Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item Identification and characterization of hydrothermally altered minerals using surface and space-based reflectance spectroscopy, in parts of south-eastern Rajasthan, India(Springer Nature, 2020) Chattoraj, S.L.; Sharma, R.U.; Kumar, C.; Champati Ray, P.K.; Sengar, V.Imaging spectroscopy has evolved as one of the most significant advancements due to contiguous spectral coverage and higher spectral resolution which enable mineral identification and mineral exploration. Many phyllosilicate and carbonate minerals show specific spectral absorption feature in the wavelength range of visible-to-near-infra-red region of electromagnetic spectrum. These spectral features enable delineation of different mineral assemblages which in turn help in mineral prospecting using hyperspectral imaging spectra. The present study is focussed on evaluation and application of EO-1 Hyperion (hyperspectral) data as an Earth Observation tool for mineral detection and mapping in parts of Udaipur district in south-eastern Rajasthan. Hyperion reflectance imagery of this area was analysed using spectral angle mapper after pre-processing, atmospheric correction and geometric correction. Five endmembers, viz. dolomite, montmorillonite, chlorite, phlogopite and serpentine, were derived from both atmospherically corrected image and from rock samples in the laboratory using ASD field spectroradiometer covering spectral range of 0.4–2.5 µm. The reflectance spectra of endmembers derived from satellite image were initially compared with USGS mineral spectral library, and then after comparing with laboratory-based spectra with respect to absorption features, target minerals were identified which shows more than 70% match with the USGS and laboratory spectra. These minerals were also cross-checked with the reported litho-sequence of the area. Minerals derived from laboratory and image spectra are indicative of hydrothermally altered outer thermal aureole which is also corroborated by litho-structural association of the area. © 2020, Springer Nature Switzerland AG.Item V3O2: hybrid deep learning model for hyperspectral image classification using vanilla-3D and octave-2D convolution(Springer Science and Business Media Deutschland GmbH, 2021) Mohan, A.; Sundaram, V.Remote sensing image analysis is an emerging area of research and is used for various applications such as climate analysis, crop monitoring and change detection. Hyperspectral image (HSI) is one of the dominant remote sensing imaging modalities that captures information beyond the visible spectrum. The evolution of deep learning has made a significant impact on HSI analysis, mainly for its classification. The spatial–spectral feature-based classification model improves the classification accuracy of hyperspectral images (HSIs). However, these models are computationally expensive, and redundancy exists in the spatial dimension of features. This research work proposes a hybrid convolutional neural network (CNN) for HSI classification. The proposed model uses principal component analysis (PCA) as a preprocessing technique for optimal band extraction from HSIs. The hybrid CNN classification technique extracts the spectral and spatial features using three-dimensional CNN (3D CNN). These features are fed into a two-dimensional CNN (2D CNN) for further feature extraction and classification. The redundancy in spatial features of the hybrid CNN model is reduced by octave convolution (OctConv) instead of standard vanilla convolution. OctConv factorizes the spatial features into lower and higher spatial frequencies, and different convolutions are performed on them based on their frequencies. The hybrid model is compared against various state-of-the-art CNN-based techniques and found that the accuracy is boosted with a lesser computational cost. © 2020, Springer-Verlag GmbH Germany, part of Springer Nature.Item Integrating Soil Spectral Library and PRISMA Data to Estimate Soil Organic Carbon in Crop Lands(Institute of Electrical and Electronics Engineers Inc., 2024) Reddy, B.S.; Shwetha, H.R.The increasing demand for precise soil organic carbon (SOC) monitoring in croplands is crucial for food security (SDG 2), and has led to the exploration of fusing soil spectral libraries (SSLs) with hyperspectral sensing data for SOC estimation. However, the widespread adoption of SSL for SOC estimation faces challenges, particularly in developing nations, due to inconsistent calibration libraries and reliable estimation models. Furthermore, SSL rely on regular soil sample collection and spectral data recording using spectroradiometers, which is impractical in agricultural-predominant countries, such as India, with limited time for sample collection between crop rotations. To address this challenge, we developed synthesized SSL in laboratory conditions and integrated it with hyperspectral data using machine learning (ML) algorithms to bridge the gap between synthesized SSL and hyperspectral data for local-scale SOC mapping. This approach was tested by mapping SOC in Mysore, India, using spectroradiometer hyperspectral measurements and PRISMA sensor data. The proposed approach and synthesized SSL exhibited better performance prediction accuracies, R2 of 0.92 and 0.79, and the RMSE values of 2.31 and 9.91 g/kg, respectively, for PRISMA and laboratory spectroscopy data. These results highlight the potential of synthesized SSL for SOC prediction in alluvial soils, leveraging local datasets, and hyperspectral data. Our future work will expand the synthesis approach to other study areas, particularly those with alluvial soil origins, further enhancing the applicability of this methodology for SOC estimation and aiding food security efforts. © 2004-2012 IEEE.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. © 2024