Department of Civil Engineering

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1927

Browse

Author: search.filters.author.Gupta, Rajiv

Search Results

Now showing 1 - 10 of 89
  • No Thumbnail Available
    Item
    Evaluating machine learning classifiers for irs high resolution satellite images using object-based and pixel-based classification techniques
    (Springer, 2024-12) Gupta, Rajiv
    Satellite imagery has provided the top view for solving many engineering, agriculture, water resources, disaster response, and environmental monitoring problems. The top view requires the classification of real-world objects from satellite images. Broadly two image classification approaches are used: pixel-based and object-based. The pixel-based classification approach primarily works on spectral characteristics and ignores spatial features, whereas object-based classification operates on both spectral and spatial features. The current work examines object-based and pixel-based methods for high resolution satellite images of novel Cartosat − 2E and Cartosat-3 satellites using machine learning classifiers (Support Vector Machines (SVM), Decision Trees (DT), Random Forest (RF), k-Nearest Neighbour (kNN) and Bayes). The study identified that decision tree classifier outperformed other classifiers under object-based approach with kappa coefficient higher than 0.90. On the other hand, for pixel-based approach kNN and SVM classifiers outperformed the other classifiers for Cartosat – 2 and Cartosat – 3 images. However, for Linear Imaging Self Scanning (LISS)-4 image Bayes, SVM and kNN performed relatively better than RF and DT. The model parameters of the machine learning classifiers may be altered or fine-tuned to increase predictive performance for object-based and pixel-based image classification techniques.
  • No Thumbnail Available
    Item
    Laboratory manual for civil engineering
    (CBS Publishers, 2019) Gupta, Rajiv
  • No Thumbnail Available
    Item
    Construction planning and technology
    (CBS Publishers, 2013) Gupta, Rajiv
    The book js a supplementary to the course in which all the building materials components of a building (doors windows finish staircase etc.) are taught. The author feels that these components can be understood if one goes through them. This is the reason for not including these topics in this book. These topics can be found in any book dealing with construction and building materials. In the text Costing and Estimation is covered in chapter one which is the first phase of planning to execute a project. After estimation CPM or PERT networks can be drawn with proper duration of the activities involved. Once network is prepared resource levelling can be done.
  • No Thumbnail Available
    Item
    Passive solar design for energy efficiency in buildings in composite climate
    (IOP, 2019) Gupta, Rajiv
    Renewable energy sources offer an unlimited supply of energy. Solar energy can be utilized to supplement energy needs of a building either passively or actively. It is feasible to reduce consumption of energy usage for heating, cooling and lighting requirements of a building by adopting a climate sensitive approach for design of building elements like static sunshade, wall and roof. To study the effect of passive building elements in composite climate zone, four rooms were designed with a different combination of type of static sunshade, wall and roof. The static sunshade and brick cavity wall with brick projections were designed using sunpath diagram and shadow angles. Air cavity was introduced in the reinforced cement concrete (RCC) roof by laying hollow stoneware pipes. This paper presents theoretical and simulation studies to compare thermal performance of the four rooms. Theoretically, the four rooms were compared by steady state method based on total heat load in every month and on representative days in different seasons throughout the year. The extreme and most frequently occurring temperature values (mode) in every season were identified by obtaining the frequency distribution of the outdoor air temperature with the software SPSS Statistics (IBM Corp. 2012). Results showed that room with designed passive elements gained minimum heat in summer and moderate summer, while it lost minimum heat in winter and moderate winter. This shows the effectiveness of the designed passive elements in insulating the room interiors from the extreme climatic conditions. The rooms were also simulated using software Autodesk Ecotect Analysis 2011 and their performance was compared on a typical day in each month. Results showed that this software can be helpful for preliminary design to get an idea about the room performance that can help to create thermally comfortable indoor environment for the well being of occupants.
  • No Thumbnail Available
    Item
    A top-down spatial scenario approach for identifying the locations of rainwater harvesting sites in an urban region
