Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item Examining the effects of vented dams on land use and land cover in the Shambhavi Catchment: a multitemporal sentinel imagery analysis(Elsevier Ltd, 2024) Chandana, S.; Aishwarya Hegde, A.; Umesh, P.; Chandan, M.C.The rapid expansion of the global economy has given rise to concerning ecological consequences, notably a dramatic increase in land cover change (LCC). This section presents how to use the Google Earth Engine (GEE) cloud platform to explore the administrative divisions of the Southern Indian Dakshina Kannada (DK) district, which were chosen for their LCC susceptibility. Leveraging GEE, we generated a time series dataset tracking LCC over a 4-year period (2019–22). Our findings demonstrate an impressive overall accuracy (OA) of 96.30% for 2019 and 95.47% for 2022. A significant revelation in our study is the 13.64% reduction in forested areas, accompanied by a 0.68% increase in urban development within the district. This research attempt offers vital insights into the impact of dam construction on LCC, aiding informed decisions on water resource management. This research promotes a sustainable and ecologically conscious approach to holistic development in the study region and beyond. © 2024 Elsevier B.V.Item A QGIS Plug-in for Processing MODIS Data(Institute of Electrical and Electronics Engineers Inc., 2019) Aishwarya Hegde, A.; Umesh, U.; Shetty, A.In the past few decades number of Earth-observing satellites are continuously gathering information and only about 10 percent of the information is utilized by the users. With so much accessible information the researchers have not explored the datasets completely as there is absence of effective tool to process the information. MODIS data sensors have accessible data at various temporal and spatial resolutions. To productively use these datasets in open-source GIS programming like QGIS, there is a need to pre-process the dataset using a plug-in. The plug-in is built using python and PyQt interface for QGIS.The plug-in operates on MODIS Data (Terra/Aqua/Combined) computerizes and process the functionalities for MODIS products like MOD11, MOD09, MOD21. The processed datasets can be largely used in investigation of time series analysis for some earth resource application. © 2019 IEEE.Item Experiential Learning of Strength of Materials and Fluid Mechanics using Virtual Labs(Institute of Electrical and Electronics Engineers Inc., 2020) Shetty, S.; Shetty, A.; Aishwarya Hegde, A.; Salian, A.B.; Akshaya; Umesh, P.; Gangadharan, K.V.Massive Open Online Courses (MOOCs) have revolutionized the teaching and learning process. It provides personalized learning while being cost effective and highly scalable. Furthermore, the advancements in Information and Communication Technology (ICT) have made it possible to deploy high fidelity, interactive web applications that provide seamless learning experience. However, the paucity of synergetic and adequate instructional support has demanded the quest for interactivity in MOOCs. Virtual Labs, an initiative by Government of India, aims to provide an interactive web interface to perform laboratory experiments (besides theoretical understanding of the subject) without affecting the experiential learning that is otherwise gained in the actual laboratory. This paper describes the design and development of Virtual Labs for two fundamentals courses of Civil and Mechanical engineering: Strength of Material (SOM) and Fluid Mechanics (FM). Subsequently, the outcomes of this work are discussed by analyzing the data collected from past four years, which reveals that these labs are an useful means to provide easy, cost effective and scalable solutions for online experiential learning. © 2020 IEEE.Item Experiential Learning of Physio-Chemical and Bacteriological Properties of Water using Virtual Labs(Institute of Electrical and Electronics Engineers Inc., 2020) Shetty, S.; Shetty, A.; Aishwarya Hegde, A.; Salian, A.B.; Akshaya; Umesh, P.; Gangadharan, K.V.Virtual Labs, an initiative by the Government of India under the National Mission on Education through Information and Communication Technology (NMEICT), has revolutionized the teaching and learning process for laboratory courses in the science and engineering disciplines. The web-based laboratories provided by the Virtual Labs project enable personalized learning while being cost effective and highly scalable. This approach helps to quickly learn the fundamental concepts of science and engineering through virtual experimentation, fosters curiosity and innovation among students, and prevents laboratory hazards. In this paper, we describe the design and development of two web-based virtual laboratories that simulate the fundamental concepts of Civil Engineering and Environmental Engineering. The proposed virtual labs provide a detailed explanation of the experiments in the respective engineering domains, and reagents and apparatuses involved while performing the experiments. The outcomes of this work are evaluated by analyzing the feedback collected from the users of these virtual labs, which reveals that the labs are an useful means to provide easy, cost effective and scalable solutions for online experiential learning. © 2020 IEEE.Item Comparison of Neural Networks for Binary Spatial Classification of Rice Field by Studying Temporal Pattern using Dual Polarimetric SAR Measurements(Springer, 2024) Aishwarya Hegde, A.; Umesh, P.; Tahiliani, M.P.Timely and precise information on rice cultivation plays a pivotal role in reshaping the global food and agricultural system. Synthetic aperture radar, with its capability to observe around the clock and in all weather conditions, is an invaluable tool for monitoring rice distribution. Such comprehensive cropland data at vast spatial scales not only enhances crop management but also provides critical support to governmental decision-making processes. The paper focuses on Binary classification by learning the temporal pattern of the Rice pixel. Time series curves of VV, VH, VV+VH, and VV/VH polarization and major rice varieties, MO4 and Kaje Jaya, cultivated in the area are analyzed to study the similarity of the curves the similarities in the curves, which could influence the temporal pattern recognition capacity of deep learning models. The study underscores the superior performance of RNN models, particularly BiLSTM and the proposed Dual Branch BiLSTM, over their CNN counterparts, such as 3DCNN and 3DUNET, especially for the VH and VV+VH polarizations. Specifically, the Dual Branch BiLSTM emerged as a standout, exhibiting an accuracy rate of 99.92% for combination of VH and VV+VH polarization. This model adeptly combined features from both VH and VV+VH polarizations, ensuring robust rice field mapping. Our results present a promising avenue for enhanced rice mapping, especially in tropical or subtropical zones, through the nuanced application of deep learning models. © Indian Society of Remote Sensing 2024.Item 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.