect the landscape and vegetation in forested lands. They cause loss of biodiversity, land degradation & ecological imbalance. As the forest fires cause extreme damage to the habitat, it is of utmost necessity to assess the impact of fire on canopy/vegetation. Post-fire assessment is an essential element for finding the effects of fire on vegetation and implementing mitigation strategies. In this article, a Post-fire burn severity assessment was carried out with high-resolution multi-spectral images such as Sentinel-2 and Landsat-8 employing Google Earth Engine (GEE) to locate the burnt areas and fire severity. Three commonly used fire severity indices based on pre-fire Normalized Burn Ratio (NBR) and post-fire NBR, namely differenced Normalized Burn Ratio (dNBR), Relativized Burn Ratio (RBR), and Relativized dNBR (RdNBR) are computed and compared based on their accuracy with the active fire points provided by MODIS & VIIRS. Both Sentinel-2 and Landsat-8 exhibited a similar trend in mapping burn severity. The RdNBR resulted in high accuracy over heterogeneous landscapes with 61.52% for Sentinel-2 and 64.1% for Landsat-8 followed by dNBR (41.67% for Sentinel-2 and 47.44% for Landsat-8) and weak performance by RBR with 32.69% for Sentinel-2 and 26.92% for Landsat-8. Hence RdNBR burn severity maps are considered highly appropriate for mapping burnt areas. Even though severity analysis from both Sentinel-2 and Landsat-8 is at an acceptable level, the Landsat based burn severity maps provided an adequate assessment of the degree of damage. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature.Item Remote sensing and machine learning based framework for the assessment of spatio-temporal water quality in the Middle Ganga Basin(Springer Science and Business Media Deutschland GmbH, 2022) Krishnaraj, A.; Honnasiddaiah, R.Understanding the dynamics of water quality in any water body is vital for the sustainability of our water resources. Thus, investigating spatio-temporal changes of dominant water quality parameters (WQPs) in any study is indeed critical for proposing the appropriate treatment for the water bodies. Traditionally, concentrations of WQPs have been measured through intensive fieldwork. Additionally, many studies have attempted to retrieve concentrations of WQPs from satellite images using regression-based methods. However, the relationship between WQPs and satellite data is complex to be modeled accurately by using simple regression-based methods. Our study attempts to develop a machine learning model for mapping the concentrations of dominant optical and non-optical WQPs such as electrical conductivity (EC), pH, temperature (Temp), total dissolved solids (TDS), silicon dioxide (SiO2), and dissolved oxygen (DO). In this context, a remote sensing framework based on the extreme gradient boosting (XGBoost) and multi-layer perceptron (MLP) regressor with optimized hyper parameters (HPs) to quantify concentrations of different WQPs from the Landsat-8 satellite imagery is developed. We evaluated six years of satellite data stretching spatially from upstream to downstream Ankinghat to Chopan (20 stations under Central Water Commission (CWC), Middle Ganga Basin) for characterizing the trends of dominant physico-chemical WQPs across the four clusters identified in our previous study. Through the developed XGBoost and MLP regression models between measured WQPs and the reflectance of the pixels corresponding to the sampling stations, a significant coefficient of determination (R2) in the range of 0.88–0.98 for XGBoost and 0.72–0.97 for MLP were generated, with bands B1–B4 and their ratios more consistent. Indeed, these findings indicate that from a small number of in-situ measurements, we can develop reliable models to estimate the spatio-temporal variations of physico-chemical and biological WQPs. Therefore, models generated from Landsat-8 could facilitate the environmental, economic, and social management of any waterbody. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.Item Integrated spatial and temporal variability of the system water use efficiency in a lower Baro River watershed, Ethiopia(IWA Publishing, 2023) Befikadu, F.; Shetty, A.; Fufa, F.The Baro Akobo River is representative of lower Baro watersheds with lost soils. Under eight landscapes, the geospatial and temporal variability of system water use efficiency (sWUE) were examined in a total area of 20,325 km2. This study used GIS, RS, Cropwat8.0, and EasyFit software. The anticipated irrigation requirement for the selected crop’s driest five months of May, February, March, January, and April was 1, 0.9, 0.78, 0.78, and 0.34 l/s/h, respectively. The sub-catchment had maximum critical test values of σ = 12.6, μ = 11.9, and γ = 0, while Sor Metu showed the smallest value of 0.80, 1.75, and 0.03. Across the watershed, the sWUE varies with runoff, with a coefficient of variation of 71%. The overall accuracy of the land cover change was 81%, the Landsat 8 images of the soil-adjusted vegetation index showed a maximum value of 0.87 and a minimum of 1.5. The normalized vegetation index ranged from a maximum of 0.58 to a minimum of 1. By 2050, the sWUE will be 10% lower temporally, but its spatial variability will be 25% higher. Therefore, soil infiltration and water storage improve, which decreases runoff and the water lost by ET and raises sWUE. © 2023 The Authors.Item INFLUENCE OF LAND USE LAND COVER CHANGE ON RUNOFF CHARACTERISTICS OF NETRAVATHI RIVER CATCHMENT, KARNATAKA, INDIA(Zibeline International Publishing Sdn. Bhd., 2024) Dwarakish, G.S.; Pai, J.B.; Jubina, C.K.The effect of LU/LC on the streamflow characteristics of the Netravathi river basin, Karnataka, India, is studied using Soil and Water Assessment Tool (SWAT) model. Landsat images, soil map from FAO, ASTER DEM (30m grid) and streamflow data, forms the database for the present work. The most significant changes from 1981 to 2015, in the LU/LC includes agricultural land (31.86%), built-up area (67.9%), forest cover (-20.01%), coconut plantation (55.12%), other vegetation (-18.55%) and others (-11.82%). The verification of performance of model was carried out by the coefficient of determination values (R2 > 0.8) and N S E (NSE > 0.78) were obtained and hence proved that SWAT model performance in estimating streamflow.. The average streamflow is increased by 13.74% from 1981 to 2015, which is mainly due to dynamic changes in LU/LC. Hence, it can be concluded that changes in LU/LC have a direct impact on streamflow in the study area. © 2024, Zibeline International Publishing Sdn. Bhd.. All rights reserved.