    (Springer, 2024-10) Gupta, Rajiv
    Alternative water sources are necessary in developing nations because surface water is not always accessible, and groundwater is depleted. In such situations, rainwater harvesting is considered a promising sustainable water resource management solution. Numerous studies have been conducted to determine suitable locations for rainwater harvesting (RWH) using bottom-up approaches applied to large watersheds. The bottom-up methods begin with various geographic criteria and end with regions suitable for RWH intervention, even considering the distance from settlements to be one of the criteria, excluding urban areas from RWH site identification. This study developed a top-down methodology that began with the distributed pinpoint locations of potential RWH sites, as determined by distributed flow accumulation values produced from a digital elevation model (DEM), and then filtered out the sites based on various criteria in the context of urban areas. The flow accumulation values were apportioned according to the flow-contributing area of each RWH site. Five flow-contributing areal scenarios corresponding to 1 km2, 2.5 km2, 5 km2, 7.5 km2, and 10 km2 were considered in this study, as it is challenging to choose a suitable location for RWH sites in urban zones for efficient water storage owing to a variety of land uses. Based on this technique, a case study was conducted in Jaipur, Rajasthan, India, where it was found that the volumetric potential of rainwater storage is maximum (403,679,424.9 cu. m) for 1 km2 and minimum (169,951,322 cu. m) for 10 km2 flow contributing areal distribution per RWH site.
  • No Thumbnail Available
    Item
    Comparative assessment of LSTM approaches for enhanced prediction of rainfall climatology with minimum uncertainty
    (Inder Science, 2025) Gupta, Rajiv
    Forecasting precipitation is highly challenging for scientific modellers due to the complexity and uncertainty of atmospheric data and weather prediction models. To investigate the hydrological alternations such as rising sea levels, increasing floods and evaporation, and changes in snowpack caused by climate change, it is essential to accurately predict precipitation, a function of several interrelated climatic variables. This study presents a unique approach to predicting precipitation with minimum uncertainty by performing a comparative assessment of long-short-term memory (LSTM) approaches. The LSTM prediction models were run using quarterly, semi-annual, annual, and biannual precipitation data and other data such as temperature, vapour pressure, cloud cover, rainy days, and potential evaporation. Bivariate models using potential evaporation and temperature produced equivalent results to the multivariate model as the mean absolute error (MAE) was found to be 23.89% and 26.35%, respectively, compared to the univariate model (MAE 76.29%).
  • No Thumbnail Available
    Item
    Micro-macro–scale flood modeling in ungauged channels: Rain-on-grid approach for improving prediction accuracy with varied resolution datasets
    (Elsevier, 2025-06) Srinivas, Rallapalli; Munusamy, Selva Balaji; Gupta, Rajiv
    Flood risk arises from the interplay of climatic variability, urbanization, and mitigation measures. While climatic patterns exhibit variability that may either exacerbate or mitigate flood risk across regions, urban development continues to decrease the distance between human settlements and flood-prone areas, intensifying vulnerability. This also necessitates the utilization of datasets with diverse resolutions. Although several studies have performed flood forecasting using advanced models, challenges remain in addressing specific limitations such as (a) improving the accuracy of micro–macro-scale model transitions when employing varied resolution datasets, and (b) enhancing predictive capabilities for ungauged channels. This study aims to address these challenges within the context of a case study, applying a rain-on-grid approach to link micro- and macro-scale flood predictions in a data-scarce environment. The study investigated the impact of grid size and simulation time steps for daily rainfall data on computation time and model accuracy through Geo-HECRAS. The results highlighted significant impacts on the accuracy of hydrological simulations due to variations in spatial resolution and simulation time steps. Volume accumulation error decreased from 1.49 % to 0.25 % in micro-scale scenarios and from 0.85 % to 0.006 % in macro-scale scenarios when transitioning from higher-resolution grids (5 m and 30 m) to coarser grids (10 m and 50 m) with a finer simulation time step of 15 min. While finer grids improve spatial detail, the findings suggest that coarser grid resolutions, when combined with finer temporal scales, can achieve reduced errors and optimized computational efficiency for both micro and macro-scale modeling. This approach enhances the accurate representation of flood dynamics over broader spatial scales, ensuring the reliability of predictive models. It supports the development of flood mitigation strategies and resilient infrastructure tailored to both regional patterns and site-specific hydrological conditions.
