Department of Civil Engineering

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

Browse

Author: search.filters.author.Srinivas, RallapalliSubject: search.filters.subject.Fuzzy logic

Search Results

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Macro and micronutrient based soil fertility zonation using fuzzy logic and geospatial techniques
    (Springer Nature, 2025-07) Srinivas, Rallapalli; Chalapathi, G.S.S.; Singh, Amit Rajnarayan
    Modeling the spatial variability and uncertainty of soil fertility parameters is crucial for sustainable agriculture but remains a challenge due to complex interactions between soil properties. Traditional models often assess individual parameters, such as pH or nitrogen (N), without considering their combined influence and uncertainty. This study develops a fuzzy logic and geoinformatics-based approach to simultaneously assess multiple soil fertility parameters. The model integrates 80 fuzzy rules to evaluate macro- and micronutrients, incorporating 250 soil samples analyzed using the PUSA Soil Test and Fertilizer Recommendation Meter (STFR). Experimental results showed soil fertility parameter ranges: pH (7.46–8.26), ECe (0.267–0.807 dS m−1), organic carbon (0.24–0.56%), N (85.56–146.32 kg ha−1), P (21.99–34.28 kg ha−1), K (116.41–156.16 kg ha−1), S (5.60–20.86 mg kg−1), Fe (1.065–5.095 mg kg−1), Mn (2.058–2.637 mg kg−1), Zn (0.748–1.105 mg kg−1), B (0.372–0.530 mg kg−1), and Cu (0.230–0.788 mg kg−1). The fuzzy model-derived fertility scores ranged from 41.55 to 52.60, with pH, organic carbon, nitrogen, phosphorus, potassium, and iron as critical parameters influencing fertility. Geostatistical kriging interpolation estimated fertility values at unsampled locations, generating a continuous, high-resolution soil fertility map for precision agriculture. Validation with crop yield data ranked suitability as: Pearl millet (0.919) > Mustard (0.890) > Wheat (0.863) > Barley (0.861). Multi-criteria decision analysis confirmed pearl millet as the most suitable crop based on fertility and yield potential. The study categorizes soil into low and moderate fertility zones across Jhunjhunu, Rajasthan, ensuring a systematic assessment for optimal nutrient management. By integrating fuzzy logic with GIS-based spatial modeling, this study enhances soil fertility classification, site-specific nutrient recommendations, and sustainable crop planning, reinforcing the role of fuzzy-GIS frameworks in precision agriculture.
  • No Thumbnail Available
    Item
    An innovative approach for predicting pandemic hotspots in complex wastewater networks using graph theory coupled with fuzzy logic
    (Springer, 2023-05) Srinivas, Rallapalli
    Early prediction of COVID-19 infected communities (potential hotspots) is essential to limit the spread of virus. Diagnostic testing has limitations in big populations because it cannot deliver information at a fast enough rate to stop the spread in its early phases. Wastewater based epidemiology (WBE) experiments showed promising results for brisk detection of ‘SARS CoV-2’ RNA in urban wastewater. However, a systematic and targeted approach to track COVID-19 virus in the complex wastewater networks at a community level is lacking. This research combines graph network (GN) theory with fuzzy logic to determine the chances of a specific community being a COVID-19 hotspot in a wastewater network. To detect 'SARS-CoV-2' RNA, GN divides wastewater network into communities and fuzzy logic-based inference system is used to identify targeted communities. For the propose of tracking, 4000 sample cases from Minnesota (USA) were tested based on various contributing factors. With a probability score of greater than 0.8, 42% of cases were likely to be designated as COVID-19 hotspots based on multiple demographic characteristics. The research enhances the conventional WBE approach through two novel aspects, viz. (1) by integrating graph theory with fuzzy logic for quick prediction of potential hotspot along with its likelihood percentage in a wastewater network, and (2) incorporating the uncertainty associated with COVID-19 contributing factors using fuzzy membership functions. The targeted approach allows for rapid testing and implementation of vaccination campaigns in potential hotspots. Consequently, governmental bodies can be well prepared to check future pandemics and variant spreading in a more planned manner.
  • No Thumbnail Available
    Item
    Development of a comprehensive fuzzy based approach for evaluating sustainability and self-purifying capacity of river Ganges
    (Taylor & Francis, 2017-11) Singh, Ajit Pratap; Srinivas, Rallapalli
