Arohi Srivastav supervised by Dr. Rehana Shaik received his Master of Science – Dual Degree  in Computer Science and Engineering (CSE). Here’s a summary of his research work on Water quantity and quality management of a reservoir-river system using machine learning and decision support system:

Rivers are a significant and low cost source of drinking, irrigation and other water demands across the world. With rising industrial and residential water demands it becomes essential to manage the water quality and quantity of rivers. The changes in global environmental factors have adversely affected the natural water cycle which in turn has resulted in variation of the natural inflow to river systems. While rapid urbanization, industrialization and population growth had led to rapid decline in river water quality. Without proper management and corrective plan of action for reviving the water quality of rivers we risk losing our precious natural resources that are essential for continuance of life on earth. This study addresses these challenges within the context of altered environmental conditions that have disrupted the natural water cycle, affecting river inflows and degrading water quality. The management of water quantity in a reservoir-river system possesses challenges in terms of forecasting inflows to the reservoir and regulating releases in an adequate manner so that water demands such as irrigation, industries and households can be fulfilled. Accurate predictions of reservoir inflows is critical for water management and is influenced by various climatic phenomenon indices (e.g., Arctic Oscillation, North Atlantic Oscillation, and Southern Oscillation Index) and hydroclimatic variables (e.g., precipitation, evapotranspiration). Recently the use of machine learning techniques for inflow prediction has received a lot of attention however a comprehensive approach that evaluates different algorithms combined with large-scale climate phenomenon indices, and various hydro-climatic variables is missing. To achieve this the present study implements an integrated framework of Machine Learning (ML) algorithms for short-range reservoir inflow forecasting using the climate indices and hydroclimatic data for Bhadra reservoir situated in Karnataka, India. The present study also proposes and evaluates an ensemble model using a robust weighted voting regressor (VR) method to quantify forecasting uncertainty and to improve model performances. The results of the study reveal that the LSTM approach has the greatest influence on prediction accuracy, followed comparably by each model. However, none of the four models used in the study that are Random Forest, GBR, KNN and LSTM seem to be noticeably superior to the VR method. Accessing the water quality of rivers is a challenge and requires the measurement of several water quality parameters. Also the amount of water released from the reservoir has a significant impact on the water quality parameters downstream of the river stretch. An integrated approach for water quality management which takes into account the release of water and the river flow conditions hence becomes important. This study develops and demonstrates the usefulness of such an integrated framework. The developed framework provides a holistic approach to water quantity and quality management by integrating ML algorithms for inflow predictions, numerical methods for reservoir release analysis, Global Environmental Flow Calculator for environmental flow estimations and Qual2k as river water quality model. The developed framework can be easily used to predict and simulate how individual water quality parameters change with changes in water release from the reservoir and flow conditions of the river. In order to ensure that the developed framework can be easily put to use we develop a web application that implements the developed framework using the Bhadra river data. The developed application titled Web-Based Decision Support System for Water Quantity and Quality Management of a Reservoir-River System (WQQM-RR) integrates machine learning algorithms, numerical models, and GIS visualization techniques to predict reservoir inflow, manage reservoir release, estimate downstream water quality, and interactively visualize water quality on a map using GIS. The application uses ReactJS for a responsive and modular frontend, Flask for efficient server-side operations, Open-Street Map for dynamic data visualization, and machine learning algorithms for precise inflow predictions. Additionally, it integrates GEFC and Qual2K software for comprehensive water quality estimation. Majorly, the application consists of three major components: inflow prediction, reservoir release management, and water quality estimation with visualization. The inflow prediction module uses historical data on weather patterns, hydrological conditions, and other relevant factors to predict the inflow to the reservoir. The reservoir release management module uses these inflow predictions and storage data provided by the user to manage the release of water from the reservoir. The water quality estimation module uses the Global Environmental Flow Calculator (GEFC) and the QUAL2K water quality model to estimate various water quality parameters (e.g., pH, dissolved oxygen (DO), biochemical oxygen demand (BOD), etc.) based on the released water from the reservoir. The estimated water quality parameters are then used to calculate the Water Quality Index (WQI), which is visualized on an interactive map for easy interpretation of water quality status. The map shows the river stretch with different classes of WQI colour-coded, enabling users to easily identify areas where water quality is poor and take appropriate action to improve it. The application provides a comprehensive solution for water quality in terms of reservoir inflow prediction and water quality management, and the integration of machine learning, numerical models, and visualization techniques provides an effective tool for managing water resources in a complex and dynamic environment. Using the proposed framework we are able to predict the water quality parameters like Dissolved Oxygen(DO), Ammonia, etc. with reasonable values of Root Mean Square Error ( RMSE ) and R square (R2 ) for Bhadra river, India during the studied time period. The study also reveals that the Water Quality Index (WQI) for the Bhadra River varies throughout its stretch, ranging from 62 to 157. This range indicates that the water quality starts from poor and progresses to unsuitable for drinking when the WQI exceeds 100. Using the visualisation tool provided in the application the users can easily identify which areas on the river map are of concern and require immediate intervention to improve the river water quality. We conclude this study with the development and analysis of an alternate approach to Water Quality Index Calculation using ML algorithms on water quality parameter data. The trained ML algorithms take a subset of the water quality indices for the calculation of the water quality index (WQI). This alternative approach is helpful when we have missing data in terms of the water quality metrics that are required for calculation of WQI through traditional approaches. This is a common scenario as collecting real-time data for water quality indices is a technical as well as practical challenge because of various natural hindrances. The results of the study demonstrate that statistical machine learning models like Gradient Boosting Regressor and XGBRegressor are effective at making WQI estimation with minimum error. Combining the models using VR further improves the performance. Overall the developed models provide a reliable and convenient method to WQI estimation in the context of data limitation. The use of the integrated framework and DSS tool for water quality and quantity management developed in this study helps in designing policies and making decisions for sustainable use of water resources. The tool provides accurate predictions of reservoir inflows, optimum water release values, and detailed water quality assessments which helps water quality managers and policymakers make informed decisions for sustainable water resource management. Overall the key contributions of the study helps in ensuring that water demands are met efficiently while maintaining river water quality and health.

September 2024