  • No Thumbnail Available
    Item
    Inception SN: An Inception based Convolutional Neural Network for Hyperspectral Image Classification
    (IEEE, 2021-10) Gupta, Rajiv
    Hyperspectral satellite imagery provides a wealth of spatial and spectral information about a given scene of interest. Therefore it is widely used in several applications like pixel-wise classification, vegetation mapping, ocean color monitoring and so on. Many pixel-wise classification algorithms like support vector machine, random forest, parallelopiped classifier, and neural networks are used for this purpose. The advent of convolutional neural networks (CNN) has brought about great development in this field, owing to their unique property of automatic feature extraction. Plain CNN architectures perform only one of pooling/convolution at each stage for feature extraction. This paper describes a new CNN architecture, the Inception SN, which makes use of both pooling and convolution at each stage to effectively extract features. It also makes use of spatial and spectral information in order to carry out classification. The outcome of this is a robust algorithm which performs well even with lower training data.
  • No Thumbnail Available
    Item
    Stability Analysis of Directional Tunnel in Sandy Soil
    (IOP, 2021-06) Gupta, Rajiv
    In recent times, water storage is becoming a confronting task because of the depletion of water resources worldwide. Domestic rainwater harvesting and human-made structures for water procurement achieved significance because of the increase in intermittent water accessibility. In turn, functional water infrastructures fetch prominence in the wake of constructive coordination among the communities in a locality. Low water security and losses through evaporation observed by practising different rainwater harvesting methods create a research gap to construct water infrastructure in rural areas to procure water productively. The current research work represents the model of a water storage structure, named directional tunnel (DT), which is placed below the ground level in a declination, as it reduces evaporation and temperature, thus storing rainwater for longer days. DT stores runoff and rainwater collected from the rooftop of multiple houses in a selected locality. The detailed working of the DT is discussed using Building Information Modelling (BIM) concept. Combined with the engineering geological characteristics, the DT's stability during water storage comes into the picture as the whole structure interacts with the soil. The current study also focuses on the behaviour of DT with respect to sandy soil using PLAXIS 3D software, and the results are interpreted for practical viability.
  • No Thumbnail Available
    Item
    Automated Bacteria Colony Counting on Agar Plates Using Machine Learning
    (ASCE, 2021-10) Gupta, Rajiv
    The identification of E. coli bacteria is critical for the prevention of health risks. According to EPA-approved gold standard methods, 24–48 h are required to count viable cells in water. Manual counting of viable bacteria colonies on agar plates is time-consuming and can be prone to human error. The method requires experts to identify and count colonies on agar plates using a microscope. Hence, the bacterial counting procedure must be automated in order to decrease error. The main objective of this study was to develop an automatic system for bacteria colony counting. A total of 1,301 groundwater samples were collected from eight districts in Rajasthan, India, for a field investigation. The results were validated using artificial intelligence (AI) methods on this experimental data set. We automated the process of E. coli bacteria identification using a convolutional neural network (CNN). We developed a smartphone application for the rapid detection of E. coli bacteria on agar plates using CNN. We also automated the process of bacteria colony counting using faster region-based convolutional neural network (R-CNN) to overcome manual cell counting process limitations. A graphical user interface (GUI) application was created to rapidly count bacteria colony–forming units on agar plates using faster R-CNN. The developed faster R-CNN model achieved an overall accuracy of 97% and an error (loss) of 0.10. The performance of the CNN and faster R-CNN models was validated using F-score, precision, sensitivity, and accuracy statistical measures. The comparative analysis showed that the faster R-CNN model is reliable and effective in E. coli cell counting. The study developed a system for identifying and counting viable cells of E. coli bacteria in water that can be used to forecast hotspots of water contamination.