    With accelerated and uncontrolled developments, large amount of untreated wastes is discharged into river water courses through various open drains. Though rivers possess self-purifying capacity, water withdrawals for different beneficial uses have impacted it significantly by reducing its flow. Presently, sustainability has also become an important affair of river basin planning and management. Therefore, assessment of behavior of river under sustainability criteria is necessary. However, the uncertainty and complexity associated with the sustainability criteria, randomness of hydrologic variables, decision-makers, and missing data have become a concern for water managers. Such problems can be modeled under fuzzy logic framework. The present work develops a comprehensive artificial intelligence approach, namely ‘MATLAB Fuzzy Inference system’ to determine the self-purifying capacity of the River Ganges. Thirty-three wastewater drains are identified, which discharge untreated wastes along Kanpur–Varanasi stretch of Ganges. Critical water quality parameters have been analyzed and impact of discharge of river at 12 sampling stations is studied. The model developed to measure the sustainability is flexible to incorporate spatial/temporal changes. Final results give emphatic information to water authorities to maintain adequate flow in the river needed to dilute the waste and also in determining the treatment technology and capacity for open drains.
  • No Thumbnail Available
    Item
    Detecting SARS-CoV-2 RNA prone clusters in a municipal wastewater network using fuzzy-Bayesian optimization model to facilitate wastewater-based epidemiology
    (Elsevier, 2021-07) Srinivas, Rallapalli; Singh, Ajit Pratap
    The current pandemic disease coronavirus (COVID-19) has not only become a worldwide health emergency, but also devoured the global economy. Despite appreciable research, identification of targeted populations for testing and tracking the spread of COVID-19 at a larger scale is an intimidating challenge. There is a need to quickly identify the infected individual or community to check the spread. The diagnostic testing done at large-scale for individuals has limitations as it cannot provide information at a swift pace in large populations, which is pivotal to contain the spread at the early stage of its breakouts. Recently, scientists are exploring the presence of SARS-CoV-2 RNA in the faeces discharged in municipal wastewater. Wastewater sampling could be a potential tool to expedite the early identification of infected communities by detecting the biomarkers from the virus. However, it needs a targeted approach to choose optimized locations for wastewater sampling. The present study proposes a novel fuzzy based Bayesian model to identify targeted populations and optimized locations with a maximum probability of detecting SARS-CoV-2 RNA in wastewater networks. Consequently, real time monitoring of SARS-CoV-2 RNA in wastewater using autosamplers or biosensors could be deployed efficiently. Fourteen criteria such as population density, patients with comorbidity, quarantine and hospital facilities, etc. are analysed using the data of 14 lac individuals infected by COVID-19 in the USA. The uniqueness of the proposed model is its ability to deal with the uncertainty associated with the data and decision maker's opinions using fuzzy logic, which is fused with Bayesian approach. The evidence-based virus detection in wastewater not only facilitates focused testing, but also provides potential communities for vaccine distribution. Consequently, governments can reduce lockdown periods, thereby relieving human stress and boosting economic growth.
  • No Thumbnail Available
    Item
    Using fuzzy logic-based hybrid modeling to guide riparian best management practices selection in tributaries of the Minnesota River Basin
    (Elsevier, 2022-05) Srinivas, Rallapalli
    Riparian corridors serve as buffer zones between land and water, thereby supporting essential ecosystem services. Though riparian zones occupy around 1% of land area in midwestern USA watersheds, their management has significant societal consequences on downstream ecosystem services, such as water quantity and quality. The management of riparian zones in the Minnesota River Basin (MRB) needs a comprehensive decision support framework (DSF) to guide conservationists to invest resources efficiently. This study attempts to classify riparian zones based on three classes: stream features, riparian characteristics, and riparian functions to suggest suitable Best Management Practices (BMPs). We developed a comprehensive hybrid decision support framework (DSF) by integrating fuzzy analytical hierarchy process (AHP) and fuzzy inference system (FIS) to propose riparian BMPs based on the physical characteristics of stream, riparian zone, and desired riparian functions. The DSF accommodates the uncertainty associated with the stakeholder's perceptions towards the riparian zone classes while also accounting for continuous variation in riparian dynamics. The advantage of a hybrid model is its ability to allow the stakeholders to prioritize critical criteria belonging to the classes to ensure that they have maximum impact on the riparian BMPs proposed by the model. We have demonstrated the model using three Minnesota River tributaries at the Hydrologic Unit Code (HUC)-8, HUC-10, HUC-12 scales. Results show that BMPs such as riparian revegetation, buffer strips, wetland management, the addition of woody debris, and an increase in tree cover obtained the highest scores and occupied 35%, 25%, 15%, 10%, and 10% of the observed sites, respectively.