iCAEED-2024
Dr. Shaik Rehana and her students presented the following papers at the 3rd International Conference on Advancements in Engineering Education (iCAEED-2024), held in Western Sydney University, Sydney, Australia, from 20-23 November 2024.
- Application of GIS in Rainwater Harvesting Potential Regions – Hyderabad Case Study –Shaik Rehana, Mohammad Shikaf Ali S, Ataur Rahman, Krishnan Sundara Rajan
Here is the summary of the research work as explained by the authors:
Rapid urbanization and population growth in metropolitan regions have led to increased demand for water resources, exerting pressure on existing water supply systems. In this scenario, Rainwater Harvesting (RWH) emerges as a viable solution to alleviate water scarcity by capturing and utilizing rainwater, thereby conserving natural water bodies. In this context, understanding the spatial distribution of RWH potential becomes crucial for implementing the same. This study aims to delineate RWH potential zones within Stormwater Zone 12 of the Greater Hyderabad Municipal Corporation (GHMC) by integrating GIS and remote sensing data along with hydrogeological features. The Analytical Hierarchy Process (AHP) was employed to assign weights to the considered factors and to calculate the correlation matrix, which is followed by Weighted Overlay Analysis (WOA) to formulate the results. In addition to topographic data such as Digital Elevation Model (DEM), Land Use/Land Cover (LULC), soil data, and socio-economic datasets were also integrated into this study. The results of this study categorized the study area into five distinct classes based on RWH capacity, namely ‘Very Low’, ‘Low’, ‘Moderate’, ‘High’ and ‘Very High’. This study revealed that the final outcomes were highly sensitive to changes in the parameters- LULC, DEM and rainfall patterns. The majority of the area was classified into moderate to low categories, with limited instances of very high potential. In urbanized areas, reduced natural infiltration capacity along with increased anthropogenic activities, impede the retention of incoming rainwater, contributing to the scarcity of areas with very high potential.
- Water Sensitive Urban Design Practices in Indian Cities: A Critical Review – Shaik Rehana, Mohammad Shikaf Ali S, Ataur Rahman, Krishnan Sundara Rajan
Here is the summary of the research work as explained by the authors:
Rapid urbanization and climate change have intensified challenges related to urban water management. Water Sensitive Urban Design (WSUD) represents an innovative approach for managing urban water resources, integrating sustainable water management practices within urban planning. This systematic review focuses on the state of WSUD research in India both at a house-hold scale to a catchment or community scale. Despite being in the early stages of WSUD implementation, India’s research highlights key themes, methodologies, and outcomes in this domain. Majority of the literatures reviewed the WSUD measures that is being practised in India from the early 19th century, which include rainwater harvesting methods, stormwater diversions, designing of permeable pavements, sustainable urban drainage systems (SuDS) etc. A considerable amount of work discusses about the improvements found in various quality and quantity-based parameters before and after WSUD implementation. The findings provide a detailed understanding of WSUD implementation and its applications, aiming to inform policymakers, practitioners, and researchers engaged in sustainable urban water management.
- Prediction of River Water Temperature using the Extreme Gradient Boosting – Tropical River System of India – Rajesh Maddu, Shaik Rehana, Ataur Rahman, Taha B.M.J Ouarda
Here is the summary of the research work as explained by the authors:
The physical, biological, and chemical properties of a river are directly influenced by its river water temperature (RWT), which also controls the survival and fitness of all aquatic organisms. Machine Learning (ML) gained popularity because of its ability to model complex and nonlinearities between RWT and its predictors compared to process-based models that require large data. The present study demonstrates a new ML approach, Extreme Gradient Boosting (XGBoost), to predict accurate RWT estimates with the most appropriate form of AT. Further, the proposed XGBoost results are compared with the Support Vector Regressor (SVR) model. The proposed modelling framework’s effectiveness is demonstrated with a tropical river system of India, Tunga-Bhadra River, as a case study. Results indicate that the XGBoost results are better than SVR for RWT prediction. The study demonstrates how ML methods can be used to generate accurate RWT predictions in river water quality modelling.
December